A good way to spread knowledge about Palembang songket woven cloth patterns is to use information technology, especially artificial intelligence technology. This study's main goal is to develop a ResNet model with dropout regularization methods and find out how dropout regularization affects the ResNet model for detecting Palembang songket fabric motif with more data. Data was collected in places like tujuh saudara songket, Zainal songket, songket PaSH, AMS songket, and batik, Ernawati songket, Nabilah collections, Ilham songket, and Marissa songket. We used eight class of data for this research. A dataset of 7,680 data for training, 960 data for validation, and 960 data for testing is a dataset that has been prepared to be implemented in experiments. In the final results, the experimental results for DResNet demonstrated that accuracy at the training stage was 92.16%, accuracy at the validation stage was 78.60%, and accuracy at the submission stage was 80.3%. The experimental results also show that dropouts are able to increase the accuracy of the ResNet model by adding +1.10% accuracy in the training process, adding +1.80% accuracy in the validation process, and adding +0.40% accuracy in the testing process.
{"title":"Palembang songket fabric motif image detection with data augmentation based on ResNet using dropout","authors":"Ermatita Ermatita, Handrie Noprisson, Abdiansah Abdiansah","doi":"10.11591/eei.v13i3.6883","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6883","url":null,"abstract":"A good way to spread knowledge about Palembang songket woven cloth patterns is to use information technology, especially artificial intelligence technology. This study's main goal is to develop a ResNet model with dropout regularization methods and find out how dropout regularization affects the ResNet model for detecting Palembang songket fabric motif with more data. Data was collected in places like tujuh saudara songket, Zainal songket, songket PaSH, AMS songket, and batik, Ernawati songket, Nabilah collections, Ilham songket, and Marissa songket. We used eight class of data for this research. A dataset of 7,680 data for training, 960 data for validation, and 960 data for testing is a dataset that has been prepared to be implemented in experiments. In the final results, the experimental results for DResNet demonstrated that accuracy at the training stage was 92.16%, accuracy at the validation stage was 78.60%, and accuracy at the submission stage was 80.3%. The experimental results also show that dropouts are able to increase the accuracy of the ResNet model by adding +1.10% accuracy in the training process, adding +1.80% accuracy in the validation process, and adding +0.40% accuracy in the testing process.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229070","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}
Interest in using ebooks by the academic community is very high. Still, there is a problem when readers are reading through screens, tend to read fast, only scan the necessary parts, and don't focus on paying attention to the content they read, so this reduces the quality of reading because readers don't study the overall meaning of the sentence. Hence, this research aims to build an interactive reader system by integrating eye tracker technology with a webcam which is expected to solve the problem of decreasing the quality of reading through the screen by helping readers stay focused on their reading and providing an interactive system that makes it easier for readers to control the computer while reading. This research adopts the waterfall method and is divided into six stages. The system is designed using class diagrams, use case diagrams, and activity diagrams. Also, the system is built using the Python language with the Django framework. Then, the interactive reader system was tested using black box testing and usability testing methods. Based on the test results, it is shown that the interactive reader system that was built can help improve the quality and concentration when reading activities take place.
