Sarfraz Brohi | University of the West of England (original) (raw)
Papers by Sarfraz Brohi
Computer Communications, 2020
Road traffic accidents are one of the leading causes of deaths and injuries in the word resulting... more Road traffic accidents are one of the leading causes of deaths and injuries in the word resulting in the not only loss of precious human lives but also affect the economic resources. According to the World Health Organization (WHO), over 1.35 million people are killed, and over 50 million are injured due to road accidents throughout the world. Unfortunately, as compared to other developing countries with the same ratio of vehicle possession, in Saudi Arabia, the fatalities and injuries are much higher. Every year around 7000-9000 people die, and over 39000 serious injuries occur in road accidents. There is at least one accident happens every minute in Saudi Arabia. To decrease the road traffic accidents, fatalities, and injuries caused by them, the Saudi Ministry of Interior came up with new rules, regulations, and hefty fines. Also, they introduced a new traffic system called the SAHER system. Still, due to the static nature and other limitations of the system, the drivers found loopholes and ways to deceive the system to avoid the fines and not being caught by the system. The most common violation includes excess speed, abrupt deceleration, and distracted driving. In this paper, we propose a smart traffic surveillance system based on Unmanned Aerial Vehicle (UAV) using 5G technology. This traffic monitoring system covers the existing limitations of the SAHER system deployed in KSA. By overcoming the existing limitations and loopholes of the SAHER system, it is observed that the number of accidents and fatalities can be decreased. The projected results show that those violations when to overcome, the number of accidents per year falls to 299,317 leading to 4,868 deaths and 33,199 injuries for 1st year, and in the next five years the number of deaths and will be decreased to 3,745 and injuries to 16,600 based on the current data available. We aim the system will further reduce the number of accidents and fatalities and injuries caused by it.
Bookmarks Related papers MentionsView impact
IEEE 2018 Fourth International Conference on Advances in Computing, Communication & Automation (ICACCA), 2019
Credit card fraud detection is growing due to the increase and the popularity of online banking. ... more Credit card fraud detection is growing due to the increase and the popularity of online banking. The need to detect fraudulent within credit card has become as a serious problem among the online shoppers. The multi-layer perceptron (MLP) machine learning algorithm is used to identify the credit card fraud. We have used the various parameters of the MLP to compare the performance of MLP. The aim of this paper is to design a high performance model to detect the credit card fraud using deep learning techniques. We found that logistic and hyperbolic tangent activation function offer good performance in detecting the credit card fraud. The logistic activation function performs better when there are 10 nodes, the sensitivity is 82% and when there are 100 nodes, the sensitivity is 83% respectively in the 3 hidden layer model. However, hyperbolic tangent activation function performs better when there is 1000 nodes, the sensitivity is 82% in all the number (1, 2 and 3) of hidden layers. This study will give us a guidance on how to choose a best model to obtain optimum results with minimum cost in deep learning.
Bookmarks Related papers MentionsView impact
With the growing popularity of cloud computing, the reliability of cloud services has become a ke... more With the growing popularity of cloud computing, the reliability of cloud services has become a key concern of cloud service providers and users. Several researchers have studied the problem of cloud service reliability assurance. However, the complexity of the cloud service provisioning system and the deep dependency stack of its layered architecture make it challenging to evaluate the reliability of cloud services. In this paper, we propose a novel analytical model of cloud service provisioning systems reliability. Further, we provide a detailed methodology for evaluating cloud service reliability using reliability block diagrams and probabilistic methods. The proposed model can be used by cloud providers to assure the reliability of their cloud services. The results of a case study using simulated cloud computing infrastructure verify the effectiveness of the proposed model.
Bookmarks Related papers MentionsView impact
Journal of Engineering Science and Technology, 2020
The research in the domain of ransomware is rapidly emerging, and the application of machine lear... more The research in the domain of ransomware is rapidly emerging, and the application of machine learning algorithms in ransomware detection is one of the recent breakthroughs. In this research, we constructed an experimental platform using ransomware datasets to compare the performance of various machine learning algorithms such as Random Forest, Gradient Boosting Decision Tree (GBDT), Neural Network using Multilayer Perceptron as well as three types of Support Vector Machine (SVM) kernels in ransomware detection. Our experiment is based on a combination of different methodologies reported in the existing literature. We used complete executable files in our experiment, analyzed the opcodes and measures their frequencies. The objective of this research was to discover the algorithms that are highly suitable to develop models as well as systems for ransomware detection. Consequently, we identified that Random Forest, GBDT and SVM (Linear) have shown optimal results in detection of ransomware.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
In this research, we compared the accuracy of machine learning algorithms that could be used for ... more In this research, we compared the accuracy of machine learning algorithms that could be used for predictive analytics in higher education. The proposed experiment is based on a combination of classic machine learning algorithms such as Naive Bayes and Random Forest with various ensemble methods such as Stochastic, Linear Discriminant Analysis (LDA), Tree model (C5.0), Bagged CART (treebag) and K Nearest Neighbors (KNN). We applied traditional classification methods to classify the students' performance and to determine the independent variables that offer the highest accuracy. Our results depict that the data with the 11 features using random forest generated the best accuracy value of 0.7333. However, we revised the experiment with ensemble algorithms to reduce the variance (bagging), bias (boosting) and to improve the prediction accuracy (stacking). Consequently, the bagging random forest outperformed other methods with the accuracy value of 0.7959.
