Pub Date : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035630
Jihyeon Ryu, Keunok Kim, Dongho Won
Recently, data experts can obtain a large amount of data with the development of the Internet. When computing such data, cloud services that do not use the personal device's memory are becoming popular. However, storing sensitive data as a source in the cloud carries the risk of hijacking. To compensate for this, homomorphic encryption, which encrypts and stores sensitive data, and can safely operate in an encrypted state, is being studied. In this paper, we analyze four methods of partially homomorphic encryption among homomorphic encryption methods. We compare and analyze the key size and ciphertext size of four partially homomorphic encryptions, Paillier, ElGamal, ASHE, and Symmetria.
{"title":"A Study on Partially Homomorphic Encryption","authors":"Jihyeon Ryu, Keunok Kim, Dongho Won","doi":"10.1109/IMCOM56909.2023.10035630","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035630","url":null,"abstract":"Recently, data experts can obtain a large amount of data with the development of the Internet. When computing such data, cloud services that do not use the personal device's memory are becoming popular. However, storing sensitive data as a source in the cloud carries the risk of hijacking. To compensate for this, homomorphic encryption, which encrypts and stores sensitive data, and can safely operate in an encrypted state, is being studied. In this paper, we analyze four methods of partially homomorphic encryption among homomorphic encryption methods. We compare and analyze the key size and ciphertext size of four partially homomorphic encryptions, Paillier, ElGamal, ASHE, and Symmetria.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"157 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":"121750228","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/IMCOM56909.2023.10035655
Nguyen Anh Tuan, To Quoc Hung, Nguyen Tai Hung, Nguyen Tien Dong, Dinh Viet Quan
We present the implementation of a caching system within the IP Allocation Service of the 5G Core Networks. The IP allocation service is one of many services in the Session Management Function (SMF) of the 5G Core that supports the allocation and management of User Equipment (UE) IP addresses. Normally, this service uses a database layer to manage the available IP address ranges. However, the current design of this function requires a database fetch for every IP address allocation request, which is called every time session establishment is called. This is costly in terms of computing and networking resources. Our proposed solution employs a caching system that fragments the available IP pool between pods (deployable computing units managed by Kubernetes that make up the service), saves the ranges to the pods' local memory resources from a shared database layer, and allows each pod to independently manage IP addresses within its range. Our testing results show that this architecture greatly improves the networking resources consumed while maintaining the consistency of IP address allocations across the network.
{"title":"Caching and Containerization of IP Address Allocation Process in 5G Core Networks for Performance Improvements","authors":"Nguyen Anh Tuan, To Quoc Hung, Nguyen Tai Hung, Nguyen Tien Dong, Dinh Viet Quan","doi":"10.1109/IMCOM56909.2023.10035655","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035655","url":null,"abstract":"We present the implementation of a caching system within the IP Allocation Service of the 5G Core Networks. The IP allocation service is one of many services in the Session Management Function (SMF) of the 5G Core that supports the allocation and management of User Equipment (UE) IP addresses. Normally, this service uses a database layer to manage the available IP address ranges. However, the current design of this function requires a database fetch for every IP address allocation request, which is called every time session establishment is called. This is costly in terms of computing and networking resources. Our proposed solution employs a caching system that fragments the available IP pool between pods (deployable computing units managed by Kubernetes that make up the service), saves the ranges to the pods' local memory resources from a shared database layer, and allows each pod to independently manage IP addresses within its range. Our testing results show that this architecture greatly improves the networking resources consumed while maintaining the consistency of IP address allocations across the network.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"13 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":"125187630","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/IMCOM56909.2023.10035645
Ran Li, M. Moh, Teng-Sheng Moh
The global art has experienced a steady growth to tens of billion dollars in annual sales. The huge profits behind art trades unfortunately have been largely overlooked and rarely been studied in most of the machine learning and recommendation system (RS) research. As a popular Deep Metric Learning (DML) model, the Siamese Neural Network (SNN) has been widely used in music and other e-commerce RS, but not been used in art recommendation tasks. In this paper we propose an art similarity metric with SNN, and based on which built a content-based art RS, followed by clustering for reducing comparison numbers. Performance evaluation of the proposed SNN-based art RS has been conducted, in comparison with our original, simpler model basing on cosine similarity. Results shows that the SNN-based visual art RS performs significantly better in every experiment subgroup, is more robust with strong resistance to overfitting and confusion. Additional experiments show that it is nontrivial to further improve these recommendation results. To the best of our knowledge, this is the first visually-aware RS that took advantage of both SNN and content-based recommendation framework in visual art recommendation. We believe that this work opens wide opportunities for applying machine-learning and deep-learning techniques in the exciting area of visual art recommendation.