{"title":"System interactive reader using eye-tracker technology in ebook reader","authors":"Herry Sujaini, Novi Safriadi, Dian Khairiyah","doi":"10.11591/eei.v13i3.5877","DOIUrl":"https://doi.org/10.11591/eei.v13i3.5877","url":null,"abstract":"Interest in using ebooks by the academic community is very high. Still, there is a problem when readers are reading through screens, tend to read fast, only scan the necessary parts, and don't focus on paying attention to the content they read, so this reduces the quality of reading because readers don't study the overall meaning of the sentence. Hence, this research aims to build an interactive reader system by integrating eye tracker technology with a webcam which is expected to solve the problem of decreasing the quality of reading through the screen by helping readers stay focused on their reading and providing an interactive system that makes it easier for readers to control the computer while reading. This research adopts the waterfall method and is divided into six stages. The system is designed using class diagrams, use case diagrams, and activity diagrams. Also, the system is built using the Python language with the Django framework. Then, the interactive reader system was tested using black box testing and usability testing methods. Based on the test results, it is shown that the interactive reader system that was built can help improve the quality and concentration when reading activities take place.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"7 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229352","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}
Anazel P. Gamilla, Anjela C. Tolentino, Reina T. Payongayong
Efficient load balancing is crucial for optimizing network performance and ensuring seamless connectivity in modern campus area networks (CANs). With the proliferation of data-intensive applications and the increasing reliance on cloud-based services, organizations are seeking effective load-balancing solutions to distribute network traffic evenly across available resources. The continuous improvement of devices, tools, and techniques to cater a large amount of network traffic, started to be employed on different campuses. Understanding the best approach to maximize the utilization of the network resources is crucial in order to stabilize and maintain the network. The study aims to discern the round-robin and software defined-wide area network (SD-WAN) techniques based on defined metrics and conducted with a predefined payload for commonly used application conditions. The analysis shows that SD-WAN delivers a much superior performance than round-robin based on the criteria. The local area network (LAN) test shows difference between the two types of technology for the three given metrics. The WAN test shows that the round-robin has higher packet loss, latency, and jitter than the SD-WAN technology. While round-robin may suffice for small-scale deployments with relatively homogeneous traffic patterns, SD-WAN offers more sophisticated capabilities for larger CANs with diverse application workloads and distributed locations.
高效的负载平衡对于优化网络性能和确保现代园区区域网络（CAN）的无缝连接至关重要。随着数据密集型应用的激增和对基于云的服务的日益依赖，企业正在寻求有效的负载平衡解决方案，以便在可用资源之间平均分配网络流量。为满足大量网络流量的需求，设备、工具和技术不断改进，并开始在不同的校园使用。为了稳定和维护网络，了解最大限度地利用网络资源的最佳方法至关重要。本研究旨在根据定义的指标，对循环和软件定义广域网（SD-WAN）技术进行鉴别，并针对常用的应用条件使用预定义的有效载荷。分析表明，根据标准，SD-WAN 的性能远远优于轮循技术。局域网（LAN）测试显示了两种技术在三个给定指标上的差异。广域网测试表明，轮循技术的丢包、延迟和抖动都高于 SD-WAN 技术。对于流量模式相对单一的小规模部署来说，轮循技术已经足够，而对于具有不同应用工作负载和分布式地点的大型 CAN 来说，SD-WAN 能提供更复杂的功能。
{"title":"A discernment of round-robin vs SD-WAN load-balancing performance for campus area network","authors":"Anazel P. Gamilla, Anjela C. Tolentino, Reina T. Payongayong","doi":"10.11591/eei.v13i3.5945","DOIUrl":"https://doi.org/10.11591/eei.v13i3.5945","url":null,"abstract":"Efficient load balancing is crucial for optimizing network performance and ensuring seamless connectivity in modern campus area networks (CANs). With the proliferation of data-intensive applications and the increasing reliance on cloud-based services, organizations are seeking effective load-balancing solutions to distribute network traffic evenly across available resources. The continuous improvement of devices, tools, and techniques to cater a large amount of network traffic, started to be employed on different campuses. Understanding the best approach to maximize the utilization of the network resources is crucial in order to stabilize and maintain the network. The study aims to discern the round-robin and software defined-wide area network (SD-WAN) techniques based on defined metrics and conducted with a predefined payload for commonly used application conditions. The analysis shows that SD-WAN delivers a much superior performance than round-robin based on the criteria. The local area network (LAN) test shows difference between the two types of technology for the three given metrics. The WAN test shows that the round-robin has higher packet loss, latency, and jitter than the SD-WAN technology. While round-robin may suffice for small-scale deployments with relatively homogeneous traffic patterns, SD-WAN offers more sophisticated capabilities for larger CANs with diverse application workloads and distributed locations.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"6 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230220","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}
Mahesh Kadu, Ramesh Pawase, Pankaj Chitte, V. Ubale
A design of a compact dual-band antenna for 5G application is presented in this research article. The dual-band operation includes the 3.6 GHz and 5.4 GHz frequency bands of the sub-6 GHz frequency band for 5G technology. The proposed antenna offers a compact design with satisfactory antenna performance parameters. Moreover, the dual-band antenna showcases the independent tuning ability for both frequency bands. The prototype of the dual-band antenna is manufactured and when tested for various antenna performance parameters shows a good agreement between the simulated and measured results. The proposed dual-band antenna has compact dimensions along with a peak gain of 2.2 dB and antenna efficiency of more than 90%.The antenna performance parameters are also compared with various dual-band antenna designs from the literature. The proposed dual-band antenna offers a compact design with satisfactory performance parameters and outperforms its counterparts.