Bookmarks Related papers MentionsView impact
Big data is an emerging area of research and its prospective applications in smart cities are ext... more Big data is an emerging area of research and its prospective applications in smart cities are extensively recognized. In this study, we provide a breadth-first review of the domain “Big Data in Smart Cities” by applying the formal research method of systematic mapping. We investigated the primary sources of publication, research growth, maturity level of the research area, prominent research themes, type of analytics applied, and the areas of smart cities where big data research is produced. Consequently, we identified that empirical research in the domain has been progressing since 2013. The IEEE Access journal and IEEE Smart Cities Conference are the leading sources of literature containing 10.34% and 13.88% of the publications, respectively. The current state of the research is semi-matured where research type of 46.15% of the publications is solution and experience, and contribution type of 60% of the publications is architecture, platform, and framework. Prescriptive is least whereas predictive is the most applied type of analytics in smart cities as it has been stated in 43.08% of the publications. Overall, 33.85%, 21.54%, 13.85%, 12.31%, 7.69%, 6.15%, and 4.61% of the research produced in the domain focused on smart transportation, smart environment, smart governance, smart healthcare, smart energy, smart education, and smart safety, respectively. Besides the requirement for producing validation and evaluation research in the areas of smart transportation and smart environment, there is a need for more research efforts in the areas of smart healthcare, smart governance, smart safety, smart education, and smart energy. Furthermore, the potential of prescriptive analytics in smart cities is also an area of research that needs to be explored.
Bookmarks Related papers MentionsView impact
Financed by the British Council Institutional Links program this Smart Mobility Cities project ha... more Financed by the British Council Institutional Links program this Smart Mobility Cities project has opened a fascinating window on a journey of discovery linking Bristol and Kuala Lumpur. This journey was in part directed towards the realization of Smart Mobility solutions to the socio-economic and environmental challenges of global urbanization. Beyond this, the journey was also concerned to strengthen research and innovation partnerships between the UK and the emerging knowledge economy of Malaysia, enabling UK social scientists to collaborate on challenging global issues with international researchers and vice versa. This Smart Mobility Cities project report presents innovative, creative and yet fully practical solutions for these societal challenges. Solutions that explore a range of opportunities, which include those arising from new urban governance requirements, and which are in-line with visions for sustainable urban mobility. These Smart Mobility solutions have arisen from intensive co-design and co-creation engagement with a diversity of stakeholders. Research co-production has linked the principal university partners of the University of the West of England (UWE), Bristol, and Taylor’s University, Kuala Lumpur, together with the Malaysia Institute of Transport (MITRANS), Universiti Teknologi Mara, and the University Sains Malaysia (USM) in intensive engagement with stakeholder interests in both UK and Malaysia over a two-year period. Foundations of a long-term global research partnership have also been established through the process of active research and innovation linking research institutes, planners and social partners in addressing the challenges of urban transformation. The dynamics of social and technological innovation has driven and defined this emerging partnership, aiding the specification of transition pathways according to an architectural frame of integrated and participatory urban governance. Indeed, common purpose binds this Bristol-Kuala Lumpur partnership, as global problems are drivers of change to invest cities with common solutions designed and delivered by cities.
Cities are the developers and implementers of innovative solutions to these common problems, and in doing so explore the potentials for common solutions that ensure the realization of global policy objectives towards the United Nations Sustainable Development Goals. Kuala Lumpur, Malaysian and ASEAN experience and expertise offers insights and understandings for Smart Mobility cities that resonate in Bristol and Europe, and vice versa. Global transformations in urban economies, the opportunities arising from emerging new technologies allied with social innovation, and the requirements for governance delivering resilient and sustainable urban development represent some of the “grand challenges” of our time. This Smart Mobility Cities project report offers some innovative potential solutions for Kuala Lumpur as a contribution to drive, define and deliver the necessary transformational change agenda for sustainable global cities. The Smart Mobility Cities project team hope these suggested solutions will be of interest to policymakers and practitioners in the field. The emerging global partnership of universities that bridges Bristol and Kuala Lumpur aims to continue this work.
Bookmarks Related papers MentionsView impact
Increasing number of privately owned vehicles are depicting Malaysians preferred mode of mobility... more Increasing number of privately owned vehicles are depicting Malaysians preferred mode of mobility and lack of interest in the public transport system. In most developing countries such as Malaysia, motorized vehicles are the major contributors to air pollution in urban zones. Air pollution is a silent killer as it infiltrates the vital organs, leading to serious diseases and death. This research critically analyses the emissions of air pollutants such as CO, NO 2 , SO 2 , hydrocarbon, and PM from various sources in Malaysia with emphasis mainly on the emission of pollutants from motor vehicles. This research also discusses the public transport initiatives undertaken by the government of Malaysia such as enhancing the bus and rail system, transforming Malaysia's taxi system, managing travel demand and enhancing the integration of urban public transport system. Furthermore, considering the smart cities initiatives, this research identified that weather, safety, security and inappropriate infrastructure are major barriers in Malaysia's move towards the implementation of smart and eco-friendly mobility practices such as cycling, carpooling and car sharing.
