Pub Date : 2023-06-06DOI: 10.1109/MECO58584.2023.10155088
Konrad Moron, Stefan Wallentowitz
WebAssembly gains increasing interest outside the browser, such as in servers or desktops. It also becomes a viable candidate as a managed virtual machine for embedded systems, supported by multiple runtimes. However, the performance of interpreters is limited. Outside embedded systems, just-in-time compilation is used to significantly improve the performance of bytecode execution. Existing WebAssembly runtimes with just-in-time compilation support are either unsuitable for the use on low-resource hardware such as micro-controllers, or they employ a basic compilation strategy that doesn't utilize optimization opportunities and increases the compilation overhead. In this work, we present a micro-controller compatible WebAssembly runtime that supports the general framework for enabling advanced, feedback guided just-in-time compilation and evaluate the memory overhead it incurs on the runtime. Our measurements show that such systems are viable on a variety of low-resource hardware and previous research suggests that a production-ready system is likely to considerably improve the speed of WebAssembly on embedded system-on-chip.
{"title":"Support for Just-in-Time Compilation of WebAssembly for Embedded Systems","authors":"Konrad Moron, Stefan Wallentowitz","doi":"10.1109/MECO58584.2023.10155088","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155088","url":null,"abstract":"WebAssembly gains increasing interest outside the browser, such as in servers or desktops. It also becomes a viable candidate as a managed virtual machine for embedded systems, supported by multiple runtimes. However, the performance of interpreters is limited. Outside embedded systems, just-in-time compilation is used to significantly improve the performance of bytecode execution. Existing WebAssembly runtimes with just-in-time compilation support are either unsuitable for the use on low-resource hardware such as micro-controllers, or they employ a basic compilation strategy that doesn't utilize optimization opportunities and increases the compilation overhead. In this work, we present a micro-controller compatible WebAssembly runtime that supports the general framework for enabling advanced, feedback guided just-in-time compilation and evaluate the memory overhead it incurs on the runtime. Our measurements show that such systems are viable on a variety of low-resource hardware and previous research suggests that a production-ready system is likely to considerably improve the speed of WebAssembly on embedded system-on-chip.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129819338","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10154996
Tushar Singh, Jayant Prakash, Tushar Bharti, A. Mandpura
We introduce Visual servoing using a novel deep-learning time-series architecture to control an unmanned aerial vehicle (UAV) with a mounted camera to track a target consisting of a finite set of stationary points lying in a plane. Many visual servoing approaches use computer vision along with estimation algorithms, sensors, and actuators' feedback to solve tasks like, tracking, obstacle avoidance, and localization. Nowadays, deep neural networks are gaining popularity in such tasks owing to their accuracy, adaptability, and flexibility. We propose a solution that employs a time-series architecture to learn temporal data from sequential values to output the control cues to the flight controller. Because of its low computational expense, the solution is deployable on less powerful onboard computers present on the UAV, ensuring real-time tracking of the target. The solution is tested both in a simulation environment and in real life, outperforming the current state-of-the-art in terms of time efficiency and accuracy.
{"title":"Time Series Approach for Visual Servoing Using Transformers","authors":"Tushar Singh, Jayant Prakash, Tushar Bharti, A. Mandpura","doi":"10.1109/MECO58584.2023.10154996","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10154996","url":null,"abstract":"We introduce Visual servoing using a novel deep-learning time-series architecture to control an unmanned aerial vehicle (UAV) with a mounted camera to track a target consisting of a finite set of stationary points lying in a plane. Many visual servoing approaches use computer vision along with estimation algorithms, sensors, and actuators' feedback to solve tasks like, tracking, obstacle avoidance, and localization. Nowadays, deep neural networks are gaining popularity in such tasks owing to their accuracy, adaptability, and flexibility. We propose a solution that employs a time-series architecture to learn temporal data from sequential values to output the control cues to the flight controller. Because of its low computational expense, the solution is deployable on less powerful onboard computers present on the UAV, ensuring real-time tracking of the target. The solution is tested both in a simulation environment and in real life, outperforming the current state-of-the-art in terms of time efficiency and accuracy.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130329573","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10154927
Fortesa Gashi, Agon Memeti
In the global education organizations, a greater focus must be given to Blind and Visually Impaired (BVI) students who live in poorer countries. Specifically in countries whose languages, such as Albanian language, have minimal influence in world organizations. Thus, Albanian BVI students in the countries of Albania, Kosovo and North Macedonia (AKNM) have difficulties accessing teaching materials in schools. In order to contribute in the education of this category of students, we have developed a web application for which we aim to facilitate the acquisition of new knowledge in and outside the classroom. Moreover, it will help to identify new learning and teaching methods, as well as manage the course materials and users of the web application.
