Pub Date : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035656
Ivan Roy S. Evangelista, Lenmar T. Catajay, A. Bandala, Ronnie S. Concepcion, E. Sybingco, E. Dadios
The health condition of poultry significantly affects egg production, meat quality, and reproduction. Behavioral activities such as feeding patterns can be indicators of their current welfare. However, assessing through on-site observation is tedious, time-consuming, possibly biased, and can induce stress to the birds. Hence, employment of an autonomous surveillance system that can continuously and noninvasively monitor the poultry behaviors is the most viable approach. In this study, detection of quail activities: eating, drinking, and roaming, is administered using computer vision (CV) and deep learning (DL). Four DL models, YOLOv5, YOLOX, Faster R-CNN, and EfficientDet, were explored to detect quail activities in cages. The three models YOLOv5, YOLOX, and Faster R-CNN, achieved an average precision (AP) of 85.52, 79.31, and 74.28, respectively. For the EfficientDet model, the training was evaluated using total loss. A total loss of 0.1616 was achieved at 10,000 iterations. All the DL models performed impressively in detecting quail activities in cages. This study contributes to the development of an intelligent health assessment system for poultry.
{"title":"Exploring Deep Learning for Detection of Poultry Activities — Towards an Autonomous Health and Welfare Monitoring in Poultry Farms","authors":"Ivan Roy S. Evangelista, Lenmar T. Catajay, A. Bandala, Ronnie S. Concepcion, E. Sybingco, E. Dadios","doi":"10.1109/IMCOM56909.2023.10035656","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035656","url":null,"abstract":"The health condition of poultry significantly affects egg production, meat quality, and reproduction. Behavioral activities such as feeding patterns can be indicators of their current welfare. However, assessing through on-site observation is tedious, time-consuming, possibly biased, and can induce stress to the birds. Hence, employment of an autonomous surveillance system that can continuously and noninvasively monitor the poultry behaviors is the most viable approach. In this study, detection of quail activities: eating, drinking, and roaming, is administered using computer vision (CV) and deep learning (DL). Four DL models, YOLOv5, YOLOX, Faster R-CNN, and EfficientDet, were explored to detect quail activities in cages. The three models YOLOv5, YOLOX, and Faster R-CNN, achieved an average precision (AP) of 85.52, 79.31, and 74.28, respectively. For the EfficientDet model, the training was evaluated using total loss. A total loss of 0.1616 was achieved at 10,000 iterations. All the DL models performed impressively in detecting quail activities in cages. This study contributes to the development of an intelligent health assessment system for poultry.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127911593","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035570
W. Liao, Yi-Shan Chang, Yi-Chieh Wu
The technology of generative adversarial networks (GAN) is constantly evolving, and synthesized images can no longer be accurately distinguished by the human eyes alone. GAN has been applied to the analysis of satellite images, mostly for the purpose of data augmentation. Recently, however, we have seen a twist in its usage. In information warfare, GAN has been used to create fake satellite images or modify the image content by putting fake bridges, buildings and clouds to mislead or conceal important intelligence. To address the increasing counterfeit cases in satellite images, the goal of this research is to develop algorithms that can classify fake remote sensing images robustly and efficiently. There exist many techniques to synthesize or manipulate the content of satellite images. In this paper, we focus on the case when the entire image is forged. Three satellite image synthesis methods, including ProGAN, cGAN and CycleGAN will be investigated. The effect of image pre-processing such as histogram equalization and bilateral filter will also be evaluated. Experiments show that satellite images generated by different GANs can be easily identified by individually trained models. The performance degraded when model trained with one type of GAN samples is employed to determine the originality of images synthesized with other types of GANs. Additionally, when histogram equalization is applied to the images, the detection model fails to distinguish its authenticity. A four-class universal classification model is proposed to address this issue. An overall accuracy of over 99% has been achieved even when pre-processing has been applied.
