Pub Date : 2020-02-01DOI: 10.1109/AECT47998.2020.9194214
A. T. Kiyani, A. Lasebae, Kamran Ali, Masood Ur-Rehman
Online banking is a substantial part of daily routine of large enterprise businesses and individual users for making transactions. However, security in online banking is a major dilemma owing to the vulnerable authentication schemes. Online banking employs conventional methods of Username and Passwords for authenticating the user. However, these techniques only verify the passwords and not the end user who requests the services for which only legitimate person is privileged to use. Using these vulnerabilities of online banking, intruders tend to masquerade legitimate user for unauthorized access to the system. This paper presents three-factor authentication scheme, which includes username/password, familiar random images and fingerprint data of user in order to make user-authentication more secure. Subsequently, Match on Card technique is proposed to ensure the confidentiality and integrity of biometric data of user since the reference feature set of user once store in credit card would not be permitted to move out and matching is performed on the credit card itself. In addition, the concept of familiar random images is used in order to enhance the security, as humans are believed to have remarkable visual remembering capability in comparison to words. The results show that the incorporation of three-factor authentication in online banking application resists the intruder to illicitly use banking services of any authorized user. The proposed biometric online banking system tends to assist in lessening the cybercrime rate of online banking and tends to escalate the user confidence in using banking services online.
{"title":"Secure Online Banking With Biometrics","authors":"A. T. Kiyani, A. Lasebae, Kamran Ali, Masood Ur-Rehman","doi":"10.1109/AECT47998.2020.9194214","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194214","url":null,"abstract":"Online banking is a substantial part of daily routine of large enterprise businesses and individual users for making transactions. However, security in online banking is a major dilemma owing to the vulnerable authentication schemes. Online banking employs conventional methods of Username and Passwords for authenticating the user. However, these techniques only verify the passwords and not the end user who requests the services for which only legitimate person is privileged to use. Using these vulnerabilities of online banking, intruders tend to masquerade legitimate user for unauthorized access to the system. This paper presents three-factor authentication scheme, which includes username/password, familiar random images and fingerprint data of user in order to make user-authentication more secure. Subsequently, Match on Card technique is proposed to ensure the confidentiality and integrity of biometric data of user since the reference feature set of user once store in credit card would not be permitted to move out and matching is performed on the credit card itself. In addition, the concept of familiar random images is used in order to enhance the security, as humans are believed to have remarkable visual remembering capability in comparison to words. The results show that the incorporation of three-factor authentication in online banking application resists the intruder to illicitly use banking services of any authorized user. The proposed biometric online banking system tends to assist in lessening the cybercrime rate of online banking and tends to escalate the user confidence in using banking services online.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129782544","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194217
Arbab Mansoor Ahmad, N. Minallah, N. Ahmed, A. Ahmad, Nouman Fazal
Vegetation is one of the most important part of an ecosystem. It is responsible for providing oxygen and gets in carbon dioxide, hence providing a suitable place for the human beings to live. The information about this vegetation is very critical. Using remote sensing, this information can be taken and gathered and later on used for different purposes. This paper aims to classify vegetation into different types and categories. Three machine learning algorithms i.e. K-means, Support Vector Machine (SVM) and Artificial Neural Networks (ANN) have been used because of their being the most popular and well known algorithms of the current time to classify vegetation. K-means being unsupervised classifier is used to compare it to two supervised classifiers i.e. SVM and ANN. Non-vegetation including buildings, roads, rivers etc. are also classified into their respective categories. This classification can be useful in many ways. They can be used by government agencies and authorities to get information about the yield of a specific crop e.g. tobacco, maize etc. This information could be very useful for gathering statistics of the crop and its location on map. These locations can be used for extracting the crops and for future planning regarding it. The information about buildings and roads can help in town planning for future.
