Pub Date : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982514
Pathathai Na-Lumpoon, Pree Thiengburanathum
At present, the higher education institutes focus on the learning outcomes that curriculums can produce graduates with qualified employability skills. Work Integrated Learning (WIL) center is a unit in academic faculty that aims to develop students’ competencies at workplace and classroom based on the integrated learning outcomes. However, measuring the performances of the WIL program is a difficult task such that the related key performance indicators are not identified. In this paper, we developed a novel model of the KPIs of WIL activities and the relevant employability skills. Additionally, design and implementation of the dashboards to display and monitor the defined KPIs are presented. As a result, users can gain insightful information and provide confidence for decision makers.
{"title":"A Design and Implementation of Performance Dashboard for the Work Integrated Learning Unit","authors":"Pathathai Na-Lumpoon, Pree Thiengburanathum","doi":"10.1109/SKIMA47702.2019.8982514","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982514","url":null,"abstract":"At present, the higher education institutes focus on the learning outcomes that curriculums can produce graduates with qualified employability skills. Work Integrated Learning (WIL) center is a unit in academic faculty that aims to develop students’ competencies at workplace and classroom based on the integrated learning outcomes. However, measuring the performances of the WIL program is a difficult task such that the related key performance indicators are not identified. In this paper, we developed a novel model of the KPIs of WIL activities and the relevant employability skills. Additionally, design and implementation of the dashboards to display and monitor the defined KPIs are presented. As a result, users can gain insightful information and provide confidence for decision makers.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130986899","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982427
Moruf Akin Adebowale, Khin T. Lwin, Mohammed Alamgir Hossain
Phishers sometimes exploit users’ trust of a known website’s appearance by using a similar page that looks like the legitimate site. In recent times, researchers have tried to identify and classify the issues that can contribute to the detection of phishing websites. This study focuses on design and development of a deep learning based phishing detection solution that leverages the Universal Resource Locator and website content such as images and frame elements. A Convolutional Neural Network (CNN) and the Long Short-Term Memory (LSTM) algorithm were used to build a classification model. The experimental results showed that the proposed model achieved an accuracy rate of 93.28%.
{"title":"Deep Learning with Convolutional Neural Network and Long Short-Term Memory for Phishing Detection","authors":"Moruf Akin Adebowale, Khin T. Lwin, Mohammed Alamgir Hossain","doi":"10.1109/SKIMA47702.2019.8982427","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982427","url":null,"abstract":"Phishers sometimes exploit users’ trust of a known website’s appearance by using a similar page that looks like the legitimate site. In recent times, researchers have tried to identify and classify the issues that can contribute to the detection of phishing websites. This study focuses on design and development of a deep learning based phishing detection solution that leverages the Universal Resource Locator and website content such as images and frame elements. A Convolutional Neural Network (CNN) and the Long Short-Term Memory (LSTM) algorithm were used to build a classification model. The experimental results showed that the proposed model achieved an accuracy rate of 93.28%.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124718712","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982392
D. A. Zebari, H. Haron, D. Zeebaree, A. Zain
The Data Compression is a creative skill which defined scientific concepts of providing contents in a compact form. Thus, it has turned into a need in the field of communication as well as in different scientific studies. Data transmission must be sufficiently secure to be utilized in a channel medium with no misfortune; and altering of information. Encryption is the way toward scrambling an information with the goal that just the known receiver can peruse or see it. Encryption can give methods for anchoring data. Along these lines, the two strategies are the two crucial advances that required for the protected transmission of huge measure of information. In typical cases, the compacted information is encoded and transmitted. In any case, this sequential technique is time consumption and computationally cost. In the present paper, an examination on simultaneous compression and encryption technique depends on DNA which is proposed for various sorts of secret data. In simultaneous technique, both techniques can be done at single step which lessens the time for the whole task. The present work is consisting of two phases. First phase, encodes the plaintext by 6-bits instead of 8-bits, means each character represented by three DNA nucleotides whereas to encode any pixel of image by four DNA nucleotides. This phase can compress the plaintext by 25% of the original text. Second phase, compression and encryption has been done at the same time. Both types of data have been compressed by their half size as well as encrypted the generated symmetric key. Thus, this technique is more secure against intruders. Experimental results show a better performance of the proposed scheme compared with standard compression techniques.
