Improvements in the data partitioning approach for frequent itemsets mining

Frequent Itemsets mining is well explored for various data types, and its computational complexity is well understood. There are methods to deal effectively with computational problems. This paper shows another approach to further performance enhancements of frequent items sets computation. We have made a series of observations that led us to inventing data pre-processing methods such that the final step of the Partition algorithm, where a combination of all local candidate sets must be processed, is executed on substantially smaller input data. The paper shows results from several experiments that confirmed our general and formally presented observations.

A border-based approach for hiding sensitive frequent itemsets

Sharing data among organizations often leads to mutual benefit. Recent technology in data mining has enabled efficient extraction of knowledge from large databases. This, however, increases risks of disclosing the sensitive knowledge when the database is released to other parties. To address this privacy issue, one may sanitize the original database so that the sensitive knowledge is hidden. The challenge is to minimize the side effect on the quality of the sanitized database so that nonsensitive knowledge can still be mined. In this paper, we study such a problem in the context of hiding sensitive frequent itemsets by judiciously modifying the transactions in the database. To preserve the non-sensitive frequent itemsets, we propose a border-based approach to efficiently evaluate the impact of any modification to the database during the hiding process. The quality of database can be well maintained by greedily selecting the modifications with minimal side effect. Experiments results are also reported to show the effectiveness of the proposed approach. © 2005 IEEE

"Action at a distance":accounting inscriptions and the reporting of episodes of clinical care

This paper reports on an aspect of the implementation of a sophisticated system of Casemix Budgeting within a large public hospital in New Zealand. The paper examines the role of accounting inscription in supporting a system of “remote” management control effected through the Finance function at the hospital. The paper provides detailed description and analysis of part of the casemix technology in use at the research site. The implementation of clinical budgeting through the Transition casemix system will be examined by describing an aspect of the casemix system in detail. The design and use of management reporting is described. Reporting to different levels of management and for differing parts of the organisation are discussed with particular emphasis on the adoption of traditional analysis of costs using standard costing and variance analysis techniques.

Seeing and believing: three episodes in the history of neurophysiology

In this contribution I look at three episodes in the history of neurophysiology that bring out the complex relationship between seeing and believing. I start with Vesalius in the mid-sixteenth century who writes that he can in no way see any cavity in nerves, even in the optic nerves. He thus questions the age-old theory (dating back to the Alexandrians in the third century BC) but, because of the overarching psychophysiology of his time, does not press his case. This conflict between observation and theory persisted for a quarter of a millennium until finally resolved at the beginning of the nineteenth century by the discoveries of Galvani and Volta. The second case is provided by the early history of retinal synaptology. Schultze in 1866 had represented rod spherules and bipolar dendrites in the outer plexiform layer as being separated by a (synaptic) gap, yet in his written account, because of his theoretical commitments, held them to be continuous. Cajal later, 1892, criticized Schultze for this pusillanimity, but his own figure in La Cellule is by no means clear. It was only with the advent of the electron microscopy in the mid-twentieth century that the true complexity of the junction was revealed and it was shown that both investigators were partially right. My final example comes from the Hodgkin-Huxley biophysics of the 1950s. Their theory of the action potential depended on the existence of unseen ion pores with quite complex biophysical characteristics. These were not seen until the Nobel-Prize-winning X-ray diffraction analyses of the early twenty-first century. Seeing, even at several removes, then confirmed Hodgkin and Huxley’s belief. The relation between seeing and believing is by no means straightforward.

Episodes in the Malaysian auditing sage

Purpose – The purpose of this paper is to examine the various episodes in the Malaysian auditing saga, covering the period of the first 40 years post-independence in 1957 to just before the onset of the Asian Financial Crisis in 1997. Design/methodology/approach – Based on documentary analysis, the paper offers a historical account of the development of the auditing profession with reference to the dynamic changes in its political and socio-economic environment. Findings – The paper concludes that the function of auditing in Malaysian society responded to political-economic pressures over time viz. changing from maintaining the economic policy to serve Western investors to accommodating ethnic relations, and to strengthening the bond between local and global corporate elites and the political leaders. Originality/value – Since, little is known of the professionalisation process in Malaysia, our analysis of the structural conditions during the 40 years from the achievement of independence from the British in 1957 to just before the onset of the Asian Financial Crisis in 1997 and our assessment of their implications for auditing contributes to knowledge in this area

The involvement/exclusion paradox of spontaneous volunteering:new lessons from winter flood episodes in England

This article focuses on the involvement and management of spontaneous volunteers (SVs). It develops a new theory—which we call the “involvement/exclusion” paradox—about a situation which is frequently manifested when SVs converge in times of disaster. After reviewing research and policy guidance relating to spontaneous volunteering, we present findings from a study of responses to winter flood episodes in England. Taking together the empirical findings and the literature, the article analyzes elements inherent in the involvement/exclusion paradox and develops a conceptual model to illustrate and explain the paradox. Implications for managers and future research are discussed.