Bookmarks Related papers MentionsView impact
Auspiciously, big data analytics had made it possible to generate value from immense amounts of r... more Auspiciously, big data analytics had made it possible to generate value from immense amounts of raw data. Organizations are able to seek incredible insights which assist them in effective decision making and providing quality of service by establishing innovative strategies to recognize, examine and address the customers' preferences. However, organizations are reluctant to adopt big data solutions due to several barriers such as data storage and transfer, scalability, data quality, data complexity, timeliness, security, privacy, trust, data ownership, and transparency. Despite the discussion on big data opportunities, in this paper, we present the findings of our in-depth review process that was focused on identifying as well as analyzing the transient and permanent barriers for adopting big data. Although, the transient barriers for big data can be eliminated in the near future with the advent of innovative technical contributions, however, it is challenging to eliminate the permanent barriers enduringly, though their impact could be recurrently reduced with the efficient and effective use of technology, standards, policies, and procedures.
Bookmarks Related papers MentionsView impact
Healthcare sector is information critical industry that deals with human lives. Transforming from... more Healthcare sector is information critical industry that deals with human lives. Transforming from traditional paper-based to Electronic Health Records (EHRs) was not efficient enough since EHRs require resources, integration, maintenance and high cost implementation. Cloud computing paradigm offers flexible, cost effective, collaborative, multi-tenant infrastructure which assists in transforming electronic healthcare to smart healthcare that consists on the use of latest technologies such as smart mobiles, smart cards, robots, sensors and Tele-health systems via internet on pay-per-use basis for best medical practices. Cloud computing reduces the cost of EHRs in terms of ownership and IT maintenance, also it offers sharing, integration and management of EHRs as well as tracking patients and diseases more efficiently and effectively. This review paper represents the significance and opportunities for implementing cloud computing in healthcare sector.
Bookmarks Related papers MentionsView impact
This study provides an in-depth review of Big Data Technology (BDT) advantages, implementations, ... more This study provides an in-depth review of Big Data Technology (BDT) advantages, implementations, and challenges in the education sector. BDT plays an essential role in optimizing education intelligence by facilitating institutions, management, educators, and learners improved quality of education, enhanced learning experience, predictive teaching and assessment strategy, effective decision-making and better market analysis. Moreover, BDTs are used to analyze, detect and predict learners' behaviors, risk failures and results to improve their learning outcomes and to ensure that the academic programmers undertaken are of high-quality standards. This study identified that some universities and governments had implemented BDTs for transferring traditional education to digital smart one. Despite BDT significant offerings for education still, there are several challenges regarding its full implementation such as security, privacy, ethics, lack of skilled professionals, data processing, storage, and interoperability.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
The journey of data from the state of being valueless to valuable has been possible due to powerf... more The journey of data from the state of being valueless to valuable has been possible due to powerful analytics tools and processing platforms. Organizations have realized the potential of data, and they are looking far ahead from the traditional relational databases to unstructured as well as semi-structured data generated from heterogeneous sources. With the numerous devices and sensors surrounding our ecosystem, IoT has become a reality, and with the use of data science, IoT analytics has become a tremendous opportunity to perceive incredible insights. However, despite the various benefits of IoT analytics, organizations are apprehensive with the dark side of IoT such as security and privacy concerns. In this research, we discuss the opportunities and concerns of IoT analytics. Moreover, we propose a generic data science methodology for IoT data analytics named as Plan, Collect and Analytics for Internet-of-Things (PCA-IoT). The proposed methodology could be applied in IoT scenarios to perform data analytics for effective and efficient decision-making.
Bookmarks Related papers MentionsView impact
Big data is an emerging area of research and its prospective applications in smart cities are ext... more Big data is an emerging area of research and its prospective applications in smart cities are extensively recognized. In this study, we provide a breadth-first review of the domain "Big Data in Smart Cities" by applying the formal research method of systematic mapping. We investigated the primary sources of publication, research growth, maturity level of the research area, prominent research themes, type of analytics applied, and the areas of smart cities where big data research is produced. Consequently, we identified that empirical research in the domain has been progressing since 2013. The IEEE Access journal and IEEE Smart Cities Conference are the leading sources of literature containing 10.34% and 13.88% of the publications, respectively. The current state of the research is semi-matured where research type of 46.15% of the publications is solution and experience, and contribution type of 60% of the publications is architecture, platform, and framework. Prescriptive is least whereas predictive is the most applied type of analytics in smart cities as it has been stated in 43.08% of the publications. Overall, 33.85%, 21.54%, 13.85%, 12.31%, 7.69%, 6.15%, and 4.61% of the research produced in the domain focused on smart transportation, smart environment, smart governance, smart healthcare, smart energy, smart education, and smart safety, respectively. Besides the requirement for producing validation and evaluation research in the areas of smart transportation and smart environment, there is a need for more research efforts in the areas of smart healthcare, smart governance, smart safety, smart education, and smart energy. Furthermore, the potential of prescriptive analytics in smart cities is also an area of research that needs to be explored.