{"title":"Detection of Synthesized Satellite Images Using Deep Neural Networks","authors":"W. Liao, Yi-Shan Chang, Yi-Chieh Wu","doi":"10.1109/IMCOM56909.2023.10035570","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035570","url":null,"abstract":"The technology of generative adversarial networks (GAN) is constantly evolving, and synthesized images can no longer be accurately distinguished by the human eyes alone. GAN has been applied to the analysis of satellite images, mostly for the purpose of data augmentation. Recently, however, we have seen a twist in its usage. In information warfare, GAN has been used to create fake satellite images or modify the image content by putting fake bridges, buildings and clouds to mislead or conceal important intelligence. To address the increasing counterfeit cases in satellite images, the goal of this research is to develop algorithms that can classify fake remote sensing images robustly and efficiently. There exist many techniques to synthesize or manipulate the content of satellite images. In this paper, we focus on the case when the entire image is forged. Three satellite image synthesis methods, including ProGAN, cGAN and CycleGAN will be investigated. The effect of image pre-processing such as histogram equalization and bilateral filter will also be evaluated. Experiments show that satellite images generated by different GANs can be easily identified by individually trained models. The performance degraded when model trained with one type of GAN samples is employed to determine the originality of images synthesized with other types of GANs. Additionally, when histogram equalization is applied to the images, the detection model fails to distinguish its authenticity. A four-class universal classification model is proposed to address this issue. An overall accuracy of over 99% has been achieved even when pre-processing has been applied.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130714084","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035613
Nivedita Singh, M. A. Alawami, Hyoungshick Kim
In the big data arena, opportunities and challenges are mixed. The volume of data in the financial institution is proliferating, which imposes a challenge to big data analytics to ensure safety during each transaction. Moreover, as more and more social networking sites (SNS) are integrating an inbuilt online payment system into their domain, an exponential surge in financial scams is expected in the upcoming days. These scenarios are alarming, and with the rapid growth in the daily addition of new end users and their increasing time spent on SNS, the situations become more vulnerable. With the existing trend of data mobilizations and rapid increase in volume, variety, and velocity of data being produced, big data has a significant role in detecting fraud incidents in financial transactions. However, in the framework of present followed international standards, there is a voluntary compliance obligation on domestic governing bodies, which is a significant source for such voluminous financial frauds on SNS. In order to strengthen the enforcement of international standards to combat financial transactions on SNS, the paper proposes that domestic legislation should comply with international standards with the further addition of machine learning encircled by domestic banking legislation. Eventually, this could solve the security and privacy governance difficulties arising from these financial frauds over SNS. We believe that with our approach of three-layer security i.e. by international standards, domestic legislation, and machine learning, the finan-cial fraud arising due to the SNS payment system will be reduced to a larger extent.
{"title":"When social networks meet payment: a security perspective","authors":"Nivedita Singh, M. A. Alawami, Hyoungshick Kim","doi":"10.1109/IMCOM56909.2023.10035613","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035613","url":null,"abstract":"In the big data arena, opportunities and challenges are mixed. The volume of data in the financial institution is proliferating, which imposes a challenge to big data analytics to ensure safety during each transaction. Moreover, as more and more social networking sites (SNS) are integrating an inbuilt online payment system into their domain, an exponential surge in financial scams is expected in the upcoming days. These scenarios are alarming, and with the rapid growth in the daily addition of new end users and their increasing time spent on SNS, the situations become more vulnerable. With the existing trend of data mobilizations and rapid increase in volume, variety, and velocity of data being produced, big data has a significant role in detecting fraud incidents in financial transactions. However, in the framework of present followed international standards, there is a voluntary compliance obligation on domestic governing bodies, which is a significant source for such voluminous financial frauds on SNS. In order to strengthen the enforcement of international standards to combat financial transactions on SNS, the paper proposes that domestic legislation should comply with international standards with the further addition of machine learning encircled by domestic banking legislation. Eventually, this could solve the security and privacy governance difficulties arising from these financial frauds over SNS. We believe that with our approach of three-layer security i.e. by international standards, domestic legislation, and machine learning, the finan-cial fraud arising due to the SNS payment system will be reduced to a larger extent.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117086410","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035597
Se-Young Jang, Yanggon Kim
Various deep learning studies have been gaining interest in environmental sound classification. In recent years, as the performance of image classification in deep learning increases, the field of converting and classifying audio data into images to classify has been steadily drawing attention. However, publicly accessible sound datasets are limited, so it is difficult to develop environmental sound classification compared to other classification. Among many augmentation methods, approaches are being made to generate synthetic data through a generative adversarial network for augmentation. In this paper, we suggest a deep learning framework that allows simultaneous learning of synthetic data and original data. Our network uses dual ResNet18, and it allows GAN-generated synthetic data and original data to be learned simultaneously within the network. The proposed method is evaluated through UrbanSound8K dataset. As a result, it showed a performance improvement compared to the method used as synthetic data augmentation in terms of learning efficiency and accuracy.
