Pub Date : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284816
Agrippina Mwangi, Emmanuel Ndashimye, Bonaventure Karikumutima, S. K. Ray
Asthma claims thousands of lives every year, especially during the cold season, mostly because of delayed access to first-aid and lack of immediate and adequate medical care. Asthma-related fatalities are preventable by home remedies, exercises, prescribed treatments, and providing rapid response and care to patients in case of asthma attacks. The latter is paramount to many asthmatics who are not able to predict an asthma attack well in advance. This work proposes and deploys an IoT-alert system that a chronic asthma patient (or any asthma patient) can use to trigger an alert to inform emergency contacts in case of a sudden asthma attack. This research, done in Rwanda, aims to alert emergency contacts early enough for a rapid response in order to reduce the number of asthma-related deaths in the country. The proposed system, in its basic form, uses a keypad unit as an interaction point with the users, which when pressed triggers the alert system to send SMS messages to registered emergency contacts and sounds a buzzer to alert few of the immediate neighbours of the asthma patients living close by. The intention is to provide support and help the chronic asthma patients, particularly those living alone, to receive appropriate medical aid within five minutes of alerting the neighbors and emergency contacts during a sudden asthma attack. The keypad interaction unit, which is the primary component of this IoT-alert system, can be wall-mounted in any room so that patients can easily access it. A small functioning prototype of the proposed system has been successfully tested at Kigali and testing has proven its effectiveness in helping the asthma patients.
{"title":"An IoT-alert System for Chronic Asthma Patients","authors":"Agrippina Mwangi, Emmanuel Ndashimye, Bonaventure Karikumutima, S. K. Ray","doi":"10.1109/IEMCON51383.2020.9284816","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284816","url":null,"abstract":"Asthma claims thousands of lives every year, especially during the cold season, mostly because of delayed access to first-aid and lack of immediate and adequate medical care. Asthma-related fatalities are preventable by home remedies, exercises, prescribed treatments, and providing rapid response and care to patients in case of asthma attacks. The latter is paramount to many asthmatics who are not able to predict an asthma attack well in advance. This work proposes and deploys an IoT-alert system that a chronic asthma patient (or any asthma patient) can use to trigger an alert to inform emergency contacts in case of a sudden asthma attack. This research, done in Rwanda, aims to alert emergency contacts early enough for a rapid response in order to reduce the number of asthma-related deaths in the country. The proposed system, in its basic form, uses a keypad unit as an interaction point with the users, which when pressed triggers the alert system to send SMS messages to registered emergency contacts and sounds a buzzer to alert few of the immediate neighbours of the asthma patients living close by. The intention is to provide support and help the chronic asthma patients, particularly those living alone, to receive appropriate medical aid within five minutes of alerting the neighbors and emergency contacts during a sudden asthma attack. The keypad interaction unit, which is the primary component of this IoT-alert system, can be wall-mounted in any room so that patients can easily access it. A small functioning prototype of the proposed system has been successfully tested at Kigali and testing has proven its effectiveness in helping the asthma patients.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"31 1","pages":"0012-0019"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77054754","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284900
L. Nahar, S. Zafar, Faria Binta Rafiq
Internet of Things (IoT) empowers people to get more significant level of mechanization by creating framework, utilizing sensors and interconnecting gadgets and Internet. In ICU, silent checking is basic and the most significant action, as little delay in choice identified with patient's treatment may cause perpetual inability or even passing. Arranged sensors (either worn on the body or introduced in our living environmental factors), allow to acquire rich information collectively for our physical and mental prosperity. Currently to start with, the chances and difficulties of IoT can be featured in understanding this vision of things in terms of medicinal services. It can be given an opportunity to develop a new patient checking canny framework in order to improve clinical administration. Through this work, a crossover engineering have been offered over a solitary stage for a visual patient checking framework for Automatic Detection of hazard Situations and Alerts (ADSA) by utilizing a multi-camera framework and communitarian clinical sensors. The majority of ICU gadgets are furnished with different sensors to quantify wellbeing parameters, yet to screen it all the time. Here an IOT based framework have been proposed in the health care system, which can assist with fast correspondence, recognize crisis and start to communicate with human services staff. Furthermore, it can assist with starting proactive and speedy treatment. This medicinal services framework will lessen the plausibility of human mistakes, delays in correspondence and encourage specialist to save additional time in choice with precise perceptions.