{"title":"Siamese Neural Networks for Content-based Visual Art Recommendation","authors":"Ran Li, M. Moh, Teng-Sheng Moh","doi":"10.1109/IMCOM56909.2023.10035645","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035645","url":null,"abstract":"The global art has experienced a steady growth to tens of billion dollars in annual sales. The huge profits behind art trades unfortunately have been largely overlooked and rarely been studied in most of the machine learning and recommendation system (RS) research. As a popular Deep Metric Learning (DML) model, the Siamese Neural Network (SNN) has been widely used in music and other e-commerce RS, but not been used in art recommendation tasks. In this paper we propose an art similarity metric with SNN, and based on which built a content-based art RS, followed by clustering for reducing comparison numbers. Performance evaluation of the proposed SNN-based art RS has been conducted, in comparison with our original, simpler model basing on cosine similarity. Results shows that the SNN-based visual art RS performs significantly better in every experiment subgroup, is more robust with strong resistance to overfitting and confusion. Additional experiments show that it is nontrivial to further improve these recommendation results. To the best of our knowledge, this is the first visually-aware RS that took advantage of both SNN and content-based recommendation framework in visual art recommendation. We believe that this work opens wide opportunities for applying machine-learning and deep-learning techniques in the exciting area of visual art recommendation.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"3 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":"129266806","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/IMCOM56909.2023.10035577
Eriko Yamano, T. Takayama
In general, support for rainy day travel is known to be imperative during long times. Rainy weather has significant risk for tourists to terribly reduce a satisfaction level of their travel. However, its solution is not fully developed. In Post-Covid-19 environment, support for tourism in an actual field could become imperative again. In the present paper, we put one assumption that “a tourist has already made his/her travel plan for a sunny day”. By the way, there exists a social approach: ‘potential-of-interest maps for mobile tourist information services’. It shows the amounts of the numbers of the photographs in social photograph sharing system ‘Flickr’ by color and intensity on a map. This paper modifies it for support of rainy day travel planning. Concretely, we propose the following three menus in our system: 1) a menu to show ‘potential-of-interest maps' per a degree of rainfall amount, 2) a menu to show only travel spot which is robust to rainy weather based on its static characteristics, and 3) a menu to show only travel spots within a specified distance range from a basic point, taking into account decrease of behavior range. With these three menus, we try to support a tourist to change his/her travel plan efficiently even if weather suddenly becomes rain. In actual, we have evaluated our pilot system by the following two method: (1) evaluation experiment with some subjects, and (2) interviews to tourism professionals. Both of their results shows that our system would be useful in order to support for a tourist to change his/her travel plan efficiently when weather has suddenly become rain.
