From sequential patterns to concurrent branch patterns: a new post sequential patterns mining approach
SubjectsG790 Artificial Intelligence not elsewhere classified
sequential patterns mining
Sequential Patterns Graph
MetadataShow full item record
AbstractSequential patterns mining is an important pattern discovery technique used to identify frequently observed sequential occurrence of items across ordered transactions over time. It has been intensively studied and there exists a great diversity of algorithms. However, there is a major problem associated with the conventional sequential patterns mining in that patterns derived are often large and not very easy to understand or use. In addition, more complex relations among events are often hidden behind sequences. A novel model for sequential patterns called Sequential Patterns Graph (SPG) is proposed. The construction algorithm of SPG is presented with experimental results to substantiate the concept. The thesis then sets out to define some new structural patterns such as concurrent branch patterns, exclusive patterns and iterative patterns which are generally hidden behind sequential patterns. Finally, an integrative framework, named Post Sequential Patterns Mining (PSPM), which is based on sequential patterns mining, is also proposed for the discovery and visualisation of structural patterns. This thesis is intended to prove that discrete sequential patterns derived from traditional sequential patterns mining can be modelled graphically using SPG. It is concluded from experiments and theoretical studies that SPG is not only a minimal representation of sequential patterns mining, but it also represents the interrelation among patterns and establishes further the foundation for mining structural knowledge (i.e. concurrent branch patterns, exclusive patterns and iterative patterns). from experiments conducted on both synthetic and real datasets, it is shown that Concurrent Branch Patterns (CBP) mining is an effective and efficient mining algorithm suitable for concurrent branch patterns.
CitationLu, J. (2006) 'From sequential patterns to concurrent branch patterns: a new post sequential patterns mining approach'. PhD thesis. University of Bedfordshire.
PublisherUniversity of Bedfordshire
TypeThesis or dissertation
DescriptionA thesis submitted for the degree of Doctor ofPhilosophy of the University of Bedfordshire
The following license files are associated with this item:
Showing items related by title, author, creator and subject.
Wandering pattern sensing at S-bandYang, Xiaodong; Shah, Syed Aziz; Ren, Aifeng; Zhao, Nan; Fan, Dou; Hu, Fangming; Ur-Rehman, Masood; von Deneen, Karen M.; Tian, Jie; Xidian University; et al. (Institute of Electrical and Electronics Engineers Inc., 2017-12-27)Increasing prevalence of dementia has posed several challenges for care-givers. Patients suffering from dementia often display wandering behavior due to boredom or memory loss. It is considered to be one of the challenging conditions to manage and understand. Traits of dementia patients can compromise their safety causing serious injuries. This paper presents investigation into the design and evaluation of wandering scenarios with patients suffering from dementia using an S-band sensing technique. This frequency band is the wireless channel commonly used to monitor and characterize different scenarios including random, lapping, and pacing movements in an indoor environment. Wandering patterns are characterized depending on the received amplitude and phase information of that measures the disturbance caused in the ideal radio signal. A secondary analysis using support vector machine is used to classify the three patterns. The results show that the proposed technique carries high classification accuracy up to 90% and has good potential for healthcare applications.
Patterns of sentencing: differential sentencing across England and WalesBateman, Tim; Stanley, Chris; Nacro; Youth Justice Board; British Quality Foundation (NCJRS Publication, 2002)This report presents findings from a research study commissioned by the Youth Justice Board to identify the relative seriousness of offenses leading to custody and other high level penalties in a range of areas where differential patterns of custodial sentencing prevailed. Criminal statistics for England and Wales reveal substantial geographic variation in the pattern of youth sentencing. Statistics to the Youth Justice Board (YJB) provides evidence of this variation. This research study, commissioned by the YJB, explored any relationship between the use of high tariff disposal, with a particular emphasis on custodial penalties, and a range of possible influences upon patterns of sentencing. The study specifically investigated the distribution of sentences below the level of custody, case gravity, including the seriousness of current offending and previous convictions, the perceived range and quality of local youth justice services to support court orders short of custody, and the effectiveness of communication between the youth offending team and the court and the exchange of information between agencies involved in the delivery of youth justice. Highlights of key findings on distinguishing characteristics typical of high and low custody areas include for low custody areas: (1) greater use of lower level penalties; (2) lower use of community sentences; (3) greater use of unconditional bail; (4) magistrates express greater confidence in delivery of services; and (5) pre-sentence reports more effective as a mechanism for provision of information. Highlights of key findings for high custody areas include: (1) lower use of lower level penalties; (2) higher use of community penalties; (3) lower average case gravity scores for community sentences; (4) magistrates express reduced confidence in delivery of services; and (5) pre-sentence reports less effective as a mechanism for provision of information. Appendixes 1-5