{"title":"Dual ResNet-based Environmental Sound Classification using GAN","authors":"Se-Young Jang, Yanggon Kim","doi":"10.1109/IMCOM56909.2023.10035597","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035597","url":null,"abstract":"Various deep learning studies have been gaining interest in environmental sound classification. In recent years, as the performance of image classification in deep learning increases, the field of converting and classifying audio data into images to classify has been steadily drawing attention. However, publicly accessible sound datasets are limited, so it is difficult to develop environmental sound classification compared to other classification. Among many augmentation methods, approaches are being made to generate synthetic data through a generative adversarial network for augmentation. In this paper, we suggest a deep learning framework that allows simultaneous learning of synthetic data and original data. Our network uses dual ResNet18, and it allows GAN-generated synthetic data and original data to be learned simultaneously within the network. The proposed method is evaluated through UrbanSound8K dataset. As a result, it showed a performance improvement compared to the method used as synthetic data augmentation in terms of learning efficiency and accuracy.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114351280","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035568
J. Yoon, K. Kim, Tae-Jin Lee
In an indoor wireless network environment com-posed of Internet of Things (loT) devices, there can be devices that transmit data in a weak link due to obstacles and low transmission power. To solve the problem without additional energy consumption of devices, a new Medium Access Control (MAC) protocol is required for receiving data from the devices in the weak link. In this paper, we propose an energy-efficient MAC protocol that the AP can collect data by using a Hybrid- Reconfigurable Intelligent Surface (H - RIS). In the proposed network, the Access Point (AP) can distinguish the packet-level failure of the weak link and control the H - RIS to receive data from the device. Using simulations, we have shown that our proposed method can enhance the performance of the network throughput and energy efficiency of devices.
{"title":"Data Exchange Protocol for Weak Links with Hybrid-RIS in Wireless Networks","authors":"J. Yoon, K. Kim, Tae-Jin Lee","doi":"10.1109/IMCOM56909.2023.10035568","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035568","url":null,"abstract":"In an indoor wireless network environment com-posed of Internet of Things (loT) devices, there can be devices that transmit data in a weak link due to obstacles and low transmission power. To solve the problem without additional energy consumption of devices, a new Medium Access Control (MAC) protocol is required for receiving data from the devices in the weak link. In this paper, we propose an energy-efficient MAC protocol that the AP can collect data by using a Hybrid- Reconfigurable Intelligent Surface (H - RIS). In the proposed network, the Access Point (AP) can distinguish the packet-level failure of the weak link and control the H - RIS to receive data from the device. Using simulations, we have shown that our proposed method can enhance the performance of the network throughput and energy efficiency of devices.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126430622","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035609
Li-Hua Li, Radius Tanone
One of Indonesia's mainstay agricultural products is the potato. Disease prevention is essential for maintaining stable potato production. One technique for detecting disease in potatoes is to determine whether potato leaves are diseased (early blight or late blight) or healthy. Deep Learning models have been widely developed and used to classify disease recognition in potato leaves in the industrial era 4.0. Swin Transformer is a deep learning model based on transformers that is more efficient and accurate at solving classification problems. The Swin Transformer, a transformer based deep learning approach, is used in this study to identify diseases of the potato leaf. Moreover, several metrics including Precision, Recall, Accuracy, and F1 score, are used to assess the experimental results of the model we use. In terms of accuracy, the value obtained when training with this model is 97.70%. These findings indicate that using the Swin Transformer model to identify potato leaf diseases could be a new trend in agricultural research.