{"title":"Compact dual-band antenna design for sub-6 GHz 5G application","authors":"Mahesh Kadu, Ramesh Pawase, Pankaj Chitte, V. Ubale","doi":"10.11591/eei.v13i3.7521","DOIUrl":"https://doi.org/10.11591/eei.v13i3.7521","url":null,"abstract":"A design of a compact dual-band antenna for 5G application is presented in this research article. The dual-band operation includes the 3.6 GHz and 5.4 GHz frequency bands of the sub-6 GHz frequency band for 5G technology. The proposed antenna offers a compact design with satisfactory antenna performance parameters. Moreover, the dual-band antenna showcases the independent tuning ability for both frequency bands. The prototype of the dual-band antenna is manufactured and when tested for various antenna performance parameters shows a good agreement between the simulated and measured results. The proposed dual-band antenna has compact dimensions along with a peak gain of 2.2 dB and antenna efficiency of more than 90%.The antenna performance parameters are also compared with various dual-band antenna designs from the literature. The proposed dual-band antenna offers a compact design with satisfactory performance parameters and outperforms its counterparts.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230614","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}
Issa Cheikh Elhassene, Bamba El Heiba, Teyeb Med Mahmoud, Zoubir Aoulmi, Issakha Youm, Abdelkader Mahmoud
This work examines a solar power plant connected to the Nouakchott electricity grid in Mauritania. Operating since 2013, the 15 MWp plant's reliability and energy yield have been evaluated using a performance index. The assessment involves three phases. First, the plant's meteorological environment and technical indicators are presented. In the second phase, mathematical performance models specified by the International Energy Agency (IEA) are applied to calculate performance indices using data from the data acquisition system (SCADA). The third phase compares actual production data for 2015, 2017, and 2020 with results simulated for PVsyst for the same years. The obtained results are thoroughly analyzed to highlight relevant physical phenomena. The analysis focuses on the plant's 7-year operating period and its impact on performance indicators for electricity production fed into the grid. This study provides insights into the solar power plant's reliability and energy yield, aiding future operational enhancements. It underscores the importance of performance monitoring and assessment in optimizing solar power generation systems.
