Nadia Slimani

Time series forecasting is an important technique to study the behavior of temporal data in order to forecast the future values, which is widely applied in intelligent traffic systems (ITS). In this paper, several deep learning models were designed to deal with the multivariate time series forecasting problem for the purpose of long-term predicting traffic volume. Simulation results showed that the best forecasts are obtained with the use of two hidden long short-term memory (LSTM) layers: the first with 64 neurons and the second with 32 neurons. Over 93% of the forecasts were made with less than ±2.0% error. The analysis of variances is mainly due to peaks in some extreme conditions. For this purpose, the data was then merged between two different sources: electromagnetic loops and cameras. Data fusion is based on a calibration of the reliability of the sources according to the visibility conditions and time of the day. The integration results were then compared with the real data to prove the improvement of the prediction results in peak periods after the data fusion step.

The world is changing quite rapidly while increasingly tuning into digitalization. However, it is important to note that data science is what most technology is evolving around and data is definitely the future of everything. For industries, adopting a “data science approach” is no longer an option, it becomes an obligation in order to enhance their business rather than survive. This paper offers a roadmap for anyone interested in this research field or getting started with “machine learning” learning while enabling the reader to easily comprehend the key concepts behind. Indeed, it examines the benefits of automated machine learning systems, starting with defining machine learning vocabulary and basic concepts. Then, explaining how to, concretely, build up a machine learning model by highlighting the challenges related to data and algorithms. Finally, exposing a summary of two studies applying machine learning in two different fields, namely transportation for road traffic forecasting and supply chain management for demand prediction where the predictive performance of various models iscompared based on different metrics.

Although digital photos have the potential to improve the precision of reported portions in dietary assessment, there are few studies investigating its accuracy in comparison to printed photos. The aim of this study was to evaluate the perception of adults in quantifying food portion sizes using printed and digital photos, displayed on computer-screens and tablets. In total, 1165 evaluations were performed for 60 photos of portion sizes in Brazil. Each participant (n = 58) attended two sessions in the study center, with an interval of at least one week. In each session, twelve food portions were prepared and randomly evaluated by each participant in its printed and digital forms. The mean error (difference between the estimated and true portions) was not significantly different between the printed photos (2.1 g ± 47.2) and the digital ones (−6.4 g ± 53.7). The agreement on using the printed and digital photos was 91% and 90%, respectively. Furthermore, the use of the tablet was more prone to underestimation when compared to printed and computer-screen photos (p < 0.001). Overall, participants did not present major difficulties in perceiving the portion sizes using the printed and digital photos, but the use of tablets led to less accurate results, indicating that this needs to be further evaluated.

Background: Pancreatic cancer (PC) has an exceptionally high mortality rate due to late discovery and poor prognosis. The etiology of the cancer is largely unknown and primary prevention strategies are limited for this lethal cancer. Over the past years, evidence has been accumulated for folate which may play a role in carcinogenesis. Previous epidemiological studies, however, have shown inconsistent results in relation to PC risk with a weak inverse association with folate intake from foods, but not from supplements. The recent large study from the Pooling Project found no association between folate intake and PC risk. However, in the pooled analysis, folate data may be heterogeneous across studies and countries, thus not readily comparable. In the EPIC study, we obtained dietary folate intake data that was standardized across 10 participating countries using the EPIC Nutrient DataBase. Folic acid fortification or supplementation use was not common in Europe at the baseline data collection. We then set out to evaluate the association between total dietary folate intake and PC risk. Methods: A total of 477,245 participants without any history of cancer and with complete dietary folate information ascertained by food frequency questionnaire were followed up for 11 years, during which 904 first incident primary PC cases were recorded. Folate intake was energy-adjusted by using the residual method. Hazard Ratios (HRs) and 95% confidence intervals (CIs) were estimated using Cox proportional hazards models. Results: In multivariable analyses stratified by age, sex, study center and adjusted for smoking status, energy intake, BMI, educational level, diabetes status, supplement use and dietary fiber intake, we observed non-significantly decreased PC risk with higher folate intake: the HR of PC risk for those in the highest quartile of folate intake (≥353 μg/d) compared with the lowest quartile (Citation Format: Jin Young Park, H.B(as) Bueno-de-Mesquita, Pietro Ferrari, Paolo Vineis, Elisabete Weiderpass, Nadia Slimani, for the EPIC Study Group. Dietary folate intake and pancreatic cancer risk: Results from the European Prospective Investigation into Cancer and Nutrition. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 4811. doi:10.1158/1538-7445.AM2013-4811

This paper discusses whether baseline demographic, socio-economic, health variables, length of follow-up and method of contacting the participants predict non-response to the invitation for a second assessment of lifestyle factors and body weight in the European multi-center EPIC-PANACEA study. Over 500.000 participants from several centers in ten European countries recruited between 1992 and 2000 were contacted 2–11 years later to update data on lifestyle and body weight. Length of follow-up as well as the method of approaching differed between the collaborating study centers. Non-responders were compared with responders using multivariate logistic regression analyses. Overall response for the second assessment was high (81.6%). Compared to postal surveys, centers where the participants completed the questionnaire by phone attained a higher response. Response was also high in centers with a short follow-up period. Non-response was higher in participants who were male (odds ratio 1.09 (confidence interval 1.07; 1.11), aged under 40 years (1.96 (1.90; 2.02), living alone (1.40 (1.37; 1.43), less educated (1.35 (1.12; 1.19), of poorer health (1.33 (1.27; 1.39), reporting an unhealthy lifestyle and who had either a low (25, 1.08 (1.06; 1.10); especially ≥30 kg/m2, 1.26 (1.23; 1.29)). Cohort studies may enhance cohort maintenance by paying particular attention to the subgroups that are most unlikely to respond and by an active recruitment strategy using telephone interviews.