{"title":"IOT Based ICU Patient Health Monitoring System","authors":"L. Nahar, S. Zafar, Faria Binta Rafiq","doi":"10.1109/IEMCON51383.2020.9284900","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284900","url":null,"abstract":"Internet of Things (IoT) empowers people to get more significant level of mechanization by creating framework, utilizing sensors and interconnecting gadgets and Internet. In ICU, silent checking is basic and the most significant action, as little delay in choice identified with patient's treatment may cause perpetual inability or even passing. Arranged sensors (either worn on the body or introduced in our living environmental factors), allow to acquire rich information collectively for our physical and mental prosperity. Currently to start with, the chances and difficulties of IoT can be featured in understanding this vision of things in terms of medicinal services. It can be given an opportunity to develop a new patient checking canny framework in order to improve clinical administration. Through this work, a crossover engineering have been offered over a solitary stage for a visual patient checking framework for Automatic Detection of hazard Situations and Alerts (ADSA) by utilizing a multi-camera framework and communitarian clinical sensors. The majority of ICU gadgets are furnished with different sensors to quantify wellbeing parameters, yet to screen it all the time. Here an IOT based framework have been proposed in the health care system, which can assist with fast correspondence, recognize crisis and start to communicate with human services staff. Furthermore, it can assist with starting proactive and speedy treatment. This medicinal services framework will lessen the plausibility of human mistakes, delays in correspondence and encourage specialist to save additional time in choice with precise perceptions.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"33 1","pages":"0407-0413"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87155230","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284870
Antonio Carlos Bento
The main objective of this work is to present the results of an experimental study using the NodeMCU12e devices with Shield, together with the Tft Nextion and the heart rate sensor MAX30102, normally these devices are used for projects that involve the Internet of Things (IoT), commonly used to create residential and electronic automation solutions, this project demonstrate how to build a solution for heart rate and pulse monitoring. The use of these resources allows the adequacy and control of patients, as well as for monitoring people who need special care. The results present a solution applicable in prototype format, which can be evolved to more complex models, serving as the basis for the development of more robust solutions and studies.
{"title":"An Experimental Survey with NodeMCU12e+Shield with Tft Nextion and MAX30102 Sensor","authors":"Antonio Carlos Bento","doi":"10.1109/IEMCON51383.2020.9284870","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284870","url":null,"abstract":"The main objective of this work is to present the results of an experimental study using the NodeMCU12e devices with Shield, together with the Tft Nextion and the heart rate sensor MAX30102, normally these devices are used for projects that involve the Internet of Things (IoT), commonly used to create residential and electronic automation solutions, this project demonstrate how to build a solution for heart rate and pulse monitoring. The use of these resources allows the adequacy and control of patients, as well as for monitoring people who need special care. The results present a solution applicable in prototype format, which can be evolved to more complex models, serving as the basis for the development of more robust solutions and studies.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"21 1","pages":"0082-0086"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87309033","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284871
Pravir Malik, Lalitha Nallamothula
The four quantum phenomena of superposition, entanglement, tunneling, and annealing are envisioned to give quantum computing the ability to solve complex problems in very low-resolution times as compared with classical computers. These four phenomena are closely related to the light-based properties of presence, knowledge, power, and harmony, central to a multilayered light-based model of reality that also offers alternative foundation for thinking about quanta and quantum computation. In this model, it is not a random process from infinite superposed possibilities that exist at the quantum-level as supposed by the Copenhagen Interpretation, and as assumed as the foundation of the infinite processing capability of quantum objects by contemporary pioneers of quantum computing. Rather, the infinite processing capability is due to a more ordered display of superposition, entanglement, tunneling and annealing: superposition, as an ordered concord of light's property of presence stacked in logical arrangement by layer of light; entanglement, as a display of light's property of knowledge that occurs at a speed faster than the known speed of light; tunneling, as a display of light's property of power that allows toggling between different “realities” in layers of light; and annealing, expressing light's property of harmony, to find an ideal minimum state among a number of realities. These four quantum phenomena derivative from an implicit and natural unity within light, engineered to maintain that unity externally, will confer quantum computation with the possibility of extraordinary processing power.