{"title":"A Simultaneous Approach for Compression and Encryption Techniques Using Deoxyribonucleic Acid","authors":"D. A. Zebari, H. Haron, D. Zeebaree, A. Zain","doi":"10.1109/SKIMA47702.2019.8982392","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982392","url":null,"abstract":"The Data Compression is a creative skill which defined scientific concepts of providing contents in a compact form. Thus, it has turned into a need in the field of communication as well as in different scientific studies. Data transmission must be sufficiently secure to be utilized in a channel medium with no misfortune; and altering of information. Encryption is the way toward scrambling an information with the goal that just the known receiver can peruse or see it. Encryption can give methods for anchoring data. Along these lines, the two strategies are the two crucial advances that required for the protected transmission of huge measure of information. In typical cases, the compacted information is encoded and transmitted. In any case, this sequential technique is time consumption and computationally cost. In the present paper, an examination on simultaneous compression and encryption technique depends on DNA which is proposed for various sorts of secret data. In simultaneous technique, both techniques can be done at single step which lessens the time for the whole task. The present work is consisting of two phases. First phase, encodes the plaintext by 6-bits instead of 8-bits, means each character represented by three DNA nucleotides whereas to encode any pixel of image by four DNA nucleotides. This phase can compress the plaintext by 25% of the original text. Second phase, compression and encryption has been done at the same time. Both types of data have been compressed by their half size as well as encrypted the generated symmetric key. Thus, this technique is more secure against intruders. Experimental results show a better performance of the proposed scheme compared with standard compression techniques.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126884938","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982388
Dóra Ori, Z. Szabó
Strategic alignment is a complex coalignment process of strategy, organization, IT and management. Enterprise architecture model describes the fundamental structure of a system, including its components and their relationships, providing a holistic view that integrates business and technology domain. The goal of this paper is to discuss enterprise architecture management (EAM) based opportunities for supporting strategic alignment process, and to provide a systematic review of available methods and analysing tools. Strategic alignment process has four phases that can be described by the combination of EAM components. Existing EAM-based tools, methods and new EA model-based analysing approaches can be directly used in the dynamic alignment process, by discovering problems and opportunities.
{"title":"Towards Dynamic Fit Assessment for Strategic Alignment using Enterprise Architecture Models","authors":"Dóra Ori, Z. Szabó","doi":"10.1109/SKIMA47702.2019.8982388","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982388","url":null,"abstract":"Strategic alignment is a complex coalignment process of strategy, organization, IT and management. Enterprise architecture model describes the fundamental structure of a system, including its components and their relationships, providing a holistic view that integrates business and technology domain. The goal of this paper is to discuss enterprise architecture management (EAM) based opportunities for supporting strategic alignment process, and to provide a systematic review of available methods and analysing tools. Strategic alignment process has four phases that can be described by the combination of EAM components. Existing EAM-based tools, methods and new EA model-based analysing approaches can be directly used in the dynamic alignment process, by discovering problems and opportunities.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121600397","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982472
Muhammad Awais Shoukat, Allah Bux Sargano, Z. Habib, L. You
In this paper, the problem of single 2D image depth estimation is considered. This is a very important problem due to its various applications in the industry. Previous learning-based methods are based on a key assumption that color images having photometric resemblance are likely to present similar depth structure. However, these methods search the whole dataset for finding corresponding images using handcrafted features, which is quite cumbersome and inefficient process. To overcome this, we have proposed a clustering-based algorithm for depth estimation of a single 2D image using transfer learning. To realize this, images are categorized into clusters using K-means clustering algorithm and features are extracted through a pre-trained deep learning model i.e., ResNet-50. After clustering, an efficient step of replacing feature vector is embedded to speedup the process without compromising on accuracy. After then, images with similar structure as an input image, are retrieved from the best matched cluster based on their correlation values. Then, retrieved candidate depth images are employed to initialize prior depth of a query image using weighted-correlation-average (WCA). Finally, the estimated depth is improved by removing variations using cross-bilateral-filter. In order to evaluate the performance of proposed algorithm, experiments are conducted on two benchmark datasets, NYU v2 and Make3D.