{"title":"An Audiobooks Web Application for K-12 Albanian-speaking Blind and Visually Impaired students","authors":"Fortesa Gashi, Agon Memeti","doi":"10.1109/MECO58584.2023.10154927","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10154927","url":null,"abstract":"In the global education organizations, a greater focus must be given to Blind and Visually Impaired (BVI) students who live in poorer countries. Specifically in countries whose languages, such as Albanian language, have minimal influence in world organizations. Thus, Albanian BVI students in the countries of Albania, Kosovo and North Macedonia (AKNM) have difficulties accessing teaching materials in schools. In order to contribute in the education of this category of students, we have developed a web application for which we aim to facilitate the acquisition of new knowledge in and outside the classroom. Moreover, it will help to identify new learning and teaching methods, as well as manage the course materials and users of the web application.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126548894","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10155082
T. Osipova, A. Baranov, I. Ivanov
In this article the possibility of determining the hydrogen concentration in a multicomponent gas mixture using the principal component analysis is investigated. Source data were obtained by a system, consisting of 8 sensors, each of which measured its own response values. It was found that, the values of the principal components form linear dependences of concentration, which are proportional to each other. At the same time, a different hydrogen concentration, pure or in a multicomponent mixture, is uniquely determined. The results showed that the principal component analysis allows both visually distinguishing sensor responses at different concentrations, and using additional mathematical operations to obtain the concentration value.
{"title":"Processing Data from Catalytic Sensors for Recognition of Hydrogen in Mixtures of Combustible Gases","authors":"T. Osipova, A. Baranov, I. Ivanov","doi":"10.1109/MECO58584.2023.10155082","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155082","url":null,"abstract":"In this article the possibility of determining the hydrogen concentration in a multicomponent gas mixture using the principal component analysis is investigated. Source data were obtained by a system, consisting of 8 sensors, each of which measured its own response values. It was found that, the values of the principal components form linear dependences of concentration, which are proportional to each other. At the same time, a different hydrogen concentration, pure or in a multicomponent mixture, is uniquely determined. The results showed that the principal component analysis allows both visually distinguishing sensor responses at different concentrations, and using additional mathematical operations to obtain the concentration value.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121343356","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10155010
A. Lipovec, Andrej Flogie
This study examines AI integration in K-12 education from the perspective of future teachers (N = 266). The results indicate that participants' attitudes towards AI are less favourable compared to the general population. The findings provide valuable insights into the need for incorporating AI-related topics in teacher training in novel ways.
{"title":"Empowering Future Teachers: Unveiling Their Attitudes and Knowledge about AI in Slovenian K-12 Education","authors":"A. Lipovec, Andrej Flogie","doi":"10.1109/MECO58584.2023.10155010","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155010","url":null,"abstract":"This study examines AI integration in K-12 education from the perspective of future teachers (N = 266). The results indicate that participants' attitudes towards AI are less favourable compared to the general population. The findings provide valuable insights into the need for incorporating AI-related topics in teacher training in novel ways.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132621581","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10154944
T. Barbu
Aneffective denoising and restoration framework that removes successfully theadditive white Gaussian noise (AWGN) from the spectral images is introduced inthis paper. Since the multispectral images can be described as vector-valuedfunctions, the proposed technique uses a novel partial differential equation(PDE)-based model created for this type of image functions. So, we consider anonlinear vector-valued hyperbolic PDE filtering model for the restorationtask. It is equivalent to a system of second-order hyperbolic equationsevolving simultaneously and sharing some coupling terms that model theinter-channel correlation. A finite difference-based fast-convergingdiscretization algorithm which solves numerically the PDE-based model ispresented next. It has been applied successfully in the MSI restorationexperiments that are also described here.