{"title":"Rainy Day Travel Planning System That Combines Tourism Potential Map with Static Characteristics of Spots","authors":"Eriko Yamano, T. Takayama","doi":"10.1109/IMCOM56909.2023.10035577","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035577","url":null,"abstract":"In general, support for rainy day travel is known to be imperative during long times. Rainy weather has significant risk for tourists to terribly reduce a satisfaction level of their travel. However, its solution is not fully developed. In Post-Covid-19 environment, support for tourism in an actual field could become imperative again. In the present paper, we put one assumption that “a tourist has already made his/her travel plan for a sunny day”. By the way, there exists a social approach: ‘potential-of-interest maps for mobile tourist information services’. It shows the amounts of the numbers of the photographs in social photograph sharing system ‘Flickr’ by color and intensity on a map. This paper modifies it for support of rainy day travel planning. Concretely, we propose the following three menus in our system: 1) a menu to show ‘potential-of-interest maps' per a degree of rainfall amount, 2) a menu to show only travel spot which is robust to rainy weather based on its static characteristics, and 3) a menu to show only travel spots within a specified distance range from a basic point, taking into account decrease of behavior range. With these three menus, we try to support a tourist to change his/her travel plan efficiently even if weather suddenly becomes rain. In actual, we have evaluated our pilot system by the following two method: (1) evaluation experiment with some subjects, and (2) interviews to tourism professionals. Both of their results shows that our system would be useful in order to support for a tourist to change his/her travel plan efficiently when weather has suddenly become rain.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"103 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":"121943038","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/IMCOM56909.2023.10035593
Daniel Luna, F. Hernández, Yao Liang, Xu Liang
This paper introduces the Hydrologic Disaster Forecasting and Response (HDFR), an online data and modeling integration software system that facilitates the machine-to-machine access to and the management of environmental sensing data from space and ground products. Available data sources include in-situ measurements from weather and hydrographic stations; remote sensing products from Doppler precipitation radars in the United States, Earth-monitoring satellites that measure precipitation, soil moisture, and snow cover; and numerical weather prediction model outputs from the U.S. National Weather Service. Additionally, the HDFR system provides a suite of hydrologic modeling tools; including data fusion, storm severity assessment, and hydrologic model preprocessing for the Distributed Hydrology Soil Vegetation Model (DHSVM); that are seamlessly incorporated with the diverse suite of data products. Two example workflows demonstrate how this unified framework could help bridge the gap between the online and on-demand accessing of growing wealth of Earth-observing data and hydrologic prediction for scientific and engineering applications.
{"title":"HDFR: A Hydrologic Data and Modeling System with On-Demand Access to Environmental Sensing Data for Decision Making","authors":"Daniel Luna, F. Hernández, Yao Liang, Xu Liang","doi":"10.1109/IMCOM56909.2023.10035593","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035593","url":null,"abstract":"This paper introduces the Hydrologic Disaster Forecasting and Response (HDFR), an online data and modeling integration software system that facilitates the machine-to-machine access to and the management of environmental sensing data from space and ground products. Available data sources include in-situ measurements from weather and hydrographic stations; remote sensing products from Doppler precipitation radars in the United States, Earth-monitoring satellites that measure precipitation, soil moisture, and snow cover; and numerical weather prediction model outputs from the U.S. National Weather Service. Additionally, the HDFR system provides a suite of hydrologic modeling tools; including data fusion, storm severity assessment, and hydrologic model preprocessing for the Distributed Hydrology Soil Vegetation Model (DHSVM); that are seamlessly incorporated with the diverse suite of data products. Two example workflows demonstrate how this unified framework could help bridge the gap between the online and on-demand accessing of growing wealth of Earth-observing data and hydrologic prediction for scientific and engineering applications.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"5 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":"116572326","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/IMCOM56909.2023.10035596
ShaoPeng Che, Shunan Zhang, Dongyan Nan, Jang-Hyun Kim
The uncertainty involved in innovation makes it inseparable from risk management, and therefore, how to effectively apply risk management to innovation has been a topic of interest in industry and academia. However, due to the interdisciplinary nature of risk management in innovation (RMI), no study has systematically analyzed the knowledge structure of RIM. To fill the gap, this paper used CiteSpace to explore how risk management has been involved in innovation between 1988 and 2021. First, this study investigated the temporal distribution of RMI publications. Second, this study used co-authorship analysis to identify scientific collaboration networks and in doing so, to understand productive authors, institutions, and countries in the field. Third, this study used co-citation analysis to unearth the key journals, authors, and literature in the area. Finally, using literature cluster and timeline view analysis, this study explores development path of RMI. The results show that although China is the most productive country, it is not as good as Europe and the United States in terms of international cooperation. Abreu A is a prolific author, with a collaborative group centered on Alex Zabeo (4) containing ten authors. Although Sustainability is the most productive journal in the RMI field, management science is the most popular journal. Finally, our study revealed the top 6 research themes in RMI and find that firm performance is always the focus of RMI research.