{"title":"Fourfold Properties of Light and its Relevance to Quantum Computation","authors":"Pravir Malik, Lalitha Nallamothula","doi":"10.1109/IEMCON51383.2020.9284871","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284871","url":null,"abstract":"The four quantum phenomena of superposition, entanglement, tunneling, and annealing are envisioned to give quantum computing the ability to solve complex problems in very low-resolution times as compared with classical computers. These four phenomena are closely related to the light-based properties of presence, knowledge, power, and harmony, central to a multilayered light-based model of reality that also offers alternative foundation for thinking about quanta and quantum computation. In this model, it is not a random process from infinite superposed possibilities that exist at the quantum-level as supposed by the Copenhagen Interpretation, and as assumed as the foundation of the infinite processing capability of quantum objects by contemporary pioneers of quantum computing. Rather, the infinite processing capability is due to a more ordered display of superposition, entanglement, tunneling and annealing: superposition, as an ordered concord of light's property of presence stacked in logical arrangement by layer of light; entanglement, as a display of light's property of knowledge that occurs at a speed faster than the known speed of light; tunneling, as a display of light's property of power that allows toggling between different “realities” in layers of light; and annealing, expressing light's property of harmony, to find an ideal minimum state among a number of realities. These four quantum phenomena derivative from an implicit and natural unity within light, engineered to maintain that unity externally, will confer quantum computation with the possibility of extraordinary processing power.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"55 1","pages":"0707-0711"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87077790","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284919
S. Manoharan, Bilal Sariffodeen, K.T Ramasinghe, L.H Rajaratne, D. Kasthurirathna, J. Wijekoon
The soil composition around the world is depleting at a rapid rate due to overexploitation by the unsustainable use of fertilizers. Streamlining the availability of nutrient deficiency and fertilizer related knowledge among impoverished farming communities would promoter environmentally and scientifically sustainable farming practices. Thus, contributing to several Sustainable Development Goals set out by the United Nations. The most direct solution to the inappropriate fertilizer usage is to add only the necessary amounts of fertilizer required by plants to produce a significant yield without nutrition deficiencies. To this end this paper proposes a Smart Nutrient Disorder Identification system employing computer vision and machine learning techniques for identification purposes and a decentralized blockchain platform to streamline a bias-less procurement system. The proposed system yielded 88% accuracy in disorder identification, while also enabling secure, transparent flow of verified information.
{"title":"Smart Plant Disorder Identification using Computer Vision Technology","authors":"S. Manoharan, Bilal Sariffodeen, K.T Ramasinghe, L.H Rajaratne, D. Kasthurirathna, J. Wijekoon","doi":"10.1109/IEMCON51383.2020.9284919","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284919","url":null,"abstract":"The soil composition around the world is depleting at a rapid rate due to overexploitation by the unsustainable use of fertilizers. Streamlining the availability of nutrient deficiency and fertilizer related knowledge among impoverished farming communities would promoter environmentally and scientifically sustainable farming practices. Thus, contributing to several Sustainable Development Goals set out by the United Nations. The most direct solution to the inappropriate fertilizer usage is to add only the necessary amounts of fertilizer required by plants to produce a significant yield without nutrition deficiencies. To this end this paper proposes a Smart Nutrient Disorder Identification system employing computer vision and machine learning techniques for identification purposes and a decentralized blockchain platform to streamline a bias-less procurement system. The proposed system yielded 88% accuracy in disorder identification, while also enabling secure, transparent flow of verified information.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"1 1","pages":"0445-0451"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82893724","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284914
David Airehrour, M. Cherrington, K. Rajagopal
According to the World Health Organization (WHO), about 91% of the global populace live in locations with air quality levels below WHO guidelines. Although ambient air pollution impacts both developed and developing nations, low- and middle-income nations suffer the highest consequences with the highest toll experienced in the Western Pacific and South East Asia regions. Poor air quality results in odour types ranging from chemical combustion smells to fungal smells. Fungal odour is formed due to damp indoor conditions like high humidity and temperature. This damp condition produces microscopic fungi which are allergens (substances that cause allergic reactions), irritants and toxic substances referred to as mould. Inhaling or touching mould spores may cause allergic reactions like sneezing, runny nose, redness of the eyes and skin rash and even respiratory complications. In this era of a global pandemic, having a general-purpose odour detection system becomes imperative. This research, therefore, aims to design and implement an odour detection system that can alert individuals or allergic sufferers to high content of toxic gases in their surroundings or homes. The study is a valuable resource for users to measure their air quality and to support those with respiratory vulnerabilities, especially in the Covid-19 environment of today.