{"title":"Long-term performance analysis of operational efficiency of a grid-connected solar power plant under Mauritania climate","authors":"Issa Cheikh Elhassene, Bamba El Heiba, Teyeb Med Mahmoud, Zoubir Aoulmi, Issakha Youm, Abdelkader Mahmoud","doi":"10.11591/eei.v13i3.7092","DOIUrl":"https://doi.org/10.11591/eei.v13i3.7092","url":null,"abstract":"This work examines a solar power plant connected to the Nouakchott electricity grid in Mauritania. Operating since 2013, the 15 MWp plant's reliability and energy yield have been evaluated using a performance index. The assessment involves three phases. First, the plant's meteorological environment and technical indicators are presented. In the second phase, mathematical performance models specified by the International Energy Agency (IEA) are applied to calculate performance indices using data from the data acquisition system (SCADA). The third phase compares actual production data for 2015, 2017, and 2020 with results simulated for PVsyst for the same years. The obtained results are thoroughly analyzed to highlight relevant physical phenomena. The analysis focuses on the plant's 7-year operating period and its impact on performance indicators for electricity production fed into the grid. This study provides insights into the solar power plant's reliability and energy yield, aiding future operational enhancements. It underscores the importance of performance monitoring and assessment in optimizing solar power generation systems.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"47 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231544","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}
This research paper presents an innovative solution for offline handwritten word recognition in Bengali, a prominent Indic language. The complexities of this script, particularly in cursive writing, often lead to overlapping characters and segmentation challenges. Conventional methodologies, reliant on individual character recognition and aggregation, are error-prone. To overcome these limitations, we propose a novel method treating the entire document as a coherent entity and utilizing the efficient you only look once (YOLO) model for word extraction. In our approach, we view individual words as distinct objects and employ the YOLO model for supervised learning, transforming object detection into a regression problematic to predict spatially detached bounding boxes and class possibilities. Rigorous training results in outstanding performance, with remarkable box_loss of 0.014, obj_loss of 0.14, and class_loss of 0.009. Furthermore, the achieved mAP_0.5 score of 0.95 and map_0.5:0.95 score of 0.97 demonstrates the model’s exceptional accuracy in detecting and recognizing handwritten words. To evaluate our method comprehensively, we introduce the Omor-Ekush dataset, a meticulously curated collection of 21,300 handwritten words from 150 participants, featuring 141 words per document. Our pioneering YOLO-based approach, combined with the curated Omor-Ekush dataset, represents a significant advancement in handwritten word recognition in Bengali.
{"title":"Bangla handwritten word recognition using YOLO V5","authors":"Md. Anwar Hossain, A. Abadin, Md. Omar Faruk, Iffat Ara, Mirza Afm Rashidul Hasan, Nafiul Fatta, Md Asraful, Ebrahim Hossen","doi":"10.11591/eei.v13i3.6953","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6953","url":null,"abstract":"This research paper presents an innovative solution for offline handwritten word recognition in Bengali, a prominent Indic language. The complexities of this script, particularly in cursive writing, often lead to overlapping characters and segmentation challenges. Conventional methodologies, reliant on individual character recognition and aggregation, are error-prone. To overcome these limitations, we propose a novel method treating the entire document as a coherent entity and utilizing the efficient you only look once (YOLO) model for word extraction. In our approach, we view individual words as distinct objects and employ the YOLO model for supervised learning, transforming object detection into a regression problematic to predict spatially detached bounding boxes and class possibilities. Rigorous training results in outstanding performance, with remarkable box_loss of 0.014, obj_loss of 0.14, and class_loss of 0.009. Furthermore, the achieved mAP_0.5 score of 0.95 and map_0.5:0.95 score of 0.97 demonstrates the model’s exceptional accuracy in detecting and recognizing handwritten words. To evaluate our method comprehensively, we introduce the Omor-Ekush dataset, a meticulously curated collection of 21,300 handwritten words from 150 participants, featuring 141 words per document. Our pioneering YOLO-based approach, combined with the curated Omor-Ekush dataset, represents a significant advancement in handwritten word recognition in Bengali.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"32 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234293","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}
Increasing crop yield with sustainable growth is the primary requirement for farmers with a growing population. Effective management and conservation of depleting natural resources is a priority task. Decrease in manpower due to migrating population has forced automation in agriculture. In this work, an automatic water irrigation and an effective crop recommendation system is proposed. Gypsum blocks based soil sensor is used to measure dielectric permittivity associated with the tested soil. The water-potential present in soil, along with potassium (K), nitrogen (N), phosphorus (P), potential of hydrogen (pH) helps to quantify the soil nutrients available and the suitable crop that can be considered for harvesting in a specified demography and environment. Sensory data indicating soil quality obtained is used to recommend crops by utilizing machine learning approaches. Telegram application is linked to the recommendation model to assist decision making and to ensure farmer-friendliness by sending notifications periodically.