Bookmarks Related papers MentionsView impact
Cloud computing is rapidly evolving due to its efficient characteristics such as cost... more Cloud computing is rapidly evolving due to its efficient characteristics such as cost-effectiveness, availability and elasticity. Healthcare organizations and consumers lose control when they outsource their sensitive data and computing resources to a third party Cloud Service Provider (CSP), which may raise security and privacy concerns related to data loss and misuse appealing threats. Lack of consumers’ knowledge about their data storage location may lead to violating rules and regulations of Health Insurance Portability and Accountability Act (HIPAA) that cancost them huge penalty. Fear of data breach by internal or external hackers may decrease consumers’ trust in adopting cloud computing and benefiting from its promising features. We designed a Healthcare Trusted Cloud Computing (HTCC) framework that maintains security, privacy and considers HIPAA regulations. HTCC framework deploys Trusted Computing Group (TCG) technologies such as Trusted Platform Module (TPM), Trusted Software Stack (TSS), virtual Trusted Platform Module (vTPM), Trusted Network Connect (TNC) and Self Encrypting Drives (SEDs). We emphasize on using strong multi-factor authentication access control mechanisms and strict security controls, as well as encryption for data at storage, in-transit and while process. We contributed in customizing a cloud Service Level Agreement (SLA) by considering healthcare requirements. HTCC was evaluated by comparing with previous researchers’ work and conducting survey from experts. Results were satisfactory and showed acceptance of the framework. We aim that our proposed framework will assist in optimizing trust on cloud computing to be adopted in healthcare sector.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Cloud computing offers significant features such as resource pooling, scalability, on-demand self... more Cloud computing offers significant features such as resource pooling, scalability, on-demand self service, availability, and reliability to organizations to improve their quality of services. For example by using cloud computing services in healthcare it is possible to reach large population of people in isolated geographical areas which will assist in saving their lives in critical situations. It enables the use of latest technologies through its various service delivery and deployment models via the internet on pay-per-use billing pattern. However, cloud computing has dark side when it comes to security and privacy considerations. Critical industries such as healthcare and banking are reluctant to trust cloud computing due to the fear of losing their sensitive data, as it resides on the cloud with no knowledge of data location and lack of transparency of Cloud Service Providers (CSPs) mechanisms used to secure their data and applications which have created a barrier against adopting this agile computing paradigm. This paper addresses cloud computing security concerns that must be considered in order to adopt cloud services in information critical industries.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
Smartphones have changed the world from a primitive to a high-tech standpoint. However, there hav... more Smartphones have changed the world from a primitive to a high-tech standpoint. However, there have been many incidents where third parties have used confidential data of the users without their consent. Thus, it causes people to be paranoid and distrustful of their smartphones, never knowing which application threatens to expose them. In this paper, we have conducted an in-depth review of the significance of smartphones in human life, and we have discussed the methods used by various authorities to collect and exploit users' data for enigmatic benefits. Moreover, we surveyed the smartphone users to identify the vulnerabilities leading to privacy violation, and to examine their knowledge about the protection mechanisms. We determined that Technology and Human are the two major vulnerabilities that are exploited to invade users' privacy. It is the necessity of the moment for the researchers and developers to formulate solutions that could be used to educate and protect smartphone users from potential threats and exploitation of data.
Bookmarks Related papers MentionsView impact
IEEE 2018 Fourth International Conference on Advances in Computing, Communication & Automation (ICACCA), 2019
Machine Learning is an emerging field which has created a significant positive and undesirable im... more Machine Learning is an emerging field which has created a significant positive and undesirable impact too many industries. This technology has been well received and widely used for precise decision making as its ability to process, analyze and visualize any mass amount of data. This paper will introduce the machine learning application, moving on to describe its use in healthcare and medical, people mobility, political campaign and banking. The discussion further continues to outline its impact from social, political and ethical aspects, Machine learning technology is discussed based on the use of machine learning is various activities and the effect that the technology perceived from the ethical, social and political point of view.
Bookmarks Related papers MentionsView impact
IEEE, 2018
NotPetya, when released in 2017, was believed to be ransomware. NotPetya injects malicious codes ... more NotPetya, when released in 2017, was believed to be ransomware. NotPetya injects malicious codes in the computer and then attempts to gain administrator access. Following that, it infects other computers in the network. NotPetya uses the EternalBlue Server Message Block (SMB) exploit to conduct the attacks. The hard drives get encrypted, and when the computer is booted, the ransom note is displayed. NotPetya does not provide enough information for a decryption key to be produced, making it a malware. Businesses across industries have been affected without having an opportunity for system recovery. While definite solutions are lacking, vaccines exist, where, the presence of a local file, blocks the NotPetya execution. Activating the vaccine can be tedious and cumbersome for average computer users. Hence, our solution is intended to educate them in an interactive manner. Users will be more susceptible towards the vaccination while learning about security habits that need to be practiced. From this, average computer users can walk away with the knowledge that can protect them from future attacks. Note: (Full paper is available on request)
Bookmarks Related papers MentionsView impact
A multi-tenant Cloud Computing Infrastructure (CCI) consists of several Virtual Machines (VMs) ru... more A multi-tenant Cloud Computing Infrastructure (CCI) consists of several Virtual Machines (VMs) running on same physical platform by using virtualization techniques. The VMs are monitored and managed by kernel based software i.e. Virtual Machine Monitor (VMM) or hypervisor which is main component of Virtualized Cloud Computing Infrastructure (VCCI). Due to software based vulnerabilities, VMMs are compromised to security attacks that may take place from inside or outside attackers. In order to formulate a secure VCCI, VMM must be protected by implementing strong security tools and techniques such as Encryption and Key Management (EKM), Access Control Mechanisms (ACMs), Intrusion Detection Tools (IDTs), Virtual Trusted Platform Module (vTPM), Virtual Firewalls (VFs) and Trusted Virtual Domains (TVDs). In this research paper we describe the techniques of virtualizing a CCI, types of attacks on VCCI, vulnerabilities of VMMs and we critically describe the significance of security tools and techniques for securing a VCCI.
