Pub Date : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096788
Waad Y. Bin Saleem, Hanan Ali, Nouf AlSalloom
Nowadays the internet of things (IoT) is one of the most arising obvious technologies which plays an important role in healthcare systems. Healthcare systems including stored Electronic healthcare records (EHR), which are vulnerable to intentional and unintentional security threats. therefore; the need for strong EHR security protection is essential. In this paper we display and analyze some of the proposed IoT-based security solutions for healthcare, and also outline a new platform that secures and enhances the process of accessing and managing EHR in hospitals databases.
{"title":"A Framework for Securing EHR Management in the Era of Internet of Things","authors":"Waad Y. Bin Saleem, Hanan Ali, Nouf AlSalloom","doi":"10.1109/ICCAIS48893.2020.9096788","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096788","url":null,"abstract":"Nowadays the internet of things (IoT) is one of the most arising obvious technologies which plays an important role in healthcare systems. Healthcare systems including stored Electronic healthcare records (EHR), which are vulnerable to intentional and unintentional security threats. therefore; the need for strong EHR security protection is essential. In this paper we display and analyze some of the proposed IoT-based security solutions for healthcare, and also outline a new platform that secures and enhances the process of accessing and managing EHR in hospitals databases.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126311961","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096740
Gerges M. Salama, Sarah A. Taha
Cognitive radio is development of wireless communication and mobile computing. Spectrum is a limited source. The licensed spectrum is proposed to be used only by the spectrum owners. Cognitive radio is a new view of the recycle licensed spectrum in an unlicensed manner. The main condition of the cognitive radio network is sensing the spectrum hole. Cognitive radio can be detect unused spectrum. It shares this with no interference to the licensed spectrum. It can be a sense signals. It makes viable communication in the middle of multiple users through co-operation in a self-organized manner. The energy detector method is unseen signal detector because it reject the data of the signal.In this paper, has implemented Simulink Energy Detection of spectrum sensing cognitive radio in a MATLAB Simulink to Exploit spectrum holes and avoid damaging interference to licensed spectrum and unlicensed spectrum. The hidden primary user problem will happened because fading or shadowing. Ithappens when cognitive radio could not be detected by primer users because of its location. Cooperative sensing spectrum sensing is the best-proposed method to solve the hidden problem.
{"title":"Cooperative Spectrum Sensing and Hard Decision Rules for Cognitive Radio Network","authors":"Gerges M. Salama, Sarah A. Taha","doi":"10.1109/ICCAIS48893.2020.9096740","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096740","url":null,"abstract":"Cognitive radio is development of wireless communication and mobile computing. Spectrum is a limited source. The licensed spectrum is proposed to be used only by the spectrum owners. Cognitive radio is a new view of the recycle licensed spectrum in an unlicensed manner. The main condition of the cognitive radio network is sensing the spectrum hole. Cognitive radio can be detect unused spectrum. It shares this with no interference to the licensed spectrum. It can be a sense signals. It makes viable communication in the middle of multiple users through co-operation in a self-organized manner. The energy detector method is unseen signal detector because it reject the data of the signal.In this paper, has implemented Simulink Energy Detection of spectrum sensing cognitive radio in a MATLAB Simulink to Exploit spectrum holes and avoid damaging interference to licensed spectrum and unlicensed spectrum. The hidden primary user problem will happened because fading or shadowing. Ithappens when cognitive radio could not be detected by primer users because of its location. Cooperative sensing spectrum sensing is the best-proposed method to solve the hidden problem.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125623229","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096739
Mostafa A. Elhosseini
Soft computing algorithms are population-based, probabilistic, that have the same common controlling parameters such as population size, number of generations, elite size. In addition to the regular control parameters, the different algorithms need specific control parameters for their algorithm. A good tuning of different algorithm parameters is an integral factor that affects the efficacy of the algorithm. The inappropriate tuning of the algorithm parameters increases the computational effort or adheres to local limits. Teaching Learning-based Optimization (TLBO) algorithms are algorithms that need no algorithm-specific parameter. Jaya is a kind of TLBO algorithm but has only one-step and is user-friendly. The main aims of this paper are to present the Jaya algorithm and its application to the most prominent engineering problem. The validation and monitoring of existing technology in the presented Jaya include case studies, ranging from the recent CEC 2016 workbench to the common engineering challenges for the gear train, welded beam, three-bar truss system. The results achieved reflect the significance of the algorithms in comparison with most popular modern algorithms.