{"title":"Smart irrigation with crop recommendation using machine learning approach","authors":"Anitha Palakshappa, Sowmya Kyathanahalli Nanjappa, Punitha Mahadevappa, Sinchana Sinchana","doi":"10.11591/eei.v13i3.6103","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6103","url":null,"abstract":"Increasing crop yield with sustainable growth is the primary requirement for farmers with a growing population. Effective management and conservation of depleting natural resources is a priority task. Decrease in manpower due to migrating population has forced automation in agriculture. In this work, an automatic water irrigation and an effective crop recommendation system is proposed. Gypsum blocks based soil sensor is used to measure dielectric permittivity associated with the tested soil. The water-potential present in soil, along with potassium (K), nitrogen (N), phosphorus (P), potential of hydrogen (pH) helps to quantify the soil nutrients available and the suitable crop that can be considered for harvesting in a specified demography and environment. Sensory data indicating soil quality obtained is used to recommend crops by utilizing machine learning approaches. Telegram application is linked to the recommendation model to assist decision making and to ensure farmer-friendliness by sending notifications periodically.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"29 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232838","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 increasing prevalence of malware targeting android mobile devices has raised significant concerns regarding user privacy and security. In response, effective methods for malware classification and detection are crucial to protect users from malicious applications. This paper presents an approach that leverages deep learning techniques and explainable artificial intelligence (XAI) for android mobile malware classification and detection. Convolutional neural networks (CNNs) are deep learning model that has shown impressive performance in several application areas, including image and text classification. In the context of android mobile malware, CNNs have shown promising results in capturing intricate patterns and features inherent in malware samples. By training these models on large datasets of benign and malicious applications, accurate classification can be achieved. To enhance transparency and interpretability, XAI techniques are integrated into the classification process. These techniques provide insights into the decision-making process of the deep learning models, enabling the identification of critical features and characteristics that contribute to the classification results. This research, by combining deep learning and XAI methods, presents a fresh strategy for identifying and categorizing Android malware. This research paper will focus on a fascinating CNN-based malware categorization technique.
{"title":"A novel method of detecting malware on Android mobile devices with explainable artificial intelligence","authors":"S. Vanjire, Mohandoss Lakshmi","doi":"10.11591/eei.v13i3.6986","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6986","url":null,"abstract":"The increasing prevalence of malware targeting android mobile devices has raised significant concerns regarding user privacy and security. In response, effective methods for malware classification and detection are crucial to protect users from malicious applications. This paper presents an approach that leverages deep learning techniques and explainable artificial intelligence (XAI) for android mobile malware classification and detection. Convolutional neural networks (CNNs) are deep learning model that has shown impressive performance in several application areas, including image and text classification. In the context of android mobile malware, CNNs have shown promising results in capturing intricate patterns and features inherent in malware samples. By training these models on large datasets of benign and malicious applications, accurate classification can be achieved. To enhance transparency and interpretability, XAI techniques are integrated into the classification process. These techniques provide insights into the decision-making process of the deep learning models, enabling the identification of critical features and characteristics that contribute to the classification results. This research, by combining deep learning and XAI methods, presents a fresh strategy for identifying and categorizing Android malware. This research paper will focus on a fascinating CNN-based malware categorization technique.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"31 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234789","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}
Shamsul Fakhar Abd Gani, M. F. Miskon, R. A. Hamzah, M. Hamid, A. F. Kadmin, A. I. Herman
Stereo matching algorithm is crucial for applications that rely on three-dimensional (3D) surface reconstruction, producing a disparity map that contains depth information by computing the disparity values between corresponding points from a stereo image pair. In order to yield desirable results, the proposed stereo matching algorithm must possess a high degree of resilience against radiometric variation and edge inconsistencies. In this article convolutional neural network (CNN) is employed in the first stage to generate the raw matching cost, which is subsequently filtered with a bilateral filter (BF) and applied with cross-based cost aggregation (CBCA) during the cost aggregation stage to enhance precision. Winner-take-all (WTA) strategy is implemented to normalise the disparity map values. Finally, the resulting output is subjected to an edge-aware smoothing filter (EASF) to reduce the noise. Due to its resistance to high contrast and brightness, the filter is found to be effective in refining and eliminating noise from the output image. Despite discontinuities like adiron's lost cup handle or artl's shattered rods, this approach, based on experimental research utilizing a Middlebury standard validation benchmark, yields a high level of accuracy, with an average non-occluded error of 6.79%, comparable to other published methods.