{"title":"An automatic cluster-based approach for depth estimation of single 2D images","authors":"Muhammad Awais Shoukat, Allah Bux Sargano, Z. Habib, L. You","doi":"10.1109/SKIMA47702.2019.8982472","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982472","url":null,"abstract":"In this paper, the problem of single 2D image depth estimation is considered. This is a very important problem due to its various applications in the industry. Previous learning-based methods are based on a key assumption that color images having photometric resemblance are likely to present similar depth structure. However, these methods search the whole dataset for finding corresponding images using handcrafted features, which is quite cumbersome and inefficient process. To overcome this, we have proposed a clustering-based algorithm for depth estimation of a single 2D image using transfer learning. To realize this, images are categorized into clusters using K-means clustering algorithm and features are extracted through a pre-trained deep learning model i.e., ResNet-50. After clustering, an efficient step of replacing feature vector is embedded to speedup the process without compromising on accuracy. After then, images with similar structure as an input image, are retrieved from the best matched cluster based on their correlation values. Then, retrieved candidate depth images are employed to initialize prior depth of a query image using weighted-correlation-average (WCA). Finally, the estimated depth is improved by removing variations using cross-bilateral-filter. In order to evaluate the performance of proposed algorithm, experiments are conducted on two benchmark datasets, NYU v2 and Make3D.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129146773","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982536
N. Jeyamohan, Xiaomin Chen, N. Aslam
In recent years recommendation systems have become popular in the e-commerce industry as they can be used to provide a personalized experience to users. However, performing analytics on users’ information has also raised privacy concerns. Various privacy protection mechanisms have been proposed for recommendation systems against user-side adversaries. However most of them disregards the privacy violations caused by the service providers. In this paper, we propose a local differential privacy mechanism for matrix factorization based recommendation systems. In our mechanism, users perturb their ratings locally on their devices using Laplace and randomized response mechanisms and send the perturbed ratings to the service provider. We evaluate the proposed mechanism using Movielens dataset and demonstrate that it can achieve a satisfactory tradeoff between data utility and user privacy.
{"title":"Local Differentially Private Matrix Factorization For Recommendations","authors":"N. Jeyamohan, Xiaomin Chen, N. Aslam","doi":"10.1109/SKIMA47702.2019.8982536","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982536","url":null,"abstract":"In recent years recommendation systems have become popular in the e-commerce industry as they can be used to provide a personalized experience to users. However, performing analytics on users’ information has also raised privacy concerns. Various privacy protection mechanisms have been proposed for recommendation systems against user-side adversaries. However most of them disregards the privacy violations caused by the service providers. In this paper, we propose a local differential privacy mechanism for matrix factorization based recommendation systems. In our mechanism, users perturb their ratings locally on their devices using Laplace and randomized response mechanisms and send the perturbed ratings to the service provider. We evaluate the proposed mechanism using Movielens dataset and demonstrate that it can achieve a satisfactory tradeoff between data utility and user privacy.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131858760","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982399
Ankhbayar Otgonbayar, Zeeshan Pervez, K. Dahal
The IoT and its applications are the inseparable part of modern world. IoT is expanding into every corner of the world where internet is available. IoT data streams are utilized by many organizations for research and business. To benefit from these data streams, the data handling party must secure the individuals’ privacy. The most common privacy preservation approach is data anonymization. However, IoT data provides missing data streams due to the varying device pool and preferences of individuals and unpredicted devices’ malfunctions of IoT. Minimization of missingess and information loss is very important for anonymizing of missing data streams. To achieve this, we introduce IncrementalPBM (Incremental Partitioning Based Marginalization) for anonymizing missig data streams. IncrementalPBM utilizes time based sliding window for missing data stream anonymization, and it aims to control the number of QIDs for anonymization while increasing the number of tuples for anonymization. Our experiment on real dataset showed IncrementalPBM is effective and efficient for anonymizing missing data streams compared to existing missing data stream anonymization algorithm. IncrementalPBM showed significant improvement; 5% to 9% less information loss, 4500 to 6000 more number of re-use anonymization while showing comparable clustering, suppression and runtime.