{"title":"Risk Management and Innovation: Analytical Mapping of Risk Management in Innovation Using CiteSpace","authors":"ShaoPeng Che, Shunan Zhang, Dongyan Nan, Jang-Hyun Kim","doi":"10.1109/IMCOM56909.2023.10035596","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035596","url":null,"abstract":"The uncertainty involved in innovation makes it inseparable from risk management, and therefore, how to effectively apply risk management to innovation has been a topic of interest in industry and academia. However, due to the interdisciplinary nature of risk management in innovation (RMI), no study has systematically analyzed the knowledge structure of RIM. To fill the gap, this paper used CiteSpace to explore how risk management has been involved in innovation between 1988 and 2021. First, this study investigated the temporal distribution of RMI publications. Second, this study used co-authorship analysis to identify scientific collaboration networks and in doing so, to understand productive authors, institutions, and countries in the field. Third, this study used co-citation analysis to unearth the key journals, authors, and literature in the area. Finally, using literature cluster and timeline view analysis, this study explores development path of RMI. The results show that although China is the most productive country, it is not as good as Europe and the United States in terms of international cooperation. Abreu A is a prolific author, with a collaborative group centered on Alex Zabeo (4) containing ten authors. Although Sustainability is the most productive journal in the RMI field, management science is the most popular journal. Finally, our study revealed the top 6 research themes in RMI and find that firm performance is always the focus of RMI research.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"1 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":"131046107","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/IMCOM56909.2023.10035634
Fareed Kaleem Khaiser, Amna Saad, Cordelia Mason
The assessment of future students' employability by the Institute of Higher Learning in collaboration with career centres is one of the most crucial steps in the educational industry for establishing an active and ascendable plan. Predictive analysis for this project is done using machine learning. This study investigates the Employability Signals of Undergraduates in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) criteria. The findings demonstrate that higher education was where the most accurate predictor of undergraduate students' employability was initially examined. The study's conclusions can be used to develop a roadmap that will make it simpler to use predictive analytics. The findings of this study may also facilitate the creation and application of predictive analytics, one of the possible approaches for analysing the education data gathered during the pre-covid period for this study. Systematic literature reviews should be trustworthy, repeatable, and valid when used in scientific investigations. As a result, the inquiry will reach a conclusion based on the evaluations found on pertinent and customized dates.
{"title":"Systematic Review of Qualitative and Quantitative Studies on Perceived Employability of Graduates","authors":"Fareed Kaleem Khaiser, Amna Saad, Cordelia Mason","doi":"10.1109/IMCOM56909.2023.10035634","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035634","url":null,"abstract":"The assessment of future students' employability by the Institute of Higher Learning in collaboration with career centres is one of the most crucial steps in the educational industry for establishing an active and ascendable plan. Predictive analysis for this project is done using machine learning. This study investigates the Employability Signals of Undergraduates in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) criteria. The findings demonstrate that higher education was where the most accurate predictor of undergraduate students' employability was initially examined. The study's conclusions can be used to develop a roadmap that will make it simpler to use predictive analytics. The findings of this study may also facilitate the creation and application of predictive analytics, one of the possible approaches for analysing the education data gathered during the pre-covid period for this study. Systematic literature reviews should be trustworthy, repeatable, and valid when used in scientific investigations. As a result, the inquiry will reach a conclusion based on the evaluations found on pertinent and customized dates.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"61 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":"128207671","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/IMCOM56909.2023.10035628
Akhmed Sakip, Ramazan Yersainov, Mokhira Atashikova, Timur Rakhimzhan, Dinh-Mao Bui, E. Huh, Sungyoung Lee
Energy efficiency is one of the most critical aspects of the modern computing paradigm, such as edge and cloud computing, due to minimizing carbon footprint and lowering operational costs. In order to achieve efficiency, it is essential to address the energy consumption problem of the computing nodes. Conventionally, power in the edge/cloud paradigm could be conserved by diminishing under-utilized resources through various virtual machine consolidation techniques. This operation can be performed more effectively if the resource management component acquires some knowledge of the system workload. In this paper, we would like to present our research on developing an energy-efficient framework to optimize and offload computationally intensive tasks to the edge/cloud system. This objective was achieved based on a two-fold effort. Firstly, an adaptation and modification were introduced to an offloading framework to make it work with heterogeneous edge/cloud systems. This modification consists of the functionalities of resource allocation and control. Subsequently, a lightweight resource scheduling algorithm, namely the Minimal Margin-Based Scheduling Algorithm, was developed to orchestrate the deployment of offloaded tasks to the best-suited container. After that, an extensive evaluation of real equipment was conducted to confirm the proposal's effectiveness. In fact, the results of practical experiments showed that the developed framework and algorithm could efficiently manage computing nodes in response to the change in the workload and reduce energy consumption.
