Now showing 1 - 10 of 49
  • Publication
    Clustering Approaches for Financial Data Analysis: a Survey
    (CSREA Press, 2012-07-19) ; ;
    Nowadays, financial data analysis is becoming increasingly important in the business market. As companies collect more and more data from daily operations, they expect to extract useful knowledge from existing collected data to help make reasonable decisions for new customer requests, e.g. user credit category, confidence of expected return, etc. Banking and financial institutes have applied different data mining techniques to enhance their business performance. Among these techniques, clustering has been considered as a significant method to capture the natural structure of data. However, there are not many studies on clustering approaches for financial data analysis. In this paper, we evaluate different clustering algorithms for analysing different financial datasets varied from time series to transactions. We also discuss the advantages and disadvantages of each method to enhance the understanding of inner structure of financial datasets as well as the capability of each clustering method in this context.
  • Publication
    Digital Forensic Investigations in the Cloud: A Proposed Approach for Irish Law Enforcement
    Cloud computing offers utility oriented Information and Communications Technology (ICT) services to users all over the world. The evolution of Cloud computing is driving the design of data centres by architecting them as networks of virtual services; this enables users to access and run applications from anywhere in the world. Cloud computing offers significant advantages to organisations through the provision of fast and flexible ICT hardware and software infrastructures, thus enabling organisations to focus on creating innovative business values for the services they provide.As the prevalence and usage of networked Cloud computer systems increases, logically the likelihood of these systems being used for criminal behaviour also increases. Thus, this new computing evolution has a direct effect on, and creates challenges for, digital forensic practitioners working in Irish law enforcement.The field of digital forensics has grown rapidly over the last decade due to the rise of the internet and associated crimes; however while the theory is well established, the practical application of the discipline is still new and developing. Law enforcement agencies can no longer rely on traditional digital forensic methods of data acquisition through device seizure to gather relevant evidence pertaining to an investigation. Using traditional digital forensic methods will lead to the loss of valuable evidential material if employed during investigations which involve Cloud based infrastructures.Cloud computing and its impact on digital forensics will continue to grow. This paper analyses traditional digital forensics methods and explains why these are inadequate for Cloud forensic investigations with particular focus on Irish law enforcement agencies. In this paper, we do a survey on approaches to digital forensics of Irish Law Enforcement Agencies for cloud based investigations and we propose a digital forensic framework approach to acquiring data from Cloud environments. This proposed approach aims to overcome the limitations of traditional digital forensics and the challenges Cloud computing presents for digital forensic practitioners working in Irish law enforcement.
  • Publication
    Toward a new cloud-based approach to preserve the privacy for detecting suspicious cases of money laundering in an investment bank
    Today, money laundering poses a serious threat not only to financialinstitutions but also to the nations. This criminal activity is becoming more andmore sophisticated and seems to have moved from the clich of drug traffickingto financing terrorism and surely not forgetting personal gain. Mostinternational financial institutions have been implementing anti-moneylaundering solutions to fight investment fraud. On the other hand, cloud-basedapplications are merging daily and bringing to clients with lower cost ofplatforms and data storage, greater scalability and improved businesscontinuity. Hence, more financial instituitions aim to move their ITinfrastructure to the cloud. However, accessing directly to the customertransaction datasets by a third party could be a confidential issue. This approachis more severe when these solutions are built by collaborating partners.Traditional methods are based on data access agreement but there is still a riskof infringing privacy. In order to preserve the privacy of datasets, different datadisguising methods have been proposed. Nevertheless, analysing disguiseddatasets is a performance issue in the context of detecting suspicious moneylaundering cases where the real value of data has an important impact. Indeed,the results of analysis could also be a privacy issue. Within the scope of acollaboration project for developing a new cloud-based solution for the Anti-Money Laundering Units in an international investment bank, in this paper, wepropose new cloud-based approach using data disguising methods applied inanalysing transaction datasets. We also show that the creating relevantdimensions from the current ones is efficient for analysing transaction datasetsin terms of both detecting suspicious case and privacy preserving.
  • Publication
    ADMIRE framework: Distributed Data Mining on Data Grid platforms
    In this paper, we present the ADMIRE architecture; a new framework for developing novel and innovative data mining techniques to deal with very large and distributed heterogeneous datasets in both commercial and academic applications. The main ADMIRE components are detailed as well as its interfaces allowing the user to efficiently develop and implement their data mining applications techniques on a Grid platform such as Globus ToolKit, DGET, etc.
  • Publication
    Distributed Knowledge Map for Mining Data on Grid Platforms
    Recently, huge datasets representing different applications domains are produced and stored on distributed platforms. These datasets are, generally, owned by different organizations. As a consequence, The scale and distribution nature of these datasets have created the problem of efficient mining and management on these platforms. Most of the existing knowledge management approaches are mainly for centralized data mining. Few of them propose solutions for mining and handling knowledge on Grid. However, the new knowledge is stored and managed as any other kinds of resources.