{"title":"Remote Sensing Based Vegetation Classification Using Machine Learning Algorithms","authors":"Arbab Mansoor Ahmad, N. Minallah, N. Ahmed, A. Ahmad, Nouman Fazal","doi":"10.1109/AECT47998.2020.9194217","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194217","url":null,"abstract":"Vegetation is one of the most important part of an ecosystem. It is responsible for providing oxygen and gets in carbon dioxide, hence providing a suitable place for the human beings to live. The information about this vegetation is very critical. Using remote sensing, this information can be taken and gathered and later on used for different purposes. This paper aims to classify vegetation into different types and categories. Three machine learning algorithms i.e. K-means, Support Vector Machine (SVM) and Artificial Neural Networks (ANN) have been used because of their being the most popular and well known algorithms of the current time to classify vegetation. K-means being unsupervised classifier is used to compare it to two supervised classifiers i.e. SVM and ANN. Non-vegetation including buildings, roads, rivers etc. are also classified into their respective categories. This classification can be useful in many ways. They can be used by government agencies and authorities to get information about the yield of a specific crop e.g. tobacco, maize etc. This information could be very useful for gathering statistics of the crop and its location on map. These locations can be used for extracting the crops and for future planning regarding it. The information about buildings and roads can help in town planning for future.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131486473","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194208
Sharqa Hameed, Sakeena Javaid, Sheeraz Ahmed, N. Javaid
Nowadays, there exists strong need to enable the Intelligent Vehicle (IV) communication for applications such as safety messaging, traffic monitoring and many other internet access purposes. In this work, we have introduced an Intelligent Vehicle Trust Points (IVTPs) sharing mechanism between vehicle to vehicle, vehicle to infrastructure and vehicle to roadside units. Existing models have already embeded Blockchain (BC), which is valuable for many purposes like security in different data transmission circumstances. However, our proposed scheme uses this BC feature along with IVTPs to ensure the trustworthiness in the communication environment. Performance of our proposed system is evaluated on the basis of IVs’ processing time, which are totally based on IVTPs. Our proposed system is efficient as compared to existing one which handles less number of vehicles at intersection point where IVTPs are shared between moving vehicles in a scalable architecture.
{"title":"Sharing Mechanism of Intelligent Vehicles Trust Points based on Blockchain for Vehicular Networks","authors":"Sharqa Hameed, Sakeena Javaid, Sheeraz Ahmed, N. Javaid","doi":"10.1109/AECT47998.2020.9194208","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194208","url":null,"abstract":"Nowadays, there exists strong need to enable the Intelligent Vehicle (IV) communication for applications such as safety messaging, traffic monitoring and many other internet access purposes. In this work, we have introduced an Intelligent Vehicle Trust Points (IVTPs) sharing mechanism between vehicle to vehicle, vehicle to infrastructure and vehicle to roadside units. Existing models have already embeded Blockchain (BC), which is valuable for many purposes like security in different data transmission circumstances. However, our proposed scheme uses this BC feature along with IVTPs to ensure the trustworthiness in the communication environment. Performance of our proposed system is evaluated on the basis of IVs’ processing time, which are totally based on IVTPs. Our proposed system is efficient as compared to existing one which handles less number of vehicles at intersection point where IVTPs are shared between moving vehicles in a scalable architecture.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116114147","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194167
K. Handono, Indarzah Masbatim Putra, Ikhsan Shobari, Ismet Isnaini, K. Kurnianto
A risk analysis and smart detection of the ultrasonic scanner for inservice inspection on Research Reactor has been conducted. The hardware ultrasonic scanner has been installed and tested. This paper consists of the risk analysis design and the smart acquisition system. Risk assessment of tool installation and operation has been carried out as part of the system. The results indicate moderate and low risk, which means the tool can be operated. The results of the test in the reactor tank that the ultrasonic scanner system can work well and safely for inservice inspection.