{"title":"Refining disparity maps using deep learning and edge-aware smoothing filter","authors":"Shamsul Fakhar Abd Gani, M. F. Miskon, R. A. Hamzah, M. Hamid, A. F. Kadmin, A. I. Herman","doi":"10.11591/eei.v13i3.6480","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6480","url":null,"abstract":"Stereo matching algorithm is crucial for applications that rely on three-dimensional (3D) surface reconstruction, producing a disparity map that contains depth information by computing the disparity values between corresponding points from a stereo image pair. In order to yield desirable results, the proposed stereo matching algorithm must possess a high degree of resilience against radiometric variation and edge inconsistencies. In this article convolutional neural network (CNN) is employed in the first stage to generate the raw matching cost, which is subsequently filtered with a bilateral filter (BF) and applied with cross-based cost aggregation (CBCA) during the cost aggregation stage to enhance precision. Winner-take-all (WTA) strategy is implemented to normalise the disparity map values. Finally, the resulting output is subjected to an edge-aware smoothing filter (EASF) to reduce the noise. Due to its resistance to high contrast and brightness, the filter is found to be effective in refining and eliminating noise from the output image. Despite discontinuities like adiron's lost cup handle or artl's shattered rods, this approach, based on experimental research utilizing a Middlebury standard validation benchmark, yields a high level of accuracy, with an average non-occluded error of 6.79%, comparable to other published methods.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"7 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234116","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}
Nowadays, modern technology includes various devices, networks, and apps from the internet of things (IoT), which consist of both positive and negative impacts on social, economic, and industrial effects. To address these issues, IoT applications and networks require lightweight, quick, and adaptable security solutions. In this sense, solutions based on artificial intelligence and big data analytics can yield positive outcomes in the realm of cyber security. This study presents a method called extreme gradient boost (XGBoost) based classification and regression tree to identify network intrusions in the IoT. This model is ideally suited for application in IoT networks with restricted resource availability because of its distributed structure and builtin higher generalization capabilities. This approach is thoroughly tested using botnet internet of things (BoT-IoT) new-generation IoT security datasets. All trials are conducted in a range of different settings, and a number of performance indicators are used to evaluate the effectiveness of the proposed method. The suggested study's findings provide recommendations and insights for situations involving binary classes and numerous classes. The suggested XGBoost model achieved 99.53% of accuracy in attack detection and 99.51% in precision for binary class and multiclass classifications, respectively.
{"title":"An extreme gradient boost based classification and regression tree for network intrusion detection in IoT","authors":"Silpa Chalichalamala, Niranjana Govindan, Ramani Kasarapu","doi":"10.11591/eei.v13i3.6843","DOIUrl":"https://doi.org/10.11591/eei.v13i3.6843","url":null,"abstract":"Nowadays, modern technology includes various devices, networks, and apps from the internet of things (IoT), which consist of both positive and negative impacts on social, economic, and industrial effects. To address these issues, IoT applications and networks require lightweight, quick, and adaptable security solutions. In this sense, solutions based on artificial intelligence and big data analytics can yield positive outcomes in the realm of cyber security. This study presents a method called extreme gradient boost (XGBoost) based classification and regression tree to identify network intrusions in the IoT. This model is ideally suited for application in IoT networks with restricted resource availability because of its distributed structure and builtin higher generalization capabilities. This approach is thoroughly tested using botnet internet of things (BoT-IoT) new-generation IoT security datasets. All trials are conducted in a range of different settings, and a number of performance indicators are used to evaluate the effectiveness of the proposed method. The suggested study's findings provide recommendations and insights for situations involving binary classes and numerous classes. The suggested XGBoost model achieved 99.53% of accuracy in attack detection and 99.51% in precision for binary class and multiclass classifications, respectively.","PeriodicalId":502860,"journal":{"name":"Bulletin of Electrical Engineering and Informatics","volume":"42 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232728","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：