{"title":"Disease Identification in Potato Leaves using Swin Transformer","authors":"Li-Hua Li, Radius Tanone","doi":"10.1109/IMCOM56909.2023.10035609","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035609","url":null,"abstract":"One of Indonesia's mainstay agricultural products is the potato. Disease prevention is essential for maintaining stable potato production. One technique for detecting disease in potatoes is to determine whether potato leaves are diseased (early blight or late blight) or healthy. Deep Learning models have been widely developed and used to classify disease recognition in potato leaves in the industrial era 4.0. Swin Transformer is a deep learning model based on transformers that is more efficient and accurate at solving classification problems. The Swin Transformer, a transformer based deep learning approach, is used in this study to identify diseases of the potato leaf. Moreover, several metrics including Precision, Recall, Accuracy, and F1 score, are used to assess the experimental results of the model we use. In terms of accuracy, the value obtained when training with this model is 97.70%. These findings indicate that using the Swin Transformer model to identify potato leaf diseases could be a new trend in agricultural research.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133370737","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035626
Ziyue Zhu, Yuanyuan Wang
This paper investigates the mood changes of youth groups during the social closure control of the COVID-19 pan-demic and the primary causes of those changes, taking Chinese online video platforms as an example. We also compare the main concerns of various periods to provide feasible references and suggestions on psychological interventions for young people during the social closure control period. In this study, we identified mood changes during the COVID-19 pandemic with 31,213 comments on the news videos of the Bilibili video platform through four stages: data collection, data processing, LDA topic modeling, and mood identification. Through a comparative analysis, we investigated the topical features of young people's mood changes in three COVID-19 periods: pre-, mid-, and late-epidemic. As a result, we found that social isolation measures such as closure and homeschooling with long-term Internet use during the epidemic were more likely to cause depression in young people.
{"title":"Topical Analysis of Depressive Mood Changes in Youth during the COVID-19 Pandemic","authors":"Ziyue Zhu, Yuanyuan Wang","doi":"10.1109/IMCOM56909.2023.10035626","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035626","url":null,"abstract":"This paper investigates the mood changes of youth groups during the social closure control of the COVID-19 pan-demic and the primary causes of those changes, taking Chinese online video platforms as an example. We also compare the main concerns of various periods to provide feasible references and suggestions on psychological interventions for young people during the social closure control period. In this study, we identified mood changes during the COVID-19 pandemic with 31,213 comments on the news videos of the Bilibili video platform through four stages: data collection, data processing, LDA topic modeling, and mood identification. Through a comparative analysis, we investigated the topical features of young people's mood changes in three COVID-19 periods: pre-, mid-, and late-epidemic. As a result, we found that social isolation measures such as closure and homeschooling with long-term Internet use during the epidemic were more likely to cause depression in young people.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116399315","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035625
Dang Anh Khoa, Nguyen Trung Kiem, N. Kien, Nguyen Ngoc Tuan, Nguyen Huu Thanh
Software-Defined Networking (SDN) is gaining attention for its flexibility in programmability. It enhances network configuration and provides global visibility for administrators via a single interface. However, the centralized nature of SDN exposes many issues in scalability and resiliency. In this paper, with the advent of cloud computing, we present a containerized architecture capable of fast scaling up and down based on traffic load for SDN control plane. With our novel traffic-adaptive algorithm, the results show that the proposed system is able to fit performance with high incoming new-flow requests and scale down underused controllers for resource efficiency.
