Incremental learning from stream data

Recent years have witnessed an incredibly increasing interest in the topic of incremental learning. Unlike conventional machine learning situations, data flow targeted by incremental learning becomes available continuously over time. Accordingly, it is desirable to be able to abandon the traditional assumption of the availability of representative training data during the training period to develop decision boundaries. Under scenarios of continuous data flow, the challenge is how to transform the vast amount of stream raw data into information and knowledge representation, and accumulate experience over time to support future decision-making process. In this paper, we propose a general adaptive incremental learning framework named ADAIN that is capable of learning from continuous raw data, accumulating experience over time, and using such knowledge to improve future learning and prediction performance. Detailed system level architecture and design strategies are presented in this paper. Simulation results over several real-world data sets are used to validate the effectiveness of this method.

Heller's myotomy and pneumatic dilatation in the treatment of achalasia: a population-based case–control study assessing long-term quality of life

Long-term health-related quality-of-life (HRQL) outcomes have not been widely reported in the
treatment of achalasia. The aims of this study were to examine long-term disease-specific and general HRQL in
achalasia patients using a population-based case–control method, and to assess HRQL between treatment interventions.
Manometrically diagnosed achalasia cases (n = 120) were identified and matched with controls (n = 115)
using a population-based approach. Participants completed general (SF-12) and disease-specific (Achalasia Severity
Questionnaire [ASQ]) HRQL questionnaires, as appropriate, in a structured interview. Mean composite scores
for SF-12 (Mental Component Summary score [MCS-12] and Physical Component Summary score [PCS-12]) and
ASQ were compared between cases and controls, or between intervention groups, using an independent t-test.
Adjusted mean differences in HRQL scores were evaluated using a linear regression model. Achalasia cases were
treated with a Heller’s myotomy (n = 43), pneumatic dilatation (n = 44), or both modalities (n = 33). The median
time from last treatment to HRQL assessment was 5.7 years (interquartile range 2.4–11.5). Comparing achalasia
patients with controls, PCS-12 was significantly worse (40.9 vs. 44.2, P = 0.01), but MCS-12 was similar. However,
both PCS-12 (39.9 vs. 44.2, P = 0.03) and MCS-12 (46.7 vs. 53.5, P = 0.004) were significantly impaired in those
requiring dual treatment compared with controls. Overall however, there was no difference in adjusted HRQL
between patients treated with Heller’s myotomy, pneumatic dilatation or both treatment modalities. In summary,
despite treatment achalasia patients have significantly worse long-term physical HRQL compared with population
controls. No HRQL differences were observed between the treatment modalities to suggest a benefit of one
treatment over another.

Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.

Malignancy and mortality in a population-based cohort of patients with coeliac disease or 'gluten sensitivity'

Aim: To determine the risk of malignancy and mortality in patients with a positive endomysial or anti-gliadin antibody test in Northern Ireland.

Methods: A population-based retrospective cohort study design was used. Laboratory test results used in the diagnosis of coeliac disease were obtained from the Regional Immunology Laboratory, cancer statistics from the Northern Ireland Cancer Registry and mortality statistics from the General Registrar Office, Northern Ireland. Age standardized incidence ratios of malignant neoplasms and standardized mortality ratios of all-cause and cause-specific mortality were calculated.

Results: A total of 13 338 people had an endomysial antibody and/or an anti-gliadin antibody test in Northern Ireland between 1993 and 1996. There were 490 patients who tested positive for endomysial antibodies and they were assumed to have coeliac disease. There were 1133 patients who tested positive for anti-gliadin anti-bodies and they were defined as gluten sensitive. Malignant neoplasms were not significantly associated with coeliac disease; however, all-cause mortality was significantly increased following diagnosis. The standardized incidence and mortality ratios for non-Hodgkin's lymphoma were increased in coeliac disease patients but did not reach statistical significance. Lung and breast cancer incidence were significantly lower and all-cause mortality, mortality from malignant neoplasms, non-Hodgkin's lymphoma and digestive system disorders were significantly higher in gluten sensitive patients compared to the Northern Ireland population.

Conclusion: Patients with coeliac disease or gluten sensitivity had higher mortality rates than the Northern Ireland population. This association persists more than one year after diagnosis in patients testing positive for anti-gliadin antibodies. Breast cancer is significantly reduced in the cohort of patients with gluten sensitivity. © 2007 The WJG Press. All rights reserved.

Accommodative dysfunction in children with cerebral palsy: a population based study

Purpose. To determine the prevalence, nature, and degree of accommodative dysfunction among children with different types and severities of cerebral palsy (CP) in Northern Ireland. Methods. Ninety subjects with CP (aged 4–15 years) were recruited through the Northern Ireland CP Register (NICPR). Modified Nott dynamic retinoscopy was used to measure lag and lead of accommodation at three test distances: 25 cm (4 D), 16.7 cm (6 D), and 10 cm (10 D) with the distance correction in place. Accommodative function was also assessed in an age-matched control group (n = 125) for comparison. Each subject’s neurologic status was derived from the NICPR. Results. Children with CP demonstrate significantly reduced accommodative responses compared with their neurologically normal peers. Of the subjects with CP, 57.6% demonstrated an accommodative lag outside normal limits at one or more distances. Reduced accommodative responses were significantly associated with more severe motor and intellectual impairments (ANOVA P = 0.001, P < 0.01, respectively). Conclusions. Brain injury such as that present in CP has a significant impact on accommodative function. These findings have implications for the optometric care of children with CP and inform our understanding of the impact of early brain injury on visual development.