{"title":"Performance Validation of Jaya Algorithm to The Most Well-known Testbench Problem","authors":"Mostafa A. Elhosseini","doi":"10.1109/ICCAIS48893.2020.9096739","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096739","url":null,"abstract":"Soft computing algorithms are population-based, probabilistic, that have the same common controlling parameters such as population size, number of generations, elite size. In addition to the regular control parameters, the different algorithms need specific control parameters for their algorithm. A good tuning of different algorithm parameters is an integral factor that affects the efficacy of the algorithm. The inappropriate tuning of the algorithm parameters increases the computational effort or adheres to local limits. Teaching Learning-based Optimization (TLBO) algorithms are algorithms that need no algorithm-specific parameter. Jaya is a kind of TLBO algorithm but has only one-step and is user-friendly. The main aims of this paper are to present the Jaya algorithm and its application to the most prominent engineering problem. The validation and monitoring of existing technology in the presented Jaya include case studies, ranging from the recent CEC 2016 workbench to the common engineering challenges for the gear train, welded beam, three-bar truss system. The results achieved reflect the significance of the algorithms in comparison with most popular modern algorithms.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122587385","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096811
N. Alnaghaimshi, A. Alhazmi, S. A. Alqanwah, M. Aldablan, M. A. Almossa
Autism Spectrum Disorder (ASD) is one of the most-prevalent neurodevelopmental disorder. ASD is defined by impaired social communication along with unusual restricted and repetitive behaviours. However, each child diagnosed with ASD presents with a unique range of behavioural, communication and social skills problems. As result, the burden on parents who are raising a child with ASD is too high, especially in countries that suffer from a lack or shortages of skilled specialists, supportive services and special centres that deal with such conditions. Extensive research has proven the efficiency of technologies as support tools for ASD children and their families. Since technologies and telehealth services have recently been introduced in KSA, we proposed with this application (app) to provide an innovative opportunity for assisting and supporting children with ASD and their parents in our context. The proposed application aims to extend and enhance care delivery in numerous ways: it will provide parents with a handy tool to help to detect signs of autism in their child and give them updated resources for education and training on how to care for their ASD child. Moreover, this application aims to improve access to specialists for parents and help to establish a space in which to share information and experiences among parents of children with ASD. Moreover, the app employs an innovative feature to simplify ASD data collection through conducting short and simple surveys and conduct interviews via text messaging.
{"title":"Autismworld: an Arabic Application for Autism Spectrum Disorder","authors":"N. Alnaghaimshi, A. Alhazmi, S. A. Alqanwah, M. Aldablan, M. A. Almossa","doi":"10.1109/ICCAIS48893.2020.9096811","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096811","url":null,"abstract":"Autism Spectrum Disorder (ASD) is one of the most-prevalent neurodevelopmental disorder. ASD is defined by impaired social communication along with unusual restricted and repetitive behaviours. However, each child diagnosed with ASD presents with a unique range of behavioural, communication and social skills problems. As result, the burden on parents who are raising a child with ASD is too high, especially in countries that suffer from a lack or shortages of skilled specialists, supportive services and special centres that deal with such conditions. Extensive research has proven the efficiency of technologies as support tools for ASD children and their families. Since technologies and telehealth services have recently been introduced in KSA, we proposed with this application (app) to provide an innovative opportunity for assisting and supporting children with ASD and their parents in our context. The proposed application aims to extend and enhance care delivery in numerous ways: it will provide parents with a handy tool to help to detect signs of autism in their child and give them updated resources for education and training on how to care for their ASD child. Moreover, this application aims to improve access to specialists for parents and help to establish a space in which to share information and experiences among parents of children with ASD. Moreover, the app employs an innovative feature to simplify ASD data collection through conducting short and simple surveys and conduct interviews via text messaging.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131277043","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096718
A. Gazdar, M. Kefi
A little attention has been made to Recommender Systems (RS) for TV services broadcast through satellites due to the one-way data flow nature of the linear satellite TV. Nevertheless, the emergence of new Internet enabled TV Set-Top-Box (STB) with an embedded open source operating system has partially overcame this shortage and has encouraged implementing new kinds of applications for those STBs. In this context, we discuss in this paper the feasability of a Recommender System for the linear satellite based TV which suggests a dynamic list of services that may interest the TV viewer based on his profile (age, gender, etc) with regards to the ongoing audience rate of users having the same profile as him.