Temporal Mining for Distributed Systems

Many systems and applications are continuously producing events. These events are used to record the status of the system and trace the behaviors of the systems. By examining these events, system administrators can check the potential problems of these systems. If the temporal dynamics of the systems are further investigated, the underlying patterns can be discovered. The uncovered knowledge can be leveraged to predict the future system behaviors or to mitigate the potential risks of the systems. Moreover, the system administrators can utilize the temporal patterns to set up event management rules to make the system more intelligent. With the popularity of data mining techniques in recent years, these events grad- ually become more and more useful. Despite the recent advances of the data mining techniques, the application to system event mining is still in a rudimentary stage. Most of works are still focusing on episodes mining or frequent pattern discovering. These methods are unable to provide a brief yet comprehensible summary to reveal the valuable information from the high level perspective. Moreover, these methods provide little actionable knowledge to help the system administrators to better man- age the systems. To better make use of the recorded events, more practical techniques are required. From the perspective of data mining, three correlated directions are considered to be helpful for system management: (1) Provide concise yet comprehensive summaries about the running status of the systems; (2) Make the systems more intelligence and autonomous; (3) Effectively detect the abnormal behaviors of the systems. Due to the richness of the event logs, all these directions can be solved in the data-driven manner. And in this way, the robustness of the systems can be enhanced and the goal of autonomous management can be approached. This dissertation mainly focuses on the foregoing directions that leverage tem- poral mining techniques to facilitate system management. More specifically, three concrete topics will be discussed, including event, resource demand prediction, and streaming anomaly detection. Besides the theoretic contributions, the experimental evaluation will also be presented to demonstrate the effectiveness and efficacy of the corresponding solutions.

Síndrome de Guillain-Barré: epidemiologia, prognóstico e fatores de risco

Introduction. Guillain-Barré syndrome (GBS) is an immune-mediated polyneuropathy and the principal cause of acute neuromuscular paralysis. The most prominent GBS subtypes are: acute inflammatory demyelinating polyneuropathy (AIDP), acute motor axonal neuropathy (AMAN), acute motor-sensory axonal neuropathy (AMSAN) and Fisher syndrome (FS). Differences in geographical distribution of variants have been reported. In Brazil, there are few studies describing the characteristics of GBS, but none on the frequency of GBS variants and their clinical manifestations. Infection-induced aberrant immune response resulting from molecular mimicry and formation of cross-reacting antibodies, contribute to complement activation. Functional biallelic polymorphism in immunoglobulin receptors that influence the affinity of IgG subclasses and the type of immune response have been described, suggesting genetic susceptibility to developing disease. It remains unclear whether individuals carrying different FCGR alleles have differential risk for GBS and⁄or disease severity. The goals of this study were: (1) To characterize GBS and describe the clinical findings in a cohort of patients with GBS from the state of Rio Grande do Norte, Brazil; (2) to determine whether polymorphism in FCGR were associated with development of GBS, and (3) to tease out whether the global gene expression studies could be a tool to identify pathways and transcriptional networks which could be regulated and decrease the time of disease. Methods. Clinical and laboratory data for 149 cases of GBS diagnosed from 1994 to 2013 were analyzed. Genomic DNA and total RNA were extracted from whole blood. Antigangliosides antibodies were determined in the sera. In addition, we also assessed whether FCGR polymorphism are present in GBS (n=141) and blood donors (n=364), and global gene expressions were determined for 12 participants with GBS. Blood samples were collected at the diagnosis and post-recovery. Results. AIDP was the most frequent variant (81.8%) of GBS, followed by AMAN (14.7%) and AMSAN (3.3%). The incidence of GBS was 0.3 ⁄ 100,000 people for the state of Rio Grande do Norte and cases occurred at a younger age. GBS was preceded by infections, with the axonal variant associated with episodes of diarrhea (P = 0.025). Proximal weakness was more frequent in AIDP, and distal weakness predominant in the axonal variant. Compared to 42.4% of cases with AIDP (P<0.0001), 84.6% of cases with the axonal variant had nadir in <10 days. Individuals with the axonal variant took longer to recover deambulation (P<0.0001). The mortality of GBS was 5.3%. A worse outcome was related to an axonal variant (OR17.063; P=0.03) and time required to improve one point in the Hughes functional scale (OR 1.028; P=0.03). The FCGR genotypes and allele frequencies did not differ significantly between the patients with GBS and the controls (FCGR2A p=0.367 and FCGR3A p=0.2430). Global gene expression using RNAseq showed variation in transcript coding for protein isoforms during acute phase of disease. Conclusions. The annual incidence of GBS was 0.3 per 100,00 and there was no seasonal pattern. A predominance of the AIDP variant was seen, and the incidence of the disease decreased with age. The distribution of weakness is a function of the clinical variants, and individuals with the axonal variant had a poorer prognosis. Early diagnosis and variant identification leads to proper intervention decreasing in long-term morbidity. FCGR polymorphisms do not seem to influence susceptibility to GBS in this population. This study found deregulated genes and signs of transcriptional network alterations during the acute and recovery phases in GBS. Identification of pathways altered during disease might be target for immune regulation and with potential to ameliorate symptoms.

