BMC medical informatics and decision making, Jan 19, 2017
Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardio... more Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardiovascular health. Machine learning (ML) can enhance the prediction of outcomes through classification techniques that classify the data into predetermined categories. The aim of this study is to present an evaluation and comparison of how machine learning techniques can be applied on medical records of cardiorespiratory fitness and how the various techniques differ in terms of capabilities of predicting medical outcomes (e.g. mortality). We use data of 34,212 patients free of known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems Between 1991 and 2009 and had a complete 10-year follow-up. Seven machine learning classification techniques were evaluated: Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Naïve Bayesian Classifier (BC), Bayesian Network (BN), K-Nearest Nei...
Proceedings of the 30th Annual ACM Symposium on Applied Computing, 2015
ABSTRACT Today s enterprises demand a high degree of compliance in their business processes to me... more ABSTRACT Today s enterprises demand a high degree of compliance in their business processes to meet diverse regulations and legislations. Sev-eral industrial studies have shown that compliance management is a daunting task, and organizations are still struggling and spending billions of dollars annually to ensure and prove their compliance. Theoretically, design-time compliance checking could provide a preliminary assurance that corresponding running instances would be compliant to relevant laws and regulations; however, due to the existence of human and machine related errors and the absence of necessary contextual information during design-time, runtime com-pliance monitoring becomes a must. In this paper, we present a generic proactive runtime Business Process (BP) compliance mon-itoring framework:BP-MaaS, which incorporates a wide range of expressive high-level compliance patterns for the abstract specifi-cation of runtime constraints. Compliance monitoring is achieved by means of anti-patterns, a novel evaluation approach that is inde-pendent of any underlying technology and could be applied to the checking of compliance in the different phases of the BP lifecycle. As a proof-of-concept, complex event processing (CEP) technol-ogy is adopted as one of the possible realizations of the framework.
Abstract Data replication is a well-known strategy to achieve the availability, scalability and p... more Abstract Data replication is a well-known strategy to achieve the availability, scalability and performance improvement goals in the data management world. However, the cost of maintaining several database replicas always strongly consistent is very high. The CAP theorem shows that a shared-data system can choose at most two out of three properties: consistency, availability, and tolerance to partitions.
Abstract: The ability to efficiently find relevant subgraphs and paths in a large graph to a give... more Abstract: The ability to efficiently find relevant subgraphs and paths in a large graph to a given query is important in many applications including scientific data analysis, social networks, and business intelligence. Currently, there is little support and no efficient approaches for expressing and executing such queries. This paper proposes a data model and a query language to address this problem.
Abstract: We analyze the database research publications of four major core database technology co... more Abstract: We analyze the database research publications of four major core database technology conferences (SIGMOD, VLDB, ICDE, EDBT), two main theoretical database conferences (PODS, ICDT) and three database journals (TODS, VLDB Journal, TKDE) over a period of 10 years (2001-2010). Our analysis considers only regular papers as we do not include short papers, demo papers, posters, tutorials or panels into our statistics.
Abstract One of the main advantages of the cloud computing paradigm is that it simplifies the tim... more Abstract One of the main advantages of the cloud computing paradigm is that it simplifies the time-consuming processes of hardware provisioning, hardware purchasing and software deployment. Currently, we are witnessing a proliferation in the number of cloud-hosted applications with a tremendous increase in the scale of the data generated as well as being consumed by such applications. Cloud-hosted database systems powering these applications form a critical component in the software stack of these applications.
ABSTRACT Graphs are widely used for modeling complicated data such as social networks, bibliograp... more ABSTRACT Graphs are widely used for modeling complicated data such as social networks, bibliographical networks and knowledge bases. The growing sizes of graph databases motivate the crucial need for developing powerful and scalable graphbased query engines. We propose a SPARQL-like language, G-SPARQL, for querying attributed graphs.
Abstract. Nowadays, modern organizations build large repositories of process models to describe a... more Abstract. Nowadays, modern organizations build large repositories of process models to describe and document their daily business operations. One reason for the large number of process models is the need to adapt with differnt business contexts, ie process variants. Automated maintenance of the consistency between process variants is an important goal that saves the time and efforts of process modelers. We present a query-based approach to maintain consistency among process variants called BPModelMasher.
Page 1. Protection notice / Copyright notice Axel Polleres (Siemens AG) & Sherif Sakr (NICTA & UN... more Page 1. Protection notice / Copyright notice Axel Polleres (Siemens AG) & Sherif Sakr (NICTA & UNSW) Siemens AG 2012. Querying and Exchanging XML and RDF on the Web WWW'2012 Tutorial This tutorial presents partially joint work with: Nuno Lopes (DERI), Stefan Bischof (Siemens AG)… … and of course the whole W3C SPARQL WG http://polleres.net/WWW2012Tutorial/ Page 2.