{"title":"A Recommender System for Linear Satellite TV: Is It Possible?","authors":"A. Gazdar, M. Kefi","doi":"10.1109/ICCAIS48893.2020.9096718","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096718","url":null,"abstract":"A little attention has been made to Recommender Systems (RS) for TV services broadcast through satellites due to the one-way data flow nature of the linear satellite TV. Nevertheless, the emergence of new Internet enabled TV Set-Top-Box (STB) with an embedded open source operating system has partially overcame this shortage and has encouraged implementing new kinds of applications for those STBs. In this context, we discuss in this paper the feasability of a Recommender System for the linear satellite based TV which suggests a dynamic list of services that may interest the TV viewer based on his profile (age, gender, etc) with regards to the ongoing audience rate of users having the same profile as him.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114342811","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096837
Amani Abuladel, O. Bamasag
The Internet of Things (IoT) is an innovative interconnected framework where all objects can interact with each other and with other people. It enhances the quality of life, business growth and efficiency in multiple domains. However, the heterogeneity of the "Things" that can be associated in such conditions makes interoperability among them a difficult issue. Moreover, the data exchanged between IoT system components are normally not protected. This leads to users losing their privacy, hence, making it difficult to share and reuse data for purposes other than what they were originally set up for. In this paper, we address these challenges in the context of IoT applications considering user’s data and location privacy as not to be shared between these ‘Things’. We first describe two use case scenarios of IoT users in healthcare applications. The first scenario describes an attacker capturing the data traveling from/to the server. The second scenario describes the case of a server acting as a malicious party (i.e., an attacker). The two scenarios highlight data and location privacy issues of IoT users. Based on the use-case scenarios, the paper presents a generic framework for IoT data and location privacy, including a description of entities and interactions among them. The paper then analyzes potential privacy threats in this framework, in order to identify a set of general privacy requirements, with an emphasis on data and location privacy. These requirements will provide guidance to future solutions for secure IoT communication and/or risk assessment.
{"title":"Data and Location Privacy Issues in IoT Applications","authors":"Amani Abuladel, O. Bamasag","doi":"10.1109/ICCAIS48893.2020.9096837","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096837","url":null,"abstract":"The Internet of Things (IoT) is an innovative interconnected framework where all objects can interact with each other and with other people. It enhances the quality of life, business growth and efficiency in multiple domains. However, the heterogeneity of the \"Things\" that can be associated in such conditions makes interoperability among them a difficult issue. Moreover, the data exchanged between IoT system components are normally not protected. This leads to users losing their privacy, hence, making it difficult to share and reuse data for purposes other than what they were originally set up for. In this paper, we address these challenges in the context of IoT applications considering user’s data and location privacy as not to be shared between these ‘Things’. We first describe two use case scenarios of IoT users in healthcare applications. The first scenario describes an attacker capturing the data traveling from/to the server. The second scenario describes the case of a server acting as a malicious party (i.e., an attacker). The two scenarios highlight data and location privacy issues of IoT users. Based on the use-case scenarios, the paper presents a generic framework for IoT data and location privacy, including a description of entities and interactions among them. The paper then analyzes potential privacy threats in this framework, in order to identify a set of general privacy requirements, with an emphasis on data and location privacy. These requirements will provide guidance to future solutions for secure IoT communication and/or risk assessment.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114772489","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096877
Abdulaziz Alhubaishy, Abdulmajeed Aljuhani
In cloud computing, service providers and service consumers often pursue conflicting benefits. The task-scheduling problem in particular requires the consideration of all characteristics affecting the scheduling process that are related to the two parties involved. The literature proposes that scheduling tasks and resource allocation problems can be structured and mathematically represented by adopting Multi-Criteria Decision-Making (MCDM) methods. This paper introduces a model to effectively prioritize tasks in a cloud environment based on consumer preferences and pre-defined criteria. The model adopts the Best-Worst Method (BWM) as a light MCDM method for structuring task-scheduling problems, accommodating consumer preferences, and providing reliable and scientific results for prioritizing tasks in the cloud. Furthermore, the model gives consumers the flexibility to change their preferences and offers a dynamic way to deal with the task-scheduling problem. The paper also provides a step-by-step example to guide consumers on the benefits of the proposed model.