Infecções por enterobacteriaceae resistente aos carbapenêmicos em hospital de ensino: epidemiologia e caracterização molecular

Introduction: The production of KPC (Klebsiella pneumoniae carbapenemase) has become an important mechanism of carbapenem-resistance among Enterobacteriaceae strains. In Brazil, KPC is already widespread and its incidence has increased significantly, reducing treatment options. The “perfect storm” combination of the absence of new drug developmentand the emergence of multidrug-resistant strains resulted in the need for the use of older drugs, with greater toxicity, such as polymyxins. Aims: To determine the occurrence of carbapenemase-producing strains in carbapenem-resistant Enterobacteriaceae isolated from patients with nosocomial infection/colonization during September/2014 to August/2015, to determine the risk factors associated with 30-day- mortality and the impact of inappropriate therapy. Materials and Methods: We performed a case control study to assess the risk factors (comorbidities, invasive procedures and inappropriate antimicrobial therapy) associated with 30-day-mortality, considering the first episode of infection in 111 patients. The resistance genes blaKPC, blaIMP, blaVIM and blaNDM-1 were detected by polymerase chain reaction technique. Molecular typing of the strains involved in the outbreak was performed by pulsed field gel electrophoresis technique. The polymyxin resistance was confirmed by the microdilution broth method. Results: 188 episodes of carbapenem-resistant Enterobacteriaceae infections/colonizations were detected; of these, 122 strains were recovered from the hospital laboratory. The presence of blaKPC gene were confirmed in the majority (74.59%) of these isolates. It was not found the presence of blaIMP , blaVIM and blaNDM-1 genes. K. pneumoniae was the most frequent microorganism (77,13%), primarily responsible for urinary tract infections (21,38%) and infections from patients of the Intensive Care Unit (ICU) (61,38%). Multivariate statistical analysis showed as predictors independently associated with mortality: dialysis and bloodstream infection. The Kaplan-Meier curve showed a lower probability of survival in the group of patients receiving antibiotic therapy inappropriately. Antimicrobial use in adult ICU varied during the study period, but positive correlation between increased incidence of strains and the consumption was not observed. In May and July 2015, the occurrence rates of carbapenem-resistant Enterobacteriaceae KPC-producing per 1000 patient-days were higher than the control limit established, confirming two outbreaks, the first caused by colistin-susceptible KPC-producing K. pneumoniae isolates, with a polyclonal profile and the second by a dominant clone of colistin-resistant (≥ 32 μg/mL) KPC-producing K. pneumoniae. The cross transmission between patients became clear by the temporal and spatial relationships observed in the second outbreak, since some patients occupied the same bed, showing problems in hand hygiene adherence among healthcare workers and inadequate terminal disinfection of environment. The outbreak was contained when the ICU was closed to new admissions. Conclusions: The study showed an endemicity of K. pneumoniae KPC-producing in adult ICU, progressing to an epidemic monoclonal expansion, resulted by a very high antibiotic consumption of carbapenems and polymyxins and facilitated by failures in control measures the unit.

A reliable and robust algorithm to identify episodes of hospitalizations using RAMQ medical services claims : methodology issues & data validation

Thèse numérisée par la Direction des bibliothèques de l'Université de Montréal.

Mining dynamic databases for frequent closed itemsets

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.