BMC medical informatics and decision making, Jan 19, 2017
Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardio... more Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardiovascular health. Machine learning (ML) can enhance the prediction of outcomes through classification techniques that classify the data into predetermined categories. The aim of this study is to present an evaluation and comparison of how machine learning techniques can be applied on medical records of cardiorespiratory fitness and how the various techniques differ in terms of capabilities of predicting medical outcomes (e.g. mortality). We use data of 34,212 patients free of known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems Between 1991 and 2009 and had a complete 10-year follow-up. Seven machine learning classification techniques were evaluated: Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Naïve Bayesian Classifier (BC), Bayesian Network (BN), K-Nearest Nei...
Proceedings of the 30th Annual ACM Symposium on Applied Computing, 2015
ABSTRACT Today s enterprises demand a high degree of compliance in their business processes to me... more ABSTRACT Today s enterprises demand a high degree of compliance in their business processes to meet diverse regulations and legislations. Sev-eral industrial studies have shown that compliance management is a daunting task, and organizations are still struggling and spending billions of dollars annually to ensure and prove their compliance. Theoretically, design-time compliance checking could provide a preliminary assurance that corresponding running instances would be compliant to relevant laws and regulations; however, due to the existence of human and machine related errors and the absence of necessary contextual information during design-time, runtime com-pliance monitoring becomes a must. In this paper, we present a generic proactive runtime Business Process (BP) compliance mon-itoring framework:BP-MaaS, which incorporates a wide range of expressive high-level compliance patterns for the abstract specifi-cation of runtime constraints. Compliance monitoring is achieved by means of anti-patterns, a novel evaluation approach that is inde-pendent of any underlying technology and could be applied to the checking of compliance in the different phases of the BP lifecycle. As a proof-of-concept, complex event processing (CEP) technol-ogy is adopted as one of the possible realizations of the framework.
Abstract Data replication is a well-known strategy to achieve the availability, scalability and p... more Abstract Data replication is a well-known strategy to achieve the availability, scalability and performance improvement goals in the data management world. However, the cost of maintaining several database replicas always strongly consistent is very high. The CAP theorem shows that a shared-data system can choose at most two out of three properties: consistency, availability, and tolerance to partitions.
Abstract: The ability to efficiently find relevant subgraphs and paths in a large graph to a give... more Abstract: The ability to efficiently find relevant subgraphs and paths in a large graph to a given query is important in many applications including scientific data analysis, social networks, and business intelligence. Currently, there is little support and no efficient approaches for expressing and executing such queries. This paper proposes a data model and a query language to address this problem.
Abstract: We analyze the database research publications of four major core database technology co... more Abstract: We analyze the database research publications of four major core database technology conferences (SIGMOD, VLDB, ICDE, EDBT), two main theoretical database conferences (PODS, ICDT) and three database journals (TODS, VLDB Journal, TKDE) over a period of 10 years (2001-2010). Our analysis considers only regular papers as we do not include short papers, demo papers, posters, tutorials or panels into our statistics.
Abstract One of the main advantages of the cloud computing paradigm is that it simplifies the tim... more Abstract One of the main advantages of the cloud computing paradigm is that it simplifies the time-consuming processes of hardware provisioning, hardware purchasing and software deployment. Currently, we are witnessing a proliferation in the number of cloud-hosted applications with a tremendous increase in the scale of the data generated as well as being consumed by such applications. Cloud-hosted database systems powering these applications form a critical component in the software stack of these applications.
ABSTRACT Graphs are widely used for modeling complicated data such as social networks, bibliograp... more ABSTRACT Graphs are widely used for modeling complicated data such as social networks, bibliographical networks and knowledge bases. The growing sizes of graph databases motivate the crucial need for developing powerful and scalable graphbased query engines. We propose a SPARQL-like language, G-SPARQL, for querying attributed graphs.
Abstract. Nowadays, modern organizations build large repositories of process models to describe a... more Abstract. Nowadays, modern organizations build large repositories of process models to describe and document their daily business operations. One reason for the large number of process models is the need to adapt with differnt business contexts, ie process variants. Automated maintenance of the consistency between process variants is an important goal that saves the time and efforts of process modelers. We present a query-based approach to maintain consistency among process variants called BPModelMasher.
Page 1. Protection notice / Copyright notice Axel Polleres (Siemens AG) & Sherif Sakr (NICTA & UN... more Page 1. Protection notice / Copyright notice Axel Polleres (Siemens AG) & Sherif Sakr (NICTA & UNSW) Siemens AG 2012. Querying and Exchanging XML and RDF on the Web WWW'2012 Tutorial This tutorial presents partially joint work with: Nuno Lopes (DERI), Stefan Bischof (Siemens AG)… … and of course the whole W3C SPARQL WG http://polleres.net/WWW2012Tutorial/ Page 2.
Uploads
Papers by Sherif Sakr