{"title":"The Best-Worst Method for Resource Allocation and Task Scheduling in Cloud Computing","authors":"Abdulaziz Alhubaishy, Abdulmajeed Aljuhani","doi":"10.1109/ICCAIS48893.2020.9096877","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096877","url":null,"abstract":"In cloud computing, service providers and service consumers often pursue conflicting benefits. The task-scheduling problem in particular requires the consideration of all characteristics affecting the scheduling process that are related to the two parties involved. The literature proposes that scheduling tasks and resource allocation problems can be structured and mathematically represented by adopting Multi-Criteria Decision-Making (MCDM) methods. This paper introduces a model to effectively prioritize tasks in a cloud environment based on consumer preferences and pre-defined criteria. The model adopts the Best-Worst Method (BWM) as a light MCDM method for structuring task-scheduling problems, accommodating consumer preferences, and providing reliable and scientific results for prioritizing tasks in the cloud. Furthermore, the model gives consumers the flexibility to change their preferences and offers a dynamic way to deal with the task-scheduling problem. The paper also provides a step-by-step example to guide consumers on the benefits of the proposed model.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114209143","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096743
Alla Abd El-Rady
E-learning systems become more popular than it has ever been. However the popularity of e-learning systems, they still suffer from some problems related to the completion rate of online courses and the learners’ failures. Nowadays, a lot of educational institutions are concentrating on how to solve those problems in order to improve the quality of learning process. This paper presents an ontological model based on machine learning techniques to predict learners coming performance using data produced by learners through their interaction with Learning Management System and Facebook groups. It also presents two different approaches to evaluate ontology model in terms of completeness and correctness.
{"title":"An Ontological Model to Predict Dropout Students Using Machine Learning Techniques","authors":"Alla Abd El-Rady","doi":"10.1109/ICCAIS48893.2020.9096743","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096743","url":null,"abstract":"E-learning systems become more popular than it has ever been. However the popularity of e-learning systems, they still suffer from some problems related to the completion rate of online courses and the learners’ failures. Nowadays, a lot of educational institutions are concentrating on how to solve those problems in order to improve the quality of learning process. This paper presents an ontological model based on machine learning techniques to predict learners coming performance using data produced by learners through their interaction with Learning Management System and Facebook groups. It also presents two different approaches to evaluate ontology model in terms of completeness and correctness.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356574","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096733
Najla Alzakari, Alanoud Bin Dris, Saad Al-Ahmadi
To accommodate the rapidly changing Internet requirements, Information-Centric Networking (ICN) was recently introduced as a promising architecture for the future Internet. One of the ICN primary features is ‘in-network caching’; due to its ability to minimize network traffic and respond faster to users’ requests. Therefore, various caching algorithms have been presented that aim to enhance the network performance using different measures, such as cache hit ratio and cache hit distance. Choosing a caching strategy is critical, and an adequate replacement strategy is also required to decide which content should be dropped. Thus, in this paper, we propose a content replacement scheme for ICN, called Randomized LFU that is implemented with respect to content popularity taking the time complexity into account. We use Abilene and Tree network topologies in our simulation models. The proposed replacement achieves encouraging results in terms of the cache hit ratio, inner hit, and hit distance and it outperforms FIFO, LRU, and Random replacement strategies.