{"title":"Spectral Vector-valued Image Restoration using a Hyperbolic Partial Differential Equation-based Filter","authors":"T. Barbu","doi":"10.1109/MECO58584.2023.10154944","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10154944","url":null,"abstract":"Aneffective denoising and restoration framework that removes successfully theadditive white Gaussian noise (AWGN) from the spectral images is introduced inthis paper. Since the multispectral images can be described as vector-valuedfunctions, the proposed technique uses a novel partial differential equation(PDE)-based model created for this type of image functions. So, we consider anonlinear vector-valued hyperbolic PDE filtering model for the restorationtask. It is equivalent to a system of second-order hyperbolic equationsevolving simultaneously and sharing some coupling terms that model theinter-channel correlation. A finite difference-based fast-convergingdiscretization algorithm which solves numerically the PDE-based model ispresented next. It has been applied successfully in the MSI restorationexperiments that are also described here.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"142 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129313551","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10154915
S. Djordjević, M. Kostić, Danijela Milošević, M. Cvetković, Katarina Mitrovic, V. Mladenović
This paper aims to predict overhydration in the hemodialysis process using Artificial Neural Network. Dehydration has negative impacts on both physical and mental health, as is well-known. Overhydration's possible negative effects are, however, less known. A balanced state of the fluid in the body represents the essence of hemodialysis therapy. The prediction of volume-related adverse events has shown potential when using machine learning techniques. Several factors could influence overhydration, such as weight, blood pressure, lean tissue index, fat tissue index, body mass index, total body water, extracellular water, adipose tissue mass, body cell mass, and bioimpedance. The objective is to use an artificial neural network to estimate overhydration more accurately than current methods, which rely on measurable factors and the physician's judgment. The training and testing processes are explained, as well as the development of the artificial network model. The model achieved satisfactory results.
{"title":"Prediction of Overhydration in the Process of Pediatric Hemodialysis using Artificial Neural Network","authors":"S. Djordjević, M. Kostić, Danijela Milošević, M. Cvetković, Katarina Mitrovic, V. Mladenović","doi":"10.1109/MECO58584.2023.10154915","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10154915","url":null,"abstract":"This paper aims to predict overhydration in the hemodialysis process using Artificial Neural Network. Dehydration has negative impacts on both physical and mental health, as is well-known. Overhydration's possible negative effects are, however, less known. A balanced state of the fluid in the body represents the essence of hemodialysis therapy. The prediction of volume-related adverse events has shown potential when using machine learning techniques. Several factors could influence overhydration, such as weight, blood pressure, lean tissue index, fat tissue index, body mass index, total body water, extracellular water, adipose tissue mass, body cell mass, and bioimpedance. The objective is to use an artificial neural network to estimate overhydration more accurately than current methods, which rely on measurable factors and the physician's judgment. The training and testing processes are explained, as well as the development of the artificial network model. The model achieved satisfactory results.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128103960","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10155072
Fatima Mammadova, Daniel Onwuchekwa, R. Obermaisser
Melanoma is a skin cancer type and has the most dangerous consequences. Melanoma spreads to other organs very fast if not detected on time. Several non-invasive techniques exist which are applied in melanoma detection. An example is dermoscopy, which is an optical method and has the advantage of being less costly and easy to use. However, professional expertise is required to detect cancer in the early stage. Artificial Intelligence (AI) has been utilized in skin cancer detection by developing algorithms that can analyse images of skin lesions and identify the characteristics associated with various types of skin cancer, including melanoma. Nevertheless, information about the depth of the melanoma is not provided by the popular technique of using 2D images in training neural networks. The missing depth information is crucial to detecting melanoma and reaching decisions to execute biopsy when necessary. Radar sensors have shown the potential to provide this depth information due to its penetrating capability, allowing them to be applied in the detection of melanoma. The application of AI techniques using 2D images to detect melanoma, and the use of radar, has been investigated independently in recent literature. However, the combined technique still remains to be investigated. We propose integrating radar and image data to improve melanoma classification in this work. Based on the unavailability of radar data, the proposed technique is applied to the skin with nevi and birthmarks, clear skin, and body parts like inner palms, lower arms, and upper arms. The data from both sources are fused by applying an early fusion technique and later utilised for AI classification. Despite the small sample size, the fusion positively impacted classification compared to using only image data. The AI classification was performed on the first two cases, where the overall accuracy increased by 36% for both. Radar signals were also tested on wet and dry skin and have shown distinguishing results.