{"title":"Smart Detection and Acquisition Design Of Ultrasonic Scanner For Inservice Inspection On Research Reactor","authors":"K. Handono, Indarzah Masbatim Putra, Ikhsan Shobari, Ismet Isnaini, K. Kurnianto","doi":"10.1109/AECT47998.2020.9194167","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194167","url":null,"abstract":"A risk analysis and smart detection of the ultrasonic scanner for inservice inspection on Research Reactor has been conducted. The hardware ultrasonic scanner has been installed and tested. This paper consists of the risk analysis design and the smart acquisition system. Risk assessment of tool installation and operation has been carried out as part of the system. The results indicate moderate and low risk, which means the tool can be operated. The results of the test in the reactor tank that the ultrasonic scanner system can work well and safely for inservice inspection.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122276065","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194194
Fatma Anwar, Omneya Attallah, Nagia M. Ghanem, M. Ismail
Breast cancer (BC) is a common health problem of major significance, as it is the most widely kind of cancer among women which leads to morbidity and mortality. Pathological diagnosis is considered as the golden standard of BC detection. However, the investigation of histopathology images is a challenging task. Automatic diagnosis of BC could lower the death rate by constructing a computer aided diagnosis (CAD) system capable of accurately diagnosing BC and reducing the time consumed by pathologists during examinations. This paper presents a CAD system to classify BC to benign and malignant. The proposed CAD method consists of 4 stages; image pre-processing, feature extraction and fusion, feature reduction, and classification. The CAD is based on fusion features extracted with ResNet Deep Convolution Neural Network (DCNN) with features of wavelets packet decomposition (WPD) and histograms of oriented gradient (HOG). Next, the feature data were reduced by utilizing principle component analysis (PCA). Finally, the reduced features are used to train different individual classifiers. Results show that the highest accuracy of 97.1% is achieved. The results were compared with recent related CAD systems. The comparison showed that the proposed CAD system is capable of accurately classifying BC to benign and malignant compared to other work. Thus, it can be used to help medical experiments in investigation procedures.
{"title":"Automatic Breast Cancer Classification from Histopathological Images","authors":"Fatma Anwar, Omneya Attallah, Nagia M. Ghanem, M. Ismail","doi":"10.1109/AECT47998.2020.9194194","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194194","url":null,"abstract":"Breast cancer (BC) is a common health problem of major significance, as it is the most widely kind of cancer among women which leads to morbidity and mortality. Pathological diagnosis is considered as the golden standard of BC detection. However, the investigation of histopathology images is a challenging task. Automatic diagnosis of BC could lower the death rate by constructing a computer aided diagnosis (CAD) system capable of accurately diagnosing BC and reducing the time consumed by pathologists during examinations. This paper presents a CAD system to classify BC to benign and malignant. The proposed CAD method consists of 4 stages; image pre-processing, feature extraction and fusion, feature reduction, and classification. The CAD is based on fusion features extracted with ResNet Deep Convolution Neural Network (DCNN) with features of wavelets packet decomposition (WPD) and histograms of oriented gradient (HOG). Next, the feature data were reduced by utilizing principle component analysis (PCA). Finally, the reduced features are used to train different individual classifiers. Results show that the highest accuracy of 97.1% is achieved. The results were compared with recent related CAD systems. The comparison showed that the proposed CAD system is capable of accurately classifying BC to benign and malignant compared to other work. Thus, it can be used to help medical experiments in investigation procedures.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125971149","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194187
Salahuddin Shaikh, Liu Changan, Maaz Rasheed Malik
In recently, all the developers, programmer and software engineers, they are working specially on software component and software testing to compete the software technology in the world. For this competition, they are using different kind of sources to analysis the software reliability and importance. Nowadays Data mining is one of source, which is used in software for overcome the problem of software fault which occur during the software test and its analysis. This kind of problem leads software deformity prophecy in software. In this research paper, we are also trying to overcome the software deformity prophecy problem with the help of our proposed solution called ONER rule attribute. We have used REPOSITORY datasets models, these datasets models are defected and non-defected datasets models. Our analysis class of interest is defected models. In our research, we have analyzed the efficiency of our proposed solution methods. The experiments results showed that using of ONER with discretize, have improved the efficiency of correctly classified instances in all. Using percentage split and training datasets with ONER discretize rule attribute have improved correctly classified in all datasets models. The analysis of positive accuracy f-measure is also increased in percentage split during the use of ONER with discretize but in some datasets models, the training data and cross validation is better with use of ONER rule attribute. The area under curve (ROC) in both scenarios using ONER rule attribute and discretize with ONER rule attribute is almost same or equal with each other.