{"title":"Partitioning based incremental marginalization algorithm for anonymizing missing data streams","authors":"Ankhbayar Otgonbayar, Zeeshan Pervez, K. Dahal","doi":"10.1109/SKIMA47702.2019.8982399","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982399","url":null,"abstract":"The IoT and its applications are the inseparable part of modern world. IoT is expanding into every corner of the world where internet is available. IoT data streams are utilized by many organizations for research and business. To benefit from these data streams, the data handling party must secure the individuals’ privacy. The most common privacy preservation approach is data anonymization. However, IoT data provides missing data streams due to the varying device pool and preferences of individuals and unpredicted devices’ malfunctions of IoT. Minimization of missingess and information loss is very important for anonymizing of missing data streams. To achieve this, we introduce IncrementalPBM (Incremental Partitioning Based Marginalization) for anonymizing missig data streams. IncrementalPBM utilizes time based sliding window for missing data stream anonymization, and it aims to control the number of QIDs for anonymization while increasing the number of tuples for anonymization. Our experiment on real dataset showed IncrementalPBM is effective and efficient for anonymizing missing data streams compared to existing missing data stream anonymization algorithm. IncrementalPBM showed significant improvement; 5% to 9% less information loss, 4500 to 6000 more number of re-use anonymization while showing comparable clustering, suppression and runtime.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114656416","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982518
Riya Aggarwal, H. Ugail
We devise a numerical method for solving the Poisson’s equation using a convolutional neural network architecture, otherwise known as deep learning. The method we have employed here uses both feedforward neural systems and backpropagation to set up a framework for achieving the numerical solutions of the elliptic partial differential equations - more superficially the Poisson’s equation. Our deep learning framework has two substantial entities. The first part of the network enables to fulfill the necessary boundary conditions of the Poisson’s equation while the second part consisting of a feedforward neural system containing flexible parameters or weights gives rise to the solution. We have compared the solutions of the Poisson’s equation arising from our deep learning framework subject to various boundary conditions with the corresponding analytic solutions. As a result, we have found that our deep learning framework can obtain solutions which are accurate as well as efficient.
{"title":"On the Solution of Poisson’s Equation using Deep Learning","authors":"Riya Aggarwal, H. Ugail","doi":"10.1109/SKIMA47702.2019.8982518","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982518","url":null,"abstract":"We devise a numerical method for solving the Poisson’s equation using a convolutional neural network architecture, otherwise known as deep learning. The method we have employed here uses both feedforward neural systems and backpropagation to set up a framework for achieving the numerical solutions of the elliptic partial differential equations - more superficially the Poisson’s equation. Our deep learning framework has two substantial entities. The first part of the network enables to fulfill the necessary boundary conditions of the Poisson’s equation while the second part consisting of a feedforward neural system containing flexible parameters or weights gives rise to the solution. We have compared the solutions of the Poisson’s equation arising from our deep learning framework subject to various boundary conditions with the corresponding analytic solutions. As a result, we have found that our deep learning framework can obtain solutions which are accurate as well as efficient.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547328","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982508
H. Ugail, Maisun Alzorgani, A. M. Bukar, Humera Hussain, Christopher Burn, Thinzar Min Sein, S. Betmouni
The demand for pathology services are significantly increasing whilst the numbers of pathologists are significantly decreasing. In order to overcome these challenges, a growing interest in faster and efficient diagnostic methods such as computer-aided diagnosis (CAD) have been observed. An increase in the use of CAD systems in clinical settings has subsequently led to a growing interest in machine learning. In this paper, we show the use of machine learning algorithms in the prediction of tumour content in Fresh Frozen (FF) histological samples of head and neck. More specifically, we explore a pre-trained convolutional neural network (CNN), namely the AlexNet, to build two common machine learning classifiers. For the first classifier, the pre-trained AlexNet network is used to extract features from the activation layer and then Support Vector Machine (SVM) based classifier is trained by using these extracted features. In the second case, we replace the last three layers of the pre-trained AlexNet network and then fine tune these layers on the FF histological image samples. The results of our experiments are very promising. We have obtained percentage classification rates in the high 90s, and our results show there is little difference between SVM and transfer learning. Thus, the present study show that an AlexNet driven CNN with SVM and fine-tuned classifiers are a suitable choice for accurate discrimination between tumour and non-tumour histological samples from the head and neck.