{"title":"Lightweight energy-efficient offloading framework for mobile edge/cloud computing","authors":"Akhmed Sakip, Ramazan Yersainov, Mokhira Atashikova, Timur Rakhimzhan, Dinh-Mao Bui, E. Huh, Sungyoung Lee","doi":"10.1109/IMCOM56909.2023.10035628","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035628","url":null,"abstract":"Energy efficiency is one of the most critical aspects of the modern computing paradigm, such as edge and cloud computing, due to minimizing carbon footprint and lowering operational costs. In order to achieve efficiency, it is essential to address the energy consumption problem of the computing nodes. Conventionally, power in the edge/cloud paradigm could be conserved by diminishing under-utilized resources through various virtual machine consolidation techniques. This operation can be performed more effectively if the resource management component acquires some knowledge of the system workload. In this paper, we would like to present our research on developing an energy-efficient framework to optimize and offload computationally intensive tasks to the edge/cloud system. This objective was achieved based on a two-fold effort. Firstly, an adaptation and modification were introduced to an offloading framework to make it work with heterogeneous edge/cloud systems. This modification consists of the functionalities of resource allocation and control. Subsequently, a lightweight resource scheduling algorithm, namely the Minimal Margin-Based Scheduling Algorithm, was developed to orchestrate the deployment of offloaded tasks to the best-suited container. After that, an extensive evaluation of real equipment was conducted to confirm the proposal's effectiveness. In fact, the results of practical experiments showed that the developed framework and algorithm could efficiently manage computing nodes in response to the change in the workload and reduce energy consumption.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":" 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113947737","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/IMCOM56909.2023.10035572
Rupesh Kumar Dey, Muhammad Ehsan Rana, Vazeerudeen Abdul Hameed
GI Tract related diseases are one of the most prevalent in today's society. Studies have shown that continuous monitoring, early detection, and treatment of these diseases are imperative in improving patients' recovery rate. Wireless Capsule Endoscopy (WCE) is an innovative imaging technology that enables invasive imaging of the GI Tract. Convolutional Neural Networks (CNN) and Image Processing have become very sought-after solutions in the process of developing a Computer Aided Diagnosis (CAD) system for many medical applications. The study aims to design and develop a generalized multiclass CNN classification algorithm to be used in CAD system for diagnosis of various GI tract diseases by analyzing WCE GI tract images with varying tract lining lesions. CNN classification-based solution framework encompassing various network architectures, image processing enhancement techniques and data augmentation methods are proposed. Three histogram stretching based enhancement techniques were introduced to enhance the quality of the raw image prior to performing classification. Data augmentation was performed as well. Different network architectures of self-developed architectures, transfer learning feature extraction, fine tuning and an ensemble of models were developed. The results were analyzed, putting emphasis on the generalization capability of the developed solutions. Results showed that image processing enhancement improved the CNN models' capability in performing accurate classification. In terms of individual network architectures, the transfer learning fine tuning models performed better as compared to the rest of the architectures. CNN networks trained on the dataset with augmentation are more generalized as compared to CNN networks trained on non-augmented data. The final proposed solution for GI tract CAD CNN network is the ensemble model which managed to achieve an overall accuracy of 97.03% when tested and compared to other proposed architectures across 4 phases of result analysis.