{"title":"Traffic-Adaptive Scheme for SDN Control Plane with Containerized Architecture","authors":"Dang Anh Khoa, Nguyen Trung Kiem, N. Kien, Nguyen Ngoc Tuan, Nguyen Huu Thanh","doi":"10.1109/IMCOM56909.2023.10035625","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035625","url":null,"abstract":"Software-Defined Networking (SDN) is gaining attention for its flexibility in programmability. It enhances network configuration and provides global visibility for administrators via a single interface. However, the centralized nature of SDN exposes many issues in scalability and resiliency. In this paper, with the advent of cloud computing, we present a containerized architecture capable of fast scaling up and down based on traffic load for SDN control plane. With our novel traffic-adaptive algorithm, the results show that the proposed system is able to fit performance with high incoming new-flow requests and scale down underused controllers for resource efficiency.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116482024","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035638
Ahmad Haiqal Abd Khalid, Nur Nazihah Mohkhlas, N. A. Zakaria, Mazidah Mat Rejab, Ruwinah Abdul Karim, Suharsiwi Suharsiwi
The enhancement of technology is well-developed and assistive technology is one of the foremost that has been used significantly. Individuals with disabilities use assistive technology to perform the desired activity that would otherwise be difficult or impossible. Mobility devices such as walkers and wheelchairs, as well as hardware, software, and peripherals that assist people with disabilities in accessing computers or other information technologies, are examples of assistive technology. Learning disabilities are caused by genetic and neurobiological factors that affect brain functioning, influencing one or more cognitive processes related to learning. This paper discusses a comprehensive systematic literature review (SLR) of the assistive technology (AT) for children with learning disabilities with combination of Kitchenham and PRISMA approach. This paper discusses on the assistive technologies developed for children with learning disabilities according to its type, purposes, techniques used, and platform or delivery system used to host the developed assistive technologies for children with learning disabilities.
{"title":"Assistive Technology for Children with Learning Disabilities: A Systematic Literature Review","authors":"Ahmad Haiqal Abd Khalid, Nur Nazihah Mohkhlas, N. A. Zakaria, Mazidah Mat Rejab, Ruwinah Abdul Karim, Suharsiwi Suharsiwi","doi":"10.1109/IMCOM56909.2023.10035638","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035638","url":null,"abstract":"The enhancement of technology is well-developed and assistive technology is one of the foremost that has been used significantly. Individuals with disabilities use assistive technology to perform the desired activity that would otherwise be difficult or impossible. Mobility devices such as walkers and wheelchairs, as well as hardware, software, and peripherals that assist people with disabilities in accessing computers or other information technologies, are examples of assistive technology. Learning disabilities are caused by genetic and neurobiological factors that affect brain functioning, influencing one or more cognitive processes related to learning. This paper discusses a comprehensive systematic literature review (SLR) of the assistive technology (AT) for children with learning disabilities with combination of Kitchenham and PRISMA approach. This paper discusses on the assistive technologies developed for children with learning disabilities according to its type, purposes, techniques used, and platform or delivery system used to host the developed assistive technologies for children with learning disabilities.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124775371","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035576
S. Kim
We propose a novel covert communication technique between the federated learning (FL) server and participants without affecting the FL performance. The FL server superimposes the covert message onto the aggregated gradient and broadcasts the superimposed signal to all FL participants. FL participants decode the covert message treating the aggregated gradient as interference, and restore the original global model after removing the covert message from the superimposed signal. Therefore, the FL performance is not affected by sending the covert message. We analyze the covertness of communication against the adversary that monitors the statistical distribution of model updates. We derive the maximum achievable transmission rate of the covert message without being detected by the adversary and without affecting the federated learning performance.
{"title":"Covert Communication over Federated Learning Channel","authors":"S. Kim","doi":"10.1109/IMCOM56909.2023.10035576","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035576","url":null,"abstract":"We propose a novel covert communication technique between the federated learning (FL) server and participants without affecting the FL performance. The FL server superimposes the covert message onto the aggregated gradient and broadcasts the superimposed signal to all FL participants. FL participants decode the covert message treating the aggregated gradient as interference, and restore the original global model after removing the covert message from the superimposed signal. Therefore, the FL performance is not affected by sending the covert message. We analyze the covertness of communication against the adversary that monitors the statistical distribution of model updates. We derive the maximum achievable transmission rate of the covert message without being detected by the adversary and without affecting the federated learning performance.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121902640","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：