Bookmarks Related papers MentionsView impact
Computer Communications, 2020
Road traffic accidents are one of the leading causes of deaths and injuries in the word resulting... more Road traffic accidents are one of the leading causes of deaths and injuries in the word resulting in the not only loss of precious human lives but also affect the economic resources. According to the World Health Organization (WHO), over 1.35 million people are killed, and over 50 million are injured due to road accidents throughout the world. Unfortunately, as compared to other developing countries with the same ratio of vehicle possession, in Saudi Arabia, the fatalities and injuries are much higher. Every year around 7000-9000 people die, and over 39000 serious injuries occur in road accidents. There is at least one accident happens every minute in Saudi Arabia. To decrease the road traffic accidents, fatalities, and injuries caused by them, the Saudi Ministry of Interior came up with new rules, regulations, and hefty fines. Also, they introduced a new traffic system called the SAHER system. Still, due to the static nature and other limitations of the system, the drivers found loopholes and ways to deceive the system to avoid the fines and not being caught by the system. The most common violation includes excess speed, abrupt deceleration, and distracted driving. In this paper, we propose a smart traffic surveillance system based on Unmanned Aerial Vehicle (UAV) using 5G technology. This traffic monitoring system covers the existing limitations of the SAHER system deployed in KSA. By overcoming the existing limitations and loopholes of the SAHER system, it is observed that the number of accidents and fatalities can be decreased. The projected results show that those violations when to overcome, the number of accidents per year falls to 299,317 leading to 4,868 deaths and 33,199 injuries for 1st year, and in the next five years the number of deaths and will be decreased to 3,745 and injuries to 16,600 based on the current data available. We aim the system will further reduce the number of accidents and fatalities and injuries caused by it.
Bookmarks Related papers MentionsView impact
IEEE 2018 Fourth International Conference on Advances in Computing, Communication & Automation (ICACCA), 2019
Credit card fraud detection is growing due to the increase and the popularity of online banking. ... more Credit card fraud detection is growing due to the increase and the popularity of online banking. The need to detect fraudulent within credit card has become as a serious problem among the online shoppers. The multi-layer perceptron (MLP) machine learning algorithm is used to identify the credit card fraud. We have used the various parameters of the MLP to compare the performance of MLP. The aim of this paper is to design a high performance model to detect the credit card fraud using deep learning techniques. We found that logistic and hyperbolic tangent activation function offer good performance in detecting the credit card fraud. The logistic activation function performs better when there are 10 nodes, the sensitivity is 82% and when there are 100 nodes, the sensitivity is 83% respectively in the 3 hidden layer model. However, hyperbolic tangent activation function performs better when there is 1000 nodes, the sensitivity is 82% in all the number (1, 2 and 3) of hidden layers. This study will give us a guidance on how to choose a best model to obtain optimum results with minimum cost in deep learning.
Bookmarks Related papers MentionsView impact
With the growing popularity of cloud computing, the reliability of cloud services has become a ke... more With the growing popularity of cloud computing, the reliability of cloud services has become a key concern of cloud service providers and users. Several researchers have studied the problem of cloud service reliability assurance. However, the complexity of the cloud service provisioning system and the deep dependency stack of its layered architecture make it challenging to evaluate the reliability of cloud services. In this paper, we propose a novel analytical model of cloud service provisioning systems reliability. Further, we provide a detailed methodology for evaluating cloud service reliability using reliability block diagrams and probabilistic methods. The proposed model can be used by cloud providers to assure the reliability of their cloud services. The results of a case study using simulated cloud computing infrastructure verify the effectiveness of the proposed model.
Bookmarks Related papers MentionsView impact
Journal of Engineering Science and Technology, 2020
The research in the domain of ransomware is rapidly emerging, and the application of machine lear... more The research in the domain of ransomware is rapidly emerging, and the application of machine learning algorithms in ransomware detection is one of the recent breakthroughs. In this research, we constructed an experimental platform using ransomware datasets to compare the performance of various machine learning algorithms such as Random Forest, Gradient Boosting Decision Tree (GBDT), Neural Network using Multilayer Perceptron as well as three types of Support Vector Machine (SVM) kernels in ransomware detection. Our experiment is based on a combination of different methodologies reported in the existing literature. We used complete executable files in our experiment, analyzed the opcodes and measures their frequencies. The objective of this research was to discover the algorithms that are highly suitable to develop models as well as systems for ransomware detection. Consequently, we identified that Random Forest, GBDT and SVM (Linear) have shown optimal results in detection of ransomware.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
In this research, we compared the accuracy of machine learning algorithms that could be used for ... more In this research, we compared the accuracy of machine learning algorithms that could be used for predictive analytics in higher education. The proposed experiment is based on a combination of classic machine learning algorithms such as Naive Bayes and Random Forest with various ensemble methods such as Stochastic, Linear Discriminant Analysis (LDA), Tree model (C5.0), Bagged CART (treebag) and K Nearest Neighbors (KNN). We applied traditional classification methods to classify the students' performance and to determine the independent variables that offer the highest accuracy. Our results depict that the data with the 11 features using random forest generated the best accuracy value of 0.7333. However, we revised the experiment with ensemble algorithms to reduce the variance (bagging), bias (boosting) and to improve the prediction accuracy (stacking). Consequently, the bagging random forest outperformed other methods with the accuracy value of 0.7959.