{"title":"Analysing Wireless Capsule Endoscopy Images Using Deep Learning Frameworks to Classify Different GI Tract Diseases","authors":"Rupesh Kumar Dey, Muhammad Ehsan Rana, Vazeerudeen Abdul Hameed","doi":"10.1109/IMCOM56909.2023.10035572","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035572","url":null,"abstract":"GI Tract related diseases are one of the most prevalent in today's society. Studies have shown that continuous monitoring, early detection, and treatment of these diseases are imperative in improving patients' recovery rate. Wireless Capsule Endoscopy (WCE) is an innovative imaging technology that enables invasive imaging of the GI Tract. Convolutional Neural Networks (CNN) and Image Processing have become very sought-after solutions in the process of developing a Computer Aided Diagnosis (CAD) system for many medical applications. The study aims to design and develop a generalized multiclass CNN classification algorithm to be used in CAD system for diagnosis of various GI tract diseases by analyzing WCE GI tract images with varying tract lining lesions. CNN classification-based solution framework encompassing various network architectures, image processing enhancement techniques and data augmentation methods are proposed. Three histogram stretching based enhancement techniques were introduced to enhance the quality of the raw image prior to performing classification. Data augmentation was performed as well. Different network architectures of self-developed architectures, transfer learning feature extraction, fine tuning and an ensemble of models were developed. The results were analyzed, putting emphasis on the generalization capability of the developed solutions. Results showed that image processing enhancement improved the CNN models' capability in performing accurate classification. In terms of individual network architectures, the transfer learning fine tuning models performed better as compared to the rest of the architectures. CNN networks trained on the dataset with augmentation are more generalized as compared to CNN networks trained on non-augmented data. The final proposed solution for GI tract CAD CNN network is the ensemble model which managed to achieve an overall accuracy of 97.03% when tested and compared to other proposed architectures across 4 phases of result analysis.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"24 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":"129269390","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/IMCOM56909.2023.10035588
Cris Ramil Calzita, Kehndee Ann Jubilo, Glenn Permejo, Roxcella Reas, Jonah Jahara G. Baun, Ronnie S. Concepcion, J. A. D. Leon, A. Bandala, A. Mayol, R. R. Vicerra, E. Dadios
Urban farming is becoming more popular in recent years as the community began to focus more on the product's quality that is now being consumed. Aeroponics is one of the new urban farming techniques that is more effective than traditional farming since it involves growing plants without soil using nutrient solutions sprayed into the roots. However, proper monitoring of the cultivation environment and control of environmental factors is crucial for efficient aeroponic farming. This study focuses on developing an IoT-based-intelligent monitoring and controlling mechanism of an aeroponic system for the effective production of lettuce (Lactuca sativa). Raspberry Pi is employed for the system's real-time monitoring capabilities of growth parameters in the data collection system based on temperature, relative humidity with respect to the root system, and light intensity. The system is capable of automatically adjusting the amount of light each sample will receive over time and automatically activates the thermoelectric cooling system, exhaust, and mister anytime the ambient temperature is too high for plant development. The monitoring system effectively logged the expected growth parameters per minute upon testing and was able to store the logged data in a Comma-Separated Value (CSV) file format. The recorded values retrieved by the system from the sensors for temperature, humidity, and light intensity were within the range of the settling, threshold, or daily amount. The real-time data can be accessed successfully in the developed web application via smartphones or personal computers. This system offers a positive financial impact on society and its consumers.
{"title":"Intelligent Aeroponic System for Real-time Control and Monitoring of Lactuca Sativa Production","authors":"Cris Ramil Calzita, Kehndee Ann Jubilo, Glenn Permejo, Roxcella Reas, Jonah Jahara G. Baun, Ronnie S. Concepcion, J. A. D. Leon, A. Bandala, A. Mayol, R. R. Vicerra, E. Dadios","doi":"10.1109/IMCOM56909.2023.10035588","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035588","url":null,"abstract":"Urban farming is becoming more popular in recent years as the community began to focus more on the product's quality that is now being consumed. Aeroponics is one of the new urban farming techniques that is more effective than traditional farming since it involves growing plants without soil using nutrient solutions sprayed into the roots. However, proper monitoring of the cultivation environment and control of environmental factors is crucial for efficient aeroponic farming. This study focuses on developing an IoT-based-intelligent monitoring and controlling mechanism of an aeroponic system for the effective production of lettuce (Lactuca sativa). Raspberry Pi is employed for the system's real-time monitoring capabilities of growth parameters in the data collection system based on temperature, relative humidity with respect to the root system, and light intensity. The system is capable of automatically adjusting the amount of light each sample will receive over time and automatically activates the thermoelectric cooling system, exhaust, and mister anytime the ambient temperature is too high for plant development. The monitoring system effectively logged the expected growth parameters per minute upon testing and was able to store the logged data in a Comma-Separated Value (CSV) file format. The recorded values retrieved by the system from the sensors for temperature, humidity, and light intensity were within the range of the settling, threshold, or daily amount. The real-time data can be accessed successfully in the developed web application via smartphones or personal computers. This system offers a positive financial impact on society and its consumers.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"20 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":"117228321","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：