A Maximum Entropy Approach for Collaborative Filtering

Collaborative filtering (CF) involves predicting the preferences of a user for a set of items given partial knowledge of the user's preferences for other items, while leveraging a database of profiles for other users. CF has applications e.g. in predicting Web sites a person will visit and in recommending products. Fundamentally, CF is a pattern recognition task, but a formidable one, often involving a huge feature space, a large data set, and many missing features. Even more daunting is the fact that a CF inference engine must be capable of predicting any (user-selected) items, given any available set of partial knowledge on the user's other preferences. In other words, the model must be designed to solve any of a huge (combinatoric) set of possible inference tasks. CF techniques include memory-based, classification-based, and statistical modelling approaches. Among these, modelling approaches scale best with large data sets and are the most adept at handling missing features. The disadvantage of these methods lies in the statistical assumptions (e.g. feature independence), which may be unjustified. To address this shortcoming we propose a new model-based CF method, based on the maximum entropy principle. For the MS Web application, the new method is demonstrated to outperform a number of CF approaches, including naive Bayes and latent variable (cluster) models, support vector machines (SVMs), and the (Pearson) correlation method.     

The role of the American Board of Professional Psychology in professional mobility.

This article describes the role of certification by the American Board of Professional Psychology (ABPP) in easing the process by which psychologists move beyond their original jurisdictional boundaries to practice psychology. Meeting the requirements for licensure or certification in the various jurisdictions can be a difficult task because these requirements vary considerably from jurisdiction to jurisdiction. Other mechanisms that are available to facilitate this process include the Certificate of Professional Qualification in Psychology issued by the Association of State and Provincial Psychology Boards and certification by the National Register of Health Service Providers in Psychology. The ABPP certificate/diploma has been regarded by many state psychological associations and state boards of psychology as an appropriate way in which to recognize psychologists who are eligible for licensure/certification in a jurisdiction because of the examination requirements for board certification. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Multiway frequency analysis for experimental psychologists.

Many research designs in experimental psychology generate data that are fundamentally discrete or categorical in nature, and produce multiway tables of frequencies. Despite an extensive and, more recently, accessible literature on the topic, multiway frequency analysis is rarely used in experimental psychology. A reason may be the form of exposition in the literature, with emphases and concerns far removed from those of the typical experimental psychologist. An approach to multiway frequency analysis for experimental psychologists is described that has the features we want: asymmetrical designs, factors assessed for their respective main and interactive effects in a manner analogous to ANOVA, and the ability to handle within-subject designs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Do changes in cognitive factors influence outcome following multidisciplinary treatment for chronic pain? A cross-lagged panel analysis.

Changes in maladaptive cognitions may constitute therapeutic processes of multidisciplinary pain programs. A cross-lagged panel design was used to determine whether (a) early-treatment cognitive change predicted late-treatment outcome index change, but not vice versa; and (b) these effects remained significant with depression change controlled. Ninety chronic pain patients, in a 4-week multidisciplinary program, completed measures of catastrophizing, pain helplessness, depression, pain, interference, and activity level at pre-, mid-, and posttreatment. With depression changes controlled, early-treatment catastrophizing and pain helplessness changes predicted late-treatment outcome index changes, but not vice versa; early-treatment depression changes predicted late-treatment activity changes, but not vice versa. Findings advance understanding of pain treatment process and suggest that negative cognition changes may indeed affect improvements in treatment outcome. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Egg Thiamine Status of Lake Ontario Salmonines 1995–2004 with Emphasis on Lake Trout

Alewives (Alosa pseudoharengus), the major prey fish for Lake Ontario, contain thiaminase. They are associated with development of a thiamine deficiency in salmonines which greatly increases the potential for developing an early mortality syndrome (EMS). To assess the possible effects of thiamine deficiency on salmonine reproduction we measured egg thiamine concentrations for five species of Lake Ontario salmonines. From this we estimated the proportion of families susceptible to EMS based on whether they were below the ED20, the egg thiamine concentration associated with 20% mortality due to EMS. The ED20s were 1.52, 2.63, and 2.99 nmol/g egg for Chinook salmon (Oncorhynchus tshawytscha), lake trout (Salvelinus namaycush), and coho salmon (Oncorhynchus kisutch), respectively. Based on the proportion of fish having egg thiamine concentrations falling below the ED20, the risk of developing EMS in Lake Ontario was highest for lake trout, followed by coho (O. kisutch), and Chinook salmon, with the least risk for rainbow trout (O. mykiss). For lake trout from western Lake Ontario, mean egg thiamine concentration showed significant annual variability during 1994 to 2003, when the proportion of lake trout at risk of developing EMS based on ED20 ranged between 77 and 100%. Variation in the annual mean egg thiamine concentration for western Lake Ontario lake trout was positively related (p < 0.001, r² = 0.94) with indices of annual adult alewife biomass. While suggesting the possible involvement of density-dependent changes in alewives, the changes are small relative to egg thiamine concentrations when alewife are not part of the diet and are of insufficient magnitude to allow for natural reproduction by lake trout.     

Occurrence of Lawn Care and Agricultural Pesticides in the Don River and Humber River Watersheds (1998–2002)

Between 1998 and 2002, surface water samples were collected from several sites in the Don River and Humber River watersheds, both tributaries to Lake Ontario, and analyzed for a variety of pesticides, including those used for urban lawn care. Analyses included 152 pesticide active ingredients and eight metabolites. Samples were collected during base flow periods (i.e., dry events) and rainfall events (i.e., wet events). The objectives of the study were to determine which pesticides were detectable, whether there was a difference in the detection frequency between the two watersheds and between upstream and downstream in each river, and whether precipitation influenced the frequency of detection. Eleven pesticides and one metabolite were detected in surface waters of the Don and Humber rivers or their tributaries, with approximately 72% of samples containing at least one pesticide attributable to lawn care use. The pesticides and pesticide metabolite detected in this study included 2,4-D, atrazine, bromacil, carbofuran, chlorpyrifos, cypermethrin, diazinon, dicamba, MECOPROP, metolachlor, metribuzin, and an atrazine metabolite (des-ethyl atrazine). Four pesticides exceeded federal or provincial water quality guidelines/objectives. Diazinon exceeded the provincial water quality objective in 28% of the samples taken. For the three other pesticides (atrazine, carbofuran and chlorpyrifos) exceedance of a water quality criteria occurred in less than 1% of the samples.     

Cytokine responses of human lung cells (BEAS-2B) treated with micron-sized and nanoparticles of metal oxides compared to soil dusts

Background  

The induction of cytokines by airway cells in vitro has been widely used to assess the effects of ambient and occupational particles. This study measured cytotoxicity and the release of the proinflammatory cytokines IL-6 and IL-8 by human bronchial epithelial cells treated with manufactured nano- and micron-sized particles of Al₂O₃, CeO₂, Fe₂O₃, NiO, SiO₂, and TiO₂, with soil-derived particles from fugitive dust sources, and with the positive controls LPS, TNF-α, and VOSO₄.