{"title":"Odour Detection System for Allergy Sufferers","authors":"David Airehrour, M. Cherrington, K. Rajagopal","doi":"10.1109/IEMCON51383.2020.9284914","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284914","url":null,"abstract":"According to the World Health Organization (WHO), about 91% of the global populace live in locations with air quality levels below WHO guidelines. Although ambient air pollution impacts both developed and developing nations, low- and middle-income nations suffer the highest consequences with the highest toll experienced in the Western Pacific and South East Asia regions. Poor air quality results in odour types ranging from chemical combustion smells to fungal smells. Fungal odour is formed due to damp indoor conditions like high humidity and temperature. This damp condition produces microscopic fungi which are allergens (substances that cause allergic reactions), irritants and toxic substances referred to as mould. Inhaling or touching mould spores may cause allergic reactions like sneezing, runny nose, redness of the eyes and skin rash and even respiratory complications. In this era of a global pandemic, having a general-purpose odour detection system becomes imperative. This research, therefore, aims to design and implement an odour detection system that can alert individuals or allergic sufferers to high content of toxic gases in their surroundings or homes. The study is a valuable resource for users to measure their air quality and to support those with respiratory vulnerabilities, especially in the Covid-19 environment of today.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"62 1","pages":"0193-0200"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80574295","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284913
Christian Nwankwo, H. Wimmer, Lei Chen, Jongyeop Kim
This research aims to propose a model to classify text messages that extracted from the smart phone using forensic software and several machine learning algorithms. The data analysis procedure subdivided into physical extraction, relevant partitions, logical extraction, digital forensic analysis, and text classification. In the text classification step, the final result derived by applying sentiment analysis and k-means clustering algorithm under the control of python application. Through this model, we were able to classify most of the messages correctly as either being positive or negative.
{"title":"Text Classification of Digital Forensic Data","authors":"Christian Nwankwo, H. Wimmer, Lei Chen, Jongyeop Kim","doi":"10.1109/IEMCON51383.2020.9284913","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284913","url":null,"abstract":"This research aims to propose a model to classify text messages that extracted from the smart phone using forensic software and several machine learning algorithms. The data analysis procedure subdivided into physical extraction, relevant partitions, logical extraction, digital forensic analysis, and text classification. In the text classification step, the final result derived by applying sentiment analysis and k-means clustering algorithm under the control of python application. Through this model, we were able to classify most of the messages correctly as either being positive or negative.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"21 1","pages":"0661-0667"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89250461","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284942
Mohamed Karim Laoufi, S. Mekaoui, M. L. Tounsi
In this paper, a new formulation of the finite difference time domain technique (FDTD) was applied for an efficient hybrid-mode analysis of inhomogeneous planar waveguides and filters. An enhanced analytical formula for the cut-off frequency was also proposed for a three-layer waveguide while the shielding effect was investigated on bandpass filter performance. The computed S-parameters are in good agreement with simulated ones obtained with CST electromagnetic tool.
{"title":"An Enhanced FDTD Algorithm for Analyzing Inhomogeneous Multilayer Waveguides and Filters","authors":"Mohamed Karim Laoufi, S. Mekaoui, M. L. Tounsi","doi":"10.1109/IEMCON51383.2020.9284942","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284942","url":null,"abstract":"In this paper, a new formulation of the finite difference time domain technique (FDTD) was applied for an efficient hybrid-mode analysis of inhomogeneous planar waveguides and filters. An enhanced analytical formula for the cut-off frequency was also proposed for a three-layer waveguide while the shielding effect was investigated on bandpass filter performance. The computed S-parameters are in good agreement with simulated ones obtained with CST electromagnetic tool.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"1 1","pages":"0692-0695"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89296034","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284938
Gustavo Salazar-Chacón, L. Marrone
This Proof-of-Concept (PoC) research presents a conceptualization of main OpenFlow Southbound messages found in Software-Defined Networks. The use of an open-source network emulator has allowed to conduct traffic captures in order to contrast the theory with a high reliability PoC scenario. This paper begins by defining SDN according to Open Networking Foundation (ONF), as well as identifying characteristics, elements, and fundamental protocols of this technology that is changing the traditional paradigm of sending data. In order to test theory in practice, an OpenFlow network built with an Open-vSwitch (OVS), two hosts and external SDN Docker Controller were emulated using Mininet, a very efficient controller-based emulator. Later, SDN-packet captures were done for analysis. Connectivity tests are proposed to capture OpenFlow messages exchanged between different devices of the network, and with that, verifying its encapsulation, structure, and vulnerabilities. The ultimate aim of the present paper is to provide a clearer and more understandable vision of SDN and its operation in the real world.