Bookmarks Related papers MentionsView impact
Big data is an emerging area of research and its prospective applications in smart cities are ext... more Big data is an emerging area of research and its prospective applications in smart cities are extensively recognized. In this study, we provide a breadth-first review of the domain “Big Data in Smart Cities” by applying the formal research method of systematic mapping. We investigated the primary sources of publication, research growth, maturity level of the research area, prominent research themes, type of analytics applied, and the areas of smart cities where big data research is produced. Consequently, we identified that empirical research in the domain has been progressing since 2013. The IEEE Access journal and IEEE Smart Cities Conference are the leading sources of literature containing 10.34% and 13.88% of the publications, respectively. The current state of the research is semi-matured where research type of 46.15% of the publications is solution and experience, and contribution type of 60% of the publications is architecture, platform, and framework. Prescriptive is least whereas predictive is the most applied type of analytics in smart cities as it has been stated in 43.08% of the publications. Overall, 33.85%, 21.54%, 13.85%, 12.31%, 7.69%, 6.15%, and 4.61% of the research produced in the domain focused on smart transportation, smart environment, smart governance, smart healthcare, smart energy, smart education, and smart safety, respectively. Besides the requirement for producing validation and evaluation research in the areas of smart transportation and smart environment, there is a need for more research efforts in the areas of smart healthcare, smart governance, smart safety, smart education, and smart energy. Furthermore, the potential of prescriptive analytics in smart cities is also an area of research that needs to be explored.
Bookmarks Related papers MentionsView impact
Financed by the British Council Institutional Links program this Smart Mobility Cities project ha... more Financed by the British Council Institutional Links program this Smart Mobility Cities project has opened a fascinating window on a journey of discovery linking Bristol and Kuala Lumpur. This journey was in part directed towards the realization of Smart Mobility solutions to the socio-economic and environmental challenges of global urbanization. Beyond this, the journey was also concerned to strengthen research and innovation partnerships between the UK and the emerging knowledge economy of Malaysia, enabling UK social scientists to collaborate on challenging global issues with international researchers and vice versa. This Smart Mobility Cities project report presents innovative, creative and yet fully practical solutions for these societal challenges. Solutions that explore a range of opportunities, which include those arising from new urban governance requirements, and which are in-line with visions for sustainable urban mobility. These Smart Mobility solutions have arisen from intensive co-design and co-creation engagement with a diversity of stakeholders. Research co-production has linked the principal university partners of the University of the West of England (UWE), Bristol, and Taylor’s University, Kuala Lumpur, together with the Malaysia Institute of Transport (MITRANS), Universiti Teknologi Mara, and the University Sains Malaysia (USM) in intensive engagement with stakeholder interests in both UK and Malaysia over a two-year period. Foundations of a long-term global research partnership have also been established through the process of active research and innovation linking research institutes, planners and social partners in addressing the challenges of urban transformation. The dynamics of social and technological innovation has driven and defined this emerging partnership, aiding the specification of transition pathways according to an architectural frame of integrated and participatory urban governance. Indeed, common purpose binds this Bristol-Kuala Lumpur partnership, as global problems are drivers of change to invest cities with common solutions designed and delivered by cities.
Cities are the developers and implementers of innovative solutions to these common problems, and in doing so explore the potentials for common solutions that ensure the realization of global policy objectives towards the United Nations Sustainable Development Goals. Kuala Lumpur, Malaysian and ASEAN experience and expertise offers insights and understandings for Smart Mobility cities that resonate in Bristol and Europe, and vice versa. Global transformations in urban economies, the opportunities arising from emerging new technologies allied with social innovation, and the requirements for governance delivering resilient and sustainable urban development represent some of the “grand challenges” of our time. This Smart Mobility Cities project report offers some innovative potential solutions for Kuala Lumpur as a contribution to drive, define and deliver the necessary transformational change agenda for sustainable global cities. The Smart Mobility Cities project team hope these suggested solutions will be of interest to policymakers and practitioners in the field. The emerging global partnership of universities that bridges Bristol and Kuala Lumpur aims to continue this work.
Bookmarks Related papers MentionsView impact
Increasing number of privately owned vehicles are depicting Malaysians preferred mode of mobility... more Increasing number of privately owned vehicles are depicting Malaysians preferred mode of mobility and lack of interest in the public transport system. In most developing countries such as Malaysia, motorized vehicles are the major contributors to air pollution in urban zones. Air pollution is a silent killer as it infiltrates the vital organs, leading to serious diseases and death. This research critically analyses the emissions of air pollutants such as CO, NO 2 , SO 2 , hydrocarbon, and PM from various sources in Malaysia with emphasis mainly on the emission of pollutants from motor vehicles. This research also discusses the public transport initiatives undertaken by the government of Malaysia such as enhancing the bus and rail system, transforming Malaysia's taxi system, managing travel demand and enhancing the integration of urban public transport system. Furthermore, considering the smart cities initiatives, this research identified that weather, safety, security and inappropriate infrastructure are major barriers in Malaysia's move towards the implementation of smart and eco-friendly mobility practices such as cycling, carpooling and car sharing.