{"title":"A Deep Learning Approach to Tumour Identification in Fresh Frozen Tissues","authors":"H. Ugail, Maisun Alzorgani, A. M. Bukar, Humera Hussain, Christopher Burn, Thinzar Min Sein, S. Betmouni","doi":"10.1109/SKIMA47702.2019.8982508","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982508","url":null,"abstract":"The demand for pathology services are significantly increasing whilst the numbers of pathologists are significantly decreasing. In order to overcome these challenges, a growing interest in faster and efficient diagnostic methods such as computer-aided diagnosis (CAD) have been observed. An increase in the use of CAD systems in clinical settings has subsequently led to a growing interest in machine learning. In this paper, we show the use of machine learning algorithms in the prediction of tumour content in Fresh Frozen (FF) histological samples of head and neck. More specifically, we explore a pre-trained convolutional neural network (CNN), namely the AlexNet, to build two common machine learning classifiers. For the first classifier, the pre-trained AlexNet network is used to extract features from the activation layer and then Support Vector Machine (SVM) based classifier is trained by using these extracted features. In the second case, we replace the last three layers of the pre-trained AlexNet network and then fine tune these layers on the FF histological image samples. The results of our experiments are very promising. We have obtained percentage classification rates in the high 90s, and our results show there is little difference between SVM and transfer learning. Thus, the present study show that an AlexNet driven CNN with SVM and fine-tuned classifiers are a suitable choice for accurate discrimination between tumour and non-tumour histological samples from the head and neck.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114933728","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 : 2019-08-01DOI: 10.1109/SKIMA47702.2019.8982509
Fahim Faisal, S. A. Hossain
Internet of Things (IoT) can help us better our lives in many ways by rendering real time information over the internet collected from a smart network of devices. In this paper, we have discussed about Remote Medical Diagnosis System (RMDS), which can come to aid for humans in many life-threatening situations. Often, people fall sick in locations where there are no hospitals or healthcare facility nearby, in such cases people sometimes even die due to lack of proper treatment and diagnosis. In rural areas of third-world countries, this problem is even more intense. For demonstration purpose, heartrate and body temperature of a person is determined and rendered over the internet. Health data is uploaded in real-time and can be viewed through a web browser. The aim of RMDS is to remotely provide health information of a patient to a healthcare professional in life-threatening situations. It can also be used for remote patient monitoring of regular patients of a doctor.
{"title":"IoT Based Remote Medical Diagnosis System Using NodeMCU","authors":"Fahim Faisal, S. A. Hossain","doi":"10.1109/SKIMA47702.2019.8982509","DOIUrl":"https://doi.org/10.1109/SKIMA47702.2019.8982509","url":null,"abstract":"Internet of Things (IoT) can help us better our lives in many ways by rendering real time information over the internet collected from a smart network of devices. In this paper, we have discussed about Remote Medical Diagnosis System (RMDS), which can come to aid for humans in many life-threatening situations. Often, people fall sick in locations where there are no hospitals or healthcare facility nearby, in such cases people sometimes even die due to lack of proper treatment and diagnosis. In rural areas of third-world countries, this problem is even more intense. For demonstration purpose, heartrate and body temperature of a person is determined and rendered over the internet. Health data is uploaded in real-time and can be viewed through a web browser. The aim of RMDS is to remotely provide health information of a patient to a healthcare professional in life-threatening situations. It can also be used for remote patient monitoring of regular patients of a doctor.","PeriodicalId":245523,"journal":{"name":"2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127034632","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：