{"title":"Randomized Least Frequently Used Cache Replacement Strategy for Named Data Networking","authors":"Najla Alzakari, Alanoud Bin Dris, Saad Al-Ahmadi","doi":"10.1109/ICCAIS48893.2020.9096733","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096733","url":null,"abstract":"To accommodate the rapidly changing Internet requirements, Information-Centric Networking (ICN) was recently introduced as a promising architecture for the future Internet. One of the ICN primary features is ‘in-network caching’; due to its ability to minimize network traffic and respond faster to users’ requests. Therefore, various caching algorithms have been presented that aim to enhance the network performance using different measures, such as cache hit ratio and cache hit distance. Choosing a caching strategy is critical, and an adequate replacement strategy is also required to decide which content should be dropped. Thus, in this paper, we propose a content replacement scheme for ICN, called Randomized LFU that is implemented with respect to content popularity taking the time complexity into account. We use Abilene and Tree network topologies in our simulation models. The proposed replacement achieves encouraging results in terms of the cache hit ratio, inner hit, and hit distance and it outperforms FIFO, LRU, and Random replacement strategies.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121040210","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 : 2020-03-01DOI: 10.1109/ICCAIS48893.2020.9096747
Shrooq A. Alsenan, Isra M. Al-Turaiki, Alaaeldin M. Hafez
The recent advances in Machine Learning tools and algorithms have influenced fields including drug discovery. Nowadays, research conducted via trial- and-error experiments have been replaced by computational approaches. This growth prompted an undeniable development in synthesizing chemical data to support chemoinformatics research. One of the widely used tools to model chemoinformatics problems is Quantitative Structure-Activity Relationships (QSAR). Previous QSAR models were dealing with small datasets and limited number of features. Current QSAR datasets suffer from the problem of high dimensionality, where the number of features exceeds the number of records. Over the years, the curse of high dimensionality posed a major shortcoming in QSAR classification models. Linear Principle Component Analysis is a popular feature extraction method used to reduce the high dimensioanlity of QSAR datasets. However, QSAR datasets are highly complex and require deep understanding of features representation. Autoencoder is a type of neural networks that is not fully explored in QSAR modeling for dimensionality reduction purposes. In this research, we investigate the impact of autoencoder on a high dimensional QSAR dataset. The autoencoder performance is compared with PCA on the over all accuracy measure. Our preliminary analysis demonstrated that the proposed technique outperforms PCA.
{"title":"Autoencoder-based Dimensionality Reduction for QSAR Modeling","authors":"Shrooq A. Alsenan, Isra M. Al-Turaiki, Alaaeldin M. Hafez","doi":"10.1109/ICCAIS48893.2020.9096747","DOIUrl":"https://doi.org/10.1109/ICCAIS48893.2020.9096747","url":null,"abstract":"The recent advances in Machine Learning tools and algorithms have influenced fields including drug discovery. Nowadays, research conducted via trial- and-error experiments have been replaced by computational approaches. This growth prompted an undeniable development in synthesizing chemical data to support chemoinformatics research. One of the widely used tools to model chemoinformatics problems is Quantitative Structure-Activity Relationships (QSAR). Previous QSAR models were dealing with small datasets and limited number of features. Current QSAR datasets suffer from the problem of high dimensionality, where the number of features exceeds the number of records. Over the years, the curse of high dimensionality posed a major shortcoming in QSAR classification models. Linear Principle Component Analysis is a popular feature extraction method used to reduce the high dimensioanlity of QSAR datasets. However, QSAR datasets are highly complex and require deep understanding of features representation. Autoencoder is a type of neural networks that is not fully explored in QSAR modeling for dimensionality reduction purposes. In this research, we investigate the impact of autoencoder on a high dimensional QSAR dataset. The autoencoder performance is compared with PCA on the over all accuracy measure. Our preliminary analysis demonstrated that the proposed technique outperforms PCA.","PeriodicalId":422184,"journal":{"name":"2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129333713","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：