Bookmarks Related papers MentionsView impact
Auspiciously, big data analytics had made it possible to generate value from immense amounts of r... more Auspiciously, big data analytics had made it possible to generate value from immense amounts of raw data. Organizations are able to seek incredible insights which assist them in effective decision making and providing quality of service by establishing innovative strategies to recognize, examine and address the customers' preferences. However, organizations are reluctant to adopt big data solutions due to several barriers such as data storage and transfer, scalability, data quality, data complexity, timeliness, security, privacy, trust, data ownership, and transparency. Despite the discussion on big data opportunities, in this paper, we present the findings of our in-depth review process that was focused on identifying as well as analyzing the transient and permanent barriers for adopting big data. Although, the transient barriers for big data can be eliminated in the near future with the advent of innovative technical contributions, however, it is challenging to eliminate the permanent barriers enduringly, though their impact could be recurrently reduced with the efficient and effective use of technology, standards, policies, and procedures.
Bookmarks Related papers MentionsView impact
Healthcare sector is information critical industry that deals with human lives. Transforming from... more Healthcare sector is information critical industry that deals with human lives. Transforming from traditional paper-based to Electronic Health Records (EHRs) was not efficient enough since EHRs require resources, integration, maintenance and high cost implementation. Cloud computing paradigm offers flexible, cost effective, collaborative, multi-tenant infrastructure which assists in transforming electronic healthcare to smart healthcare that consists on the use of latest technologies such as smart mobiles, smart cards, robots, sensors and Tele-health systems via internet on pay-per-use basis for best medical practices. Cloud computing reduces the cost of EHRs in terms of ownership and IT maintenance, also it offers sharing, integration and management of EHRs as well as tracking patients and diseases more efficiently and effectively. This review paper represents the significance and opportunities for implementing cloud computing in healthcare sector.
Bookmarks Related papers MentionsView impact
This study provides an in-depth review of Big Data Technology (BDT) advantages, implementations, ... more This study provides an in-depth review of Big Data Technology (BDT) advantages, implementations, and challenges in the education sector. BDT plays an essential role in optimizing education intelligence by facilitating institutions, management, educators, and learners improved quality of education, enhanced learning experience, predictive teaching and assessment strategy, effective decision-making and better market analysis. Moreover, BDTs are used to analyze, detect and predict learners' behaviors, risk failures and results to improve their learning outcomes and to ensure that the academic programmers undertaken are of high-quality standards. This study identified that some universities and governments had implemented BDTs for transferring traditional education to digital smart one. Despite BDT significant offerings for education still, there are several challenges regarding its full implementation such as security, privacy, ethics, lack of skilled professionals, data processing, storage, and interoperability.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
The journey of data from the state of being valueless to valuable has been possible due to powerf... more The journey of data from the state of being valueless to valuable has been possible due to powerful analytics tools and processing platforms. Organizations have realized the potential of data, and they are looking far ahead from the traditional relational databases to unstructured as well as semi-structured data generated from heterogeneous sources. With the numerous devices and sensors surrounding our ecosystem, IoT has become a reality, and with the use of data science, IoT analytics has become a tremendous opportunity to perceive incredible insights. However, despite the various benefits of IoT analytics, organizations are apprehensive with the dark side of IoT such as security and privacy concerns. In this research, we discuss the opportunities and concerns of IoT analytics. Moreover, we propose a generic data science methodology for IoT data analytics named as Plan, Collect and Analytics for Internet-of-Things (PCA-IoT). The proposed methodology could be applied in IoT scenarios to perform data analytics for effective and efficient decision-making.
Bookmarks Related papers MentionsView impact
Big data is an emerging area of research and its prospective applications in smart cities are ext... more Big data is an emerging area of research and its prospective applications in smart cities are extensively recognized. In this study, we provide a breadth-first review of the domain "Big Data in Smart Cities" by applying the formal research method of systematic mapping. We investigated the primary sources of publication, research growth, maturity level of the research area, prominent research themes, type of analytics applied, and the areas of smart cities where big data research is produced. Consequently, we identified that empirical research in the domain has been progressing since 2013. The IEEE Access journal and IEEE Smart Cities Conference are the leading sources of literature containing 10.34% and 13.88% of the publications, respectively. The current state of the research is semi-matured where research type of 46.15% of the publications is solution and experience, and contribution type of 60% of the publications is architecture, platform, and framework. Prescriptive is least whereas predictive is the most applied type of analytics in smart cities as it has been stated in 43.08% of the publications. Overall, 33.85%, 21.54%, 13.85%, 12.31%, 7.69%, 6.15%, and 4.61% of the research produced in the domain focused on smart transportation, smart environment, smart governance, smart healthcare, smart energy, smart education, and smart safety, respectively. Besides the requirement for producing validation and evaluation research in the areas of smart transportation and smart environment, there is a need for more research efforts in the areas of smart healthcare, smart governance, smart safety, smart education, and smart energy. Furthermore, the potential of prescriptive analytics in smart cities is also an area of research that needs to be explored.
