Searcharxiv⌕ Search

arXiv subjects

Wenjing Meng

Publications and source records attributed to Wenjing Meng.

3 recordsLinked to original sources

Modeling Risks with Masked Causes and Variable Exposure

Cohort studies and surveys often record how much time each subject spent under each of two or several treatment conditions and whether an event occurred, but not the condition under which it occurred. We develop two models for such data, for binary and count outcomes. Both start with events under each treatment condition as independent Poisson counts, and estimate rate ratios between treatment and control conditions. In the binary model, only an indicator of any event is observed, and the event probability under each condition follows a complementary log-log model with a log-exposure offset; development is done for general link functions, including log and logit. The interpretation of the treatment effect changes accordingly. In the count model, the number of events combined over all treatment conditions is observed; overdispersion is handled by Pearson scaling. Parameters are estimated either by the expectation-maximization algorithm or by direct maximization of the observed-data likelihood with Fisher scoring; standard errors are available via observed or expected information. When total exposure is common to all subjects, a relative slope summarizes the treatment effect and, unlike the rate ratio, does not depend on the assumed total exposure. In simulations, interval coverage was near nominal when enough events occurred during each treatment condition. The models are implemented in the R package maskcave. The work was motivated by the Adolescent Brain Cognitive Development study of 10,948 children. Assuming 16 waking hours per day, the adjusted sport-to-non-sport rate ratio for mild traumatic brain injury was 8.78 (95% confidence interval 4.47-17.27). We applied the count model to concussions during sports reported for 6,379 children at the Year 5 visit: the concussion rate per hour of football was 2.46 (1.37-4.43) times that of the other reported sports.

stat.ME↗

Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation

Session-based recommendation (SR) has become an important and popular component of various e-commerce platforms, which aims to predict the next interacted item based on a given session. Most of existing SR models only focus on exploiting the consecutive items in a session interacted by a certain user, to capture the transition pattern among the items. Although some of them have been proven effective, the following two insights are often neglected. First, a user's micro-behaviors, such as the manner in which the user locates an item, the activities that the user commits on an item (e.g., reading comments, adding to cart), offer fine-grained and deep understanding of the user's preference. Second, the item attributes, also known as item knowledge, provide side information to model the transition pattern among interacted items and alleviate the data sparsity problem. These insights motivate us to propose a novel SR model MKM-SR in this paper, which incorporates user Micro-behaviors and item Knowledge into Multi-task learning for Session-based Recommendation. Specifically, a given session is modeled on micro-behavior level in MKM-SR, i.e., with a sequence of item-operation pairs rather than a sequence of items, to capture the transition pattern in the session sufficiently. Furthermore, we propose a multi-task learning paradigm to involve learning knowledge embeddings which plays a role as an auxiliary task to promote the major task of SR. It enables our model to obtain better session representations, resulting in more precise SR recommendation results. The extensive evaluations on two benchmark datasets demonstrate MKM-SR's superiority over the state-of-the-art SR models, justifying the strategy of incorporating knowledge learning.

cs.IR↗

Investigating Safety Impacts of Roadway Network Features of Suburban Arterials in Shanghai, China

With the rapid changes in land use development along suburban arterials in Shanghai, there is also a corresponding increase in traffic demand along these arterials. With a preference toward increased accessibility and efficiency, these arterials have been installed with an increased number of signalized intersections and accesses to serve local traffic needs. The absence of a defined functional hierarchy along the road network, together with the non-uniform installation of signals and accesses tends to deteriorate arterial safety. Previous studies on arterial safety have generally been based on a single type of road entity (either intersection or roadway segment). These studies only analyzed partial safety impacts of signal spacing and access density, as these factors would significantly influence the safety performance of both intersections and roadway segments. Macro level safety modeling was usually applied to investigate the relationship between the zonal crash frequencies and demographics, road network features and traffic characteristics. In this study, a new modeling strategy was proposed to analyze the safety impacts of roadway network features (i.e., road network patterns, signal spacing and access density) of arterials by applying a macro level safety modeling technique. Bayesian Conditional Autoregressive models were developed for arterials covering 173 Traffic Analysis Zones in the suburban area in Shanghai. The results identified that the road network pattern with collector