  • Publication
    An Efficient Data Warehouse for Crop Yield Prediction
    Nowadays, precision agriculture combined with modern information and communications technologies, is becoming more common in agricultural activities such as automated irrigation systems, precision planting, variable rate applications of nutrients and pesticides, and agricultural decision support systems. In the latter, crop management data analysis, based on machine learning and data mining, focuses mainly on how to efficiently forecast and improve crop yield. In recent years, raw and semi-processed agricultural data are usually collected using sensors, robots, satellites, weather stations, farm equipment, farmers and agribusinesses while the Internet of Things (IoT) should deliver the promise of wirelessly connecting objects and devices in the agricultural ecosystem. Agricultural data typically captures information about farming entities and operations. Every farming entity encapsulates an individual farming concept, such as field, crop, seed, soil, temperature, humidity, pest, and weed. Agricultural datasets are spatial, temporal, complex, heterogeneous, non-standardized, and very large. In particular, agricultural data is considered as Big Data in terms of volume, variety, velocity and veracity. Designing and developing a data warehouse for precision agriculture is a key foundation for establishing a crop intelligence platform, which will enable resource efficient agronomy decision making and recommendations. Some of the requirements for such an agricultural data warehouse are privacy, security, and real-time access among its stakeholders (e.g., farmers, farm equipment manufacturers, agribusinesses, co-operative societies, customers and possibly Government agencies). However, currently there are very few reports in the literature that focus on the design of efficient data warehouses with the view of enabling Agricultural Big Data analysis and data mining. In this paper, we propose a system architecture and a database schema for designing and implementing a continental level data warehouse. Besides, some major challenges and agriculture dimensions are also reviewed and analysed.
  • Publication
    Leveraging Decentralisation to Extend the Digital Evidence Acquisition Window: Case Study on BitTorrent Sync
    (Association of Digital Forensics, Security and Law, 2014) ; ; ;
    File synchronization services such as Dropbox, Google Drive, Microsoft OneDrive, Apple iCloud, etc., are becoming increasingly popular in today's always-connected world. A popular alternative to the aforementioned services is BitTorrent Sync. This is a decentralized/cloudless file synchronization service and is gaining significant popularity among Internet users with privacy concerns over where their data is stored and who has the ability to access it. The focus of this paper is the remote recovery of digital evidence pertaining to files identified as being accessed or stored on a suspect's computer or mobile device. A methodology for the identification, investigation, recovery and verification of such remote digital evidence is outlined. Finally, a proof-of-concept remote evidence recovery from BitTorrent Sync shared folder highlighting a number of potential scenarios for the recovery and verification of such evidence.
  • Publication
    Security Threats of URL Shortening: A Users Perspective
    (IACSIT Press, 2015-09) ;
    Short URLs have been used on the Internet for several years now and as time goes by new security threats are discovered in relation to their use (e.g. malware, phishing, spam). However, although current research in literature has compiled addressing the security threats when utilizing such types of URLs, no study approached the assessment of user confidence and user awareness regarding short URLs. Thus the aim of this paper is to cover the existing knowledge gap and to compile a baseline assessment on the frequency of use, user confidence and user awareness when utilizing short URLs. To do so, we have developed questionnaire connected to the previously mentioned aspects and which was applied to one hundred persons of various nationalities from within the European Union with various user experiences when it comes to the Internet and short URLs. The analysis of the replies received from the participants to the survey has revealed a general awareness that there are security risks associated with short URLs, a tendency of propagation of short URLs to other Internet services and platforms.
  • Publication
    Forensic analysis of Exfat Artefacts
    (University College Dublin, 2018-05-23) ; ; ;
    Although keeping some basic concepts inherited from FAT32, the exFAT file system introduces many differences, such as the new mapping scheme of directory entries. The combination of exFAT mapping scheme with the allocation of bitmap files and the use of FAT leads to new forensic possibilities. The recovery of deleted files, including fragmented ones and carving becomes more accurate compared with former forensic processes. Nowadays, the accurate and sound forensic analysis is more than ever needed, as there is a high risk of erroneous interpretation. Indeed, most of the related work in the literature on exFAT structure and forensics, is mainly based on reverse engineering research, and only few of them cover the forensic interpretation. In this paper, we propose a new methodology using of exFAT file systems features to improve the interpretation of inactive entries by using bitmap file analysis and recover the file system metadata information for carved files. Experimental results show how our approach improves the forensic interpretation accuracy.
  • Publication
    An Analytical Approach to the Recovery of Data from 3rd Party Proprietary CCTV File Systems
    According to recent predictions, the global video surveillance market is expected to reach $42.06 billion annually by 2020. The market is extremely fragmented with only around 40% of the market being accounted for by the 15 top video surveillance equipment suppliers as in an annual report issued by IMS Research. The remaining market share was split amongst the numerous other smaller companies who provide CCTV solutions, usually at lower prices than their brand name counterparts. This cost cutting generally results in a lower specification of components. Recently, an investigation was undertaken in relation to a serious criminal offence, of which significant video footage had been captured on a CCTV DigitalVideo Recorder (DVR). The unit was setup to save the last 31 days of footage to an internal hard drive. However, despite the referenced footage being within this timeframe, it could not be located. The DVR unit was submitted for forensic examination anddata retrieval of specified video footage which, according to the proprietary video backup application, was not retrievable. In this paper, we present the process and method of the forensic retrieval of video footage from a DVR. The objective of this method is to retrieve the oldest video footage possible from a proprietary designed file storage system. We also evaluate our approach with a Ganz CCTV DVR system model C-MPDVR-16 to show that the file system of a DVR has been reversed engineering with no initial knowledge, application or documentation available.