{"title":"Attribute Rule performance in Data Mining for Software Deformity Prophecy Datasets Models","authors":"Salahuddin Shaikh, Liu Changan, Maaz Rasheed Malik","doi":"10.1109/AECT47998.2020.9194187","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194187","url":null,"abstract":"In recently, all the developers, programmer and software engineers, they are working specially on software component and software testing to compete the software technology in the world. For this competition, they are using different kind of sources to analysis the software reliability and importance. Nowadays Data mining is one of source, which is used in software for overcome the problem of software fault which occur during the software test and its analysis. This kind of problem leads software deformity prophecy in software. In this research paper, we are also trying to overcome the software deformity prophecy problem with the help of our proposed solution called ONER rule attribute. We have used REPOSITORY datasets models, these datasets models are defected and non-defected datasets models. Our analysis class of interest is defected models. In our research, we have analyzed the efficiency of our proposed solution methods. The experiments results showed that using of ONER with discretize, have improved the efficiency of correctly classified instances in all. Using percentage split and training datasets with ONER discretize rule attribute have improved correctly classified in all datasets models. The analysis of positive accuracy f-measure is also increased in percentage split during the use of ONER with discretize but in some datasets models, the training data and cross validation is better with use of ONER rule attribute. The area under curve (ROC) in both scenarios using ONER rule attribute and discretize with ONER rule attribute is almost same or equal with each other.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125447294","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194224
Mahwish Amjad, Hira Zahid, S. Zafar, Tariq Mahmood
Rapid increase of network devices have brought several complexities in today’s network data. Deep learning algorithms provides better solution for analyzing complex network data. Several deep learning algorithms have been proposed by researchers for identifying either known or unknown intrusions present in network traffic. But, in real time, incoming network traffic might encounter with known or unknown intrusions. Presence of unknown intrusions in network traffic arises a need to bring a framework that can identify both known and unknown network traffic intrusions. This paper is an attempt to bring a novel deep learning framework that can identify both known or unknown attacks with maximum 82% accuracy. Also, the particular category of known attack will be revealed via proposed framework. Proposed framework is a novel integration of two well known deep learning algorithms autoencoder and LSTM that brings an effective intrusion detection system. We believe that deployment of proposed framework in real time network will bring improvement in the security of future internet.
{"title":"A Novel Deep Learning Framework for Intrusion Detection System","authors":"Mahwish Amjad, Hira Zahid, S. Zafar, Tariq Mahmood","doi":"10.1109/AECT47998.2020.9194224","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194224","url":null,"abstract":"Rapid increase of network devices have brought several complexities in today’s network data. Deep learning algorithms provides better solution for analyzing complex network data. Several deep learning algorithms have been proposed by researchers for identifying either known or unknown intrusions present in network traffic. But, in real time, incoming network traffic might encounter with known or unknown intrusions. Presence of unknown intrusions in network traffic arises a need to bring a framework that can identify both known and unknown network traffic intrusions. This paper is an attempt to bring a novel deep learning framework that can identify both known or unknown attacks with maximum 82% accuracy. Also, the particular category of known attack will be revealed via proposed framework. Proposed framework is a novel integration of two well known deep learning algorithms autoencoder and LSTM that brings an effective intrusion detection system. We believe that deployment of proposed framework in real time network will bring improvement in the security of future internet.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126609954","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194155
Arwa Alzammam, H. Binsalleeh, Basil AsSadhan, K. Kyriakopoulos, S. Lambotharan
Malware is considered as one of the main actors in cyber attacks. The number of unique malware samples is constantly on the rise; however, the ratio of benign software still greatly outnumbers malware samples. In machine learning, such datasets are known as imbalanced, where the majority class label greatly dominates over others. In this paper, we present a comparative analysis and evaluation of some of the proposed techniques in the literature in order to address the problem of classifying imbalanced multi-class malware datasets. More specifically, we use Convolutional Neural Network (CNN) as a classification algorithm to study the effect of imbalanced datasets on deep learning approaches. These experiments are conducted on three publicly available imbalanced datasets. Our performance analysis demonstrates that methods such as cost sensitive learning, oversampling and cross validation have positive effects on the model classification performance, albeit in varying degrees. Meanwhile others like using pre-trained models require more special parameter settings. However, best practices may change in accordance with the problem domain.