{"title":"Towards Melanoma Detection Using Radar and Image Data","authors":"Fatima Mammadova, Daniel Onwuchekwa, R. Obermaisser","doi":"10.1109/MECO58584.2023.10155072","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155072","url":null,"abstract":"Melanoma is a skin cancer type and has the most dangerous consequences. Melanoma spreads to other organs very fast if not detected on time. Several non-invasive techniques exist which are applied in melanoma detection. An example is dermoscopy, which is an optical method and has the advantage of being less costly and easy to use. However, professional expertise is required to detect cancer in the early stage. Artificial Intelligence (AI) has been utilized in skin cancer detection by developing algorithms that can analyse images of skin lesions and identify the characteristics associated with various types of skin cancer, including melanoma. Nevertheless, information about the depth of the melanoma is not provided by the popular technique of using 2D images in training neural networks. The missing depth information is crucial to detecting melanoma and reaching decisions to execute biopsy when necessary. Radar sensors have shown the potential to provide this depth information due to its penetrating capability, allowing them to be applied in the detection of melanoma. The application of AI techniques using 2D images to detect melanoma, and the use of radar, has been investigated independently in recent literature. However, the combined technique still remains to be investigated. We propose integrating radar and image data to improve melanoma classification in this work. Based on the unavailability of radar data, the proposed technique is applied to the skin with nevi and birthmarks, clear skin, and body parts like inner palms, lower arms, and upper arms. The data from both sources are fused by applying an early fusion technique and later utilised for AI classification. Despite the small sample size, the fusion positively impacted classification compared to using only image data. The AI classification was performed on the first two cases, where the overall accuracy increased by 36% for both. Radar signals were also tested on wet and dry skin and have shown distinguishing results.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131276873","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10155023
A. Bocci, Stefano Forti, Antonio Brogi
Utility computing paradigms (e.g, Fog, Edge, Mist computing) allow application operators to deploy applications onto heterogeneous resources along the infrastructure continuum spanning from virtually unbounded datacenters to resource-constrained Edge and IoT devices. Application operators must suitably select infrastructure resources where to deploy at best the services that compose their applications, and then manage the application life-cycle across the infrastructure. We propose a new view of the Cloud-Edge continuum, where infrastructure providers lease tailored portions of the infrastructure, determined by taking into account the hardware and QoS requirements as well as the sustainability goals expressed by application operators. Most importantly, infrastructure providers offer the selected Cloud-Edge infrastructure portion as a single virtual infrastructure node that customers can exploit to deploy and manage their applications in a seamless way.
{"title":"Sustainable Cloud-Edge Infrastructure as a Service","authors":"A. Bocci, Stefano Forti, Antonio Brogi","doi":"10.1109/MECO58584.2023.10155023","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155023","url":null,"abstract":"Utility computing paradigms (e.g, Fog, Edge, Mist computing) allow application operators to deploy applications onto heterogeneous resources along the infrastructure continuum spanning from virtually unbounded datacenters to resource-constrained Edge and IoT devices. Application operators must suitably select infrastructure resources where to deploy at best the services that compose their applications, and then manage the application life-cycle across the infrastructure. We propose a new view of the Cloud-Edge continuum, where infrastructure providers lease tailored portions of the infrastructure, determined by taking into account the hardware and QoS requirements as well as the sustainability goals expressed by application operators. Most importantly, infrastructure providers offer the selected Cloud-Edge infrastructure portion as a single virtual infrastructure node that customers can exploit to deploy and manage their applications in a seamless way.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123309285","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 : 2023-06-06DOI: 10.1109/MECO58584.2023.10155107
M. Kuzlu, Zhenxin Xiao, S. Sarp, Ferhat Ozgur Catak, Necip Gurler, Ozgur Guler
Generative Artificial Intelligence (GAI) is transforming various fields, including finance, education, marketing, and healthcare. Especially in healthcare, GAI has the potential to revolutionize various aspects, such as medical imaging, drug development, patient care, and treatment planning. Key stakeholders who stand to benefit from these advancements include hospitals, clinics, pharmaceutical companies, medical device manufacturers, and research institutions. However, the implementation of GAI in healthcare presents several challenges, such as ensuring data privacy and security, addressing ethical considerations, maintaining quality and accuracy, adhering to regulatory compliance, and integrating with existing systems. This paper examines the current state of GAI in healthcare, discusses its potential benefits and challenges, and highlights future directions that must be addressed to fully harness the power of GAI in improving patient outcomes and healthcare systems.
{"title":"The Rise of Generative Artificial Intelligence in Healthcare","authors":"M. Kuzlu, Zhenxin Xiao, S. Sarp, Ferhat Ozgur Catak, Necip Gurler, Ozgur Guler","doi":"10.1109/MECO58584.2023.10155107","DOIUrl":"https://doi.org/10.1109/MECO58584.2023.10155107","url":null,"abstract":"Generative Artificial Intelligence (GAI) is transforming various fields, including finance, education, marketing, and healthcare. Especially in healthcare, GAI has the potential to revolutionize various aspects, such as medical imaging, drug development, patient care, and treatment planning. Key stakeholders who stand to benefit from these advancements include hospitals, clinics, pharmaceutical companies, medical device manufacturers, and research institutions. However, the implementation of GAI in healthcare presents several challenges, such as ensuring data privacy and security, addressing ethical considerations, maintaining quality and accuracy, adhering to regulatory compliance, and integrating with existing systems. This paper examines the current state of GAI in healthcare, discusses its potential benefits and challenges, and highlights future directions that must be addressed to fully harness the power of GAI in improving patient outcomes and healthcare systems.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116797222","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：