Bookmarks Related papers MentionsView impact
Cloud computing is rapidly evolving due to its efficient characteristics such as cost... more Cloud computing is rapidly evolving due to its efficient characteristics such as cost-effectiveness, availability and elasticity. Healthcare organizations and consumers lose control when they outsource their sensitive data and computing resources to a third party Cloud Service Provider (CSP), which may raise security and privacy concerns related to data loss and misuse appealing threats. Lack of consumers’ knowledge about their data storage location may lead to violating rules and regulations of Health Insurance Portability and Accountability Act (HIPAA) that cancost them huge penalty. Fear of data breach by internal or external hackers may decrease consumers’ trust in adopting cloud computing and benefiting from its promising features. We designed a Healthcare Trusted Cloud Computing (HTCC) framework that maintains security, privacy and considers HIPAA regulations. HTCC framework deploys Trusted Computing Group (TCG) technologies such as Trusted Platform Module (TPM), Trusted Software Stack (TSS), virtual Trusted Platform Module (vTPM), Trusted Network Connect (TNC) and Self Encrypting Drives (SEDs). We emphasize on using strong multi-factor authentication access control mechanisms and strict security controls, as well as encryption for data at storage, in-transit and while process. We contributed in customizing a cloud Service Level Agreement (SLA) by considering healthcare requirements. HTCC was evaluated by comparing with previous researchers’ work and conducting survey from experts. Results were satisfactory and showed acceptance of the framework. We aim that our proposed framework will assist in optimizing trust on cloud computing to be adopted in healthcare sector.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Cloud computing offers significant features such as resource pooling, scalability, on-demand self... more Cloud computing offers significant features such as resource pooling, scalability, on-demand self service, availability, and reliability to organizations to improve their quality of services. For example by using cloud computing services in healthcare it is possible to reach large population of people in isolated geographical areas which will assist in saving their lives in critical situations. It enables the use of latest technologies through its various service delivery and deployment models via the internet on pay-per-use billing pattern. However, cloud computing has dark side when it comes to security and privacy considerations. Critical industries such as healthcare and banking are reluctant to trust cloud computing due to the fear of losing their sensitive data, as it resides on the cloud with no knowledge of data location and lack of transparency of Cloud Service Providers (CSPs) mechanisms used to secure their data and applications which have created a barrier against adopting this agile computing paradigm. This paper addresses cloud computing security concerns that must be considered in order to adopt cloud services in information critical industries.
Bookmarks Related papers MentionsView impact
International Conference for Emerging Technologies in Computing, 2019
Smartphones have changed the world from a primitive to a high-tech standpoint. However, there hav... more Smartphones have changed the world from a primitive to a high-tech standpoint. However, there have been many incidents where third parties have used confidential data of the users without their consent. Thus, it causes people to be paranoid and distrustful of their smartphones, never knowing which application threatens to expose them. In this paper, we have conducted an in-depth review of the significance of smartphones in human life, and we have discussed the methods used by various authorities to collect and exploit users' data for enigmatic benefits. Moreover, we surveyed the smartphone users to identify the vulnerabilities leading to privacy violation, and to examine their knowledge about the protection mechanisms. We determined that Technology and Human are the two major vulnerabilities that are exploited to invade users' privacy. It is the necessity of the moment for the researchers and developers to formulate solutions that could be used to educate and protect smartphone users from potential threats and exploitation of data.
Bookmarks Related papers MentionsView impact
IEEE 2018 Fourth International Conference on Advances in Computing, Communication & Automation (ICACCA), 2019
Machine Learning is an emerging field which has created a significant positive and undesirable im... more Machine Learning is an emerging field which has created a significant positive and undesirable impact too many industries. This technology has been well received and widely used for precise decision making as its ability to process, analyze and visualize any mass amount of data. This paper will introduce the machine learning application, moving on to describe its use in healthcare and medical, people mobility, political campaign and banking. The discussion further continues to outline its impact from social, political and ethical aspects, Machine learning technology is discussed based on the use of machine learning is various activities and the effect that the technology perceived from the ethical, social and political point of view.
Bookmarks Related papers MentionsView impact
IEEE, 2018
NotPetya, when released in 2017, was believed to be ransomware. NotPetya injects malicious codes ... more NotPetya, when released in 2017, was believed to be ransomware. NotPetya injects malicious codes in the computer and then attempts to gain administrator access. Following that, it infects other computers in the network. NotPetya uses the EternalBlue Server Message Block (SMB) exploit to conduct the attacks. The hard drives get encrypted, and when the computer is booted, the ransom note is displayed. NotPetya does not provide enough information for a decryption key to be produced, making it a malware. Businesses across industries have been affected without having an opportunity for system recovery. While definite solutions are lacking, vaccines exist, where, the presence of a local file, blocks the NotPetya execution. Activating the vaccine can be tedious and cumbersome for average computer users. Hence, our solution is intended to educate them in an interactive manner. Users will be more susceptible towards the vaccination while learning about security habits that need to be practiced. From this, average computer users can walk away with the knowledge that can protect them from future attacks. Note: (Full paper is available on request)
Bookmarks Related papers MentionsView impact
A multi-tenant Cloud Computing Infrastructure (CCI) consists of several Virtual Machines (VMs) ru... more A multi-tenant Cloud Computing Infrastructure (CCI) consists of several Virtual Machines (VMs) running on same physical platform by using virtualization techniques. The VMs are monitored and managed by kernel based software i.e. Virtual Machine Monitor (VMM) or hypervisor which is main component of Virtualized Cloud Computing Infrastructure (VCCI). Due to software based vulnerabilities, VMMs are compromised to security attacks that may take place from inside or outside attackers. In order to formulate a secure VCCI, VMM must be protected by implementing strong security tools and techniques such as Encryption and Key Management (EKM), Access Control Mechanisms (ACMs), Intrusion Detection Tools (IDTs), Virtual Trusted Platform Module (vTPM), Virtual Firewalls (VFs) and Trusted Virtual Domains (TVDs). In this research paper we describe the techniques of virtualizing a CCI, types of attacks on VCCI, vulnerabilities of VMMs and we critically describe the significance of security tools and techniques for securing a VCCI.
Bookmarks Related papers MentionsView impact