{"title":"OpenSDN Southbound Traffic Characterization: Proof-of-Concept Virtualized SDN-Infrastructure","authors":"Gustavo Salazar-Chacón, L. Marrone","doi":"10.1109/IEMCON51383.2020.9284938","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284938","url":null,"abstract":"This Proof-of-Concept (PoC) research presents a conceptualization of main OpenFlow Southbound messages found in Software-Defined Networks. The use of an open-source network emulator has allowed to conduct traffic captures in order to contrast the theory with a high reliability PoC scenario. This paper begins by defining SDN according to Open Networking Foundation (ONF), as well as identifying characteristics, elements, and fundamental protocols of this technology that is changing the traditional paradigm of sending data. In order to test theory in practice, an OpenFlow network built with an Open-vSwitch (OVS), two hosts and external SDN Docker Controller were emulated using Mininet, a very efficient controller-based emulator. Later, SDN-packet captures were done for analysis. Connectivity tests are proposed to capture OpenFlow messages exchanged between different devices of the network, and with that, verifying its encapsulation, structure, and vulnerabilities. The ultimate aim of the present paper is to provide a clearer and more understandable vision of SDN and its operation in the real world.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"11 1","pages":"0282-0287"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89490018","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284931
Michael Chi Seng Tang, S. S. Teoh
Diabetic Retinopathy (DR) is a severe eye disease that could lead to sight loss. This disease is caused by damages in the blood vessels of the retina due to prolonged high blood glucose level. DR is characterized by the presence lesions and the formation of abnormal blood vessels in the retina called neovascularization. Early detection of DR is essential to prevent the disease from worsening and avoid early loss of vision in diabetic patients. Identification and segmentation of retinal blood vessels from fundus images are crucial tasks for automatic DR detection. This paper presents a blood vessel segmentation technique using Hessian Matrix. First, the green channel is extracted from the fundus image in the pre-processing stage. A Gaussian filter is then used to smoothen the image. Next, the Hessian Matrix is constructed to calculate the maximum principal curvature of the image's intensity for extracting the blood vessels' structure. The retina's boundary is then removed to reduce false detection. In the post-processing stage, morphological erosion is used to remove noise from the image. Contrast-limited adaptive histogram equalization (CLAHE) is then applied to enhance the resulting image. Finally, Iterative Self-Organizing Data Analysis (ISODATA) thresholding technique is used to binarize the image. Experiments were conducted to evaluate the proposed method's performance using fundus images obtained from DRIVE, HRF, and STARE datasets. The results showed that the technique could provide good accuracy on average up to 0.95.
{"title":"Blood Vessel Segmentation in Fundus Images Using Hessian Matrix for Diabetic Retinopathy Detection","authors":"Michael Chi Seng Tang, S. S. Teoh","doi":"10.1109/IEMCON51383.2020.9284931","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284931","url":null,"abstract":"Diabetic Retinopathy (DR) is a severe eye disease that could lead to sight loss. This disease is caused by damages in the blood vessels of the retina due to prolonged high blood glucose level. DR is characterized by the presence lesions and the formation of abnormal blood vessels in the retina called neovascularization. Early detection of DR is essential to prevent the disease from worsening and avoid early loss of vision in diabetic patients. Identification and segmentation of retinal blood vessels from fundus images are crucial tasks for automatic DR detection. This paper presents a blood vessel segmentation technique using Hessian Matrix. First, the green channel is extracted from the fundus image in the pre-processing stage. A Gaussian filter is then used to smoothen the image. Next, the Hessian Matrix is constructed to calculate the maximum principal curvature of the image's intensity for extracting the blood vessels' structure. The retina's boundary is then removed to reduce false detection. In the post-processing stage, morphological erosion is used to remove noise from the image. Contrast-limited adaptive histogram equalization (CLAHE) is then applied to enhance the resulting image. Finally, Iterative Self-Organizing Data Analysis (ISODATA) thresholding technique is used to binarize the image. Experiments were conducted to evaluate the proposed method's performance using fundus images obtained from DRIVE, HRF, and STARE datasets. The results showed that the technique could provide good accuracy on average up to 0.95.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"50 1","pages":"0728-0733"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90237577","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：