{"title":"Comparative Analysis on Imbalanced Multi-class Classification for Malware Samples using CNN","authors":"Arwa Alzammam, H. Binsalleeh, Basil AsSadhan, K. Kyriakopoulos, S. Lambotharan","doi":"10.1109/AECT47998.2020.9194155","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194155","url":null,"abstract":"Malware is considered as one of the main actors in cyber attacks. The number of unique malware samples is constantly on the rise; however, the ratio of benign software still greatly outnumbers malware samples. In machine learning, such datasets are known as imbalanced, where the majority class label greatly dominates over others. In this paper, we present a comparative analysis and evaluation of some of the proposed techniques in the literature in order to address the problem of classifying imbalanced multi-class malware datasets. More specifically, we use Convolutional Neural Network (CNN) as a classification algorithm to study the effect of imbalanced datasets on deep learning approaches. These experiments are conducted on three publicly available imbalanced datasets. Our performance analysis demonstrates that methods such as cost sensitive learning, oversampling and cross validation have positive effects on the model classification performance, albeit in varying degrees. Meanwhile others like using pre-trained models require more special parameter settings. However, best practices may change in accordance with the problem domain.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130527726","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 : 2020-02-01DOI: 10.1109/AECT47998.2020.9194154
A. Ayman, Omneya Attalah, H. Shaban
Recognizing daily human activity using machine learning techniques is of great interest to many researchers working in the field of human health monitoring. Recently, wearable sensors have been used extensively for human activity recognition (HAR) for their great ability for capturing human actions during his daily life. Wearable wrist sensors have the advantage of being easily and comfortably worn. Extracting multimodal data from such sensors could enhance recognition rates leading to a healthier life style. Machine learning (ML) techniques have exciting capabilities, and can be used to facilitate HAR process. In this paper, a new daily HAR system is proposed for accurately recognizing daily human activity based on multimodal data from a wearable IMU wrist sensor. Two publically available datasets are employed to examine its effectiveness. The results indicate that the proposed HAR system is competitive to other recent related HAR approaches. This proves that the proposed HAR system is robust and, can be used for health monitoring applications.
{"title":"Smart System for Recognizing Daily Human Activities Based on Wrist IMU Sensors","authors":"A. Ayman, Omneya Attalah, H. Shaban","doi":"10.1109/AECT47998.2020.9194154","DOIUrl":"https://doi.org/10.1109/AECT47998.2020.9194154","url":null,"abstract":"Recognizing daily human activity using machine learning techniques is of great interest to many researchers working in the field of human health monitoring. Recently, wearable sensors have been used extensively for human activity recognition (HAR) for their great ability for capturing human actions during his daily life. Wearable wrist sensors have the advantage of being easily and comfortably worn. Extracting multimodal data from such sensors could enhance recognition rates leading to a healthier life style. Machine learning (ML) techniques have exciting capabilities, and can be used to facilitate HAR process. In this paper, a new daily HAR system is proposed for accurately recognizing daily human activity based on multimodal data from a wearable IMU wrist sensor. Two publically available datasets are employed to examine its effectiveness. The results indicate that the proposed HAR system is competitive to other recent related HAR approaches. This proves that the proposed HAR system is robust and, can be used for health monitoring applications.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132504948","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 : 2020-02-01DOI: 10.1109/aect47998.2020.9194190
M. A. Raheem, M. El-Melegy
In this paper, we present a fully automated road assessment methods using cellular based internet of things platforms. The vibration data recorded from accelerometer sensor attached to a moving car is transmitted over the internet via cellular network to the monitoring server. At the monitoring server side, the vibration signal is used to calculate the international roughness index as a measure of the road surface roughness and its values are visualized on the road map for different road segments. Also, the possibility of using smartphone with built in accelerometer is investigated and its performance is compared with other proposed platforms.
{"title":"Drive-By Road Condition Assessment Using Internet of Things Technology","authors":"M. A. Raheem, M. El-Melegy","doi":"10.1109/aect47998.2020.9194190","DOIUrl":"https://doi.org/10.1109/aect47998.2020.9194190","url":null,"abstract":"In this paper, we present a fully automated road assessment methods using cellular based internet of things platforms. The vibration data recorded from accelerometer sensor attached to a moving car is transmitted over the internet via cellular network to the monitoring server. At the monitoring server side, the vibration signal is used to calculate the international roughness index as a measure of the road surface roughness and its values are visualized on the road map for different road segments. Also, the possibility of using smartphone with built in accelerometer is investigated and its performance is compared with other proposed platforms.","PeriodicalId":331415,"journal":{"name":"2019 International Conference on Advances in the Emerging Computing Technologies (AECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124573301","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：