Whether there are differences between countries in the validity of self-reported diet in relation to BMI, as evaluated using recovery biomarkers, is not well understood. We aimed to evaluate BMI-related reporting errors on 24 h dietary recalls (24-HDR) and on dietary questionnaires (DQ) using biomarkers for protein and K intake and whether the BMI effect differs between six European countries. Between 1995 and 1999, 1086 men and women participating in the European Prospective Investigation into Cancer and Nutrition completed a single 24-HDR, a DQ and one 24 h urine collection. In regression analysis, controlling for age, sex, education and country, each unit (1 kg/m2) increase in BMI predicted an approximately 1·7 and 1·3 % increase in protein under-reporting on 24-HDR and DQ, respectively (both P < 0·0001). Exclusion of individuals who probably misreported energy intake attenuated BMI-related bias on both instruments. The BMI effect on protein under-reporting did not differ for men and women and neither between countries on both instruments as tested by interaction (all P>0·15). In women, but not in men, the DQ yielded higher mean intakes of protein that were closer to the biomarker-based measurements across BMI groups when compared with 24-HDR. Results for K were similar to those of protein, although BMI-related under-reporting of K was of a smaller magnitude, suggesting differential misreporting of foods. Under-reporting of protein and K appears to be predicted by BMI, but this effect may be driven by ‘low-energy reporters’. The BMI effect on under-reporting seems to be the same across countries.

Background/Objectives: Subjects/Methods: Results: Conclusions:

Background: To examine the association of education with body mass index (BMI) and waist circumference (WC) in the European Prospective Investigation into Cancer and Nutrition (EPIC). Method: This study included 141,230 male and 336,637 female EPIC-participants, who were recruited between 1992 and 2000. Education, which was assessed by questionnaire, was classified into four categories; BMI and WC, measured by trained personnel in most participating centers, were modeled as continuous dependent variables. Associations were estimated using multilevel mixed effects linear regression models. Results: Compared with the lowest education level, BMI and WC were significantly lower for all three higher education categories, which was consistent for all countries. Women with university degree had a 2.1 kg/m² lower BMI compared with women with lowest education level. For men, a statistically significant, but less pronounced difference was observed (1.3 kg/m²). The association between WC and education level was also of greater magnitude for women: compared with the lowest education level, average WC of women was lower by 5.2 cm for women in the highest category. For men the difference was 2.9 cm. Conclusion: In this European cohort, there is an inverse association between higher BMI as well as higher WC and lower education level. Public Health Programs that aim to reduce overweight and obesity should primarily focus on the lower educated population.

Scope: The objective was to perform an inventory and critical evaluation of folate data in selected European and international databases. The ultimate aim was to establish guidelines for compiling standardized folate databases for international nutritional studies. Methods and results: An ad hoc questionnaire was prepared to critically compare and evaluate folate data completeness, quantification, terminologies, and documentation of 18 European and international databases, and national fortification regulations. Selected countries participated in the European Prospective Investigation into Nutrition and Cancer project and European Food Information Resource Network (EuroFIR). Folate completeness was generally high. “Total folate” was the most common terminology and microbiological assay was the most frequently reported quantification method. There is a lack of comparability within and between databases due to a lack of value documentation, the use of generic or non‐appropriate terminologies, folate value conversions, and/or lack of identification of synthetic folic acid. Conclusion: Full value documentation and the use of EuroFIR component identifiers and/or INFOODS tagnames for total folate (“FOL”) and synthetic folic acid (“FOLAC”), with the additional use of individual folates, will increase comparability between databases. For now, the standardized microbiological assay for total folate and HPLC for synthetic folic acid are the recommended quantification methods.

Background: The single nucleotide polymorphism rs7566605, located in the promoter of the INSIG2 gene, has been the subject of a strong scientific effort aimed to elucidate its possible association with body mass index (BMI). The first report showing that rs7566605 could be associated with body fatness was a genome-wide association study (GWAS) which used BMI as the primary phenotype. Many follow-up studies sought to validate the association of rs7566605 with various markers of obesity, with several publications reporting inconsistent findings. BMI is considered to be one of the measures of choice to evaluate body fatness and there is evidence that body fatness is related with an increased risk of breast cancer (BC). Methods: we tested in a large-scale association study (3,973 women, including 1,269 invasive BC cases and 2,194 controls), nested within the EPIC cohort, the involvement of rs7566605 as predictor of BMI and BC risk. Results and Conclusions: In this study we were not able to find any statistically significant association between this SNP and BMI, nor did we find any significant association between the SNP and an increased risk of breast cancer overall and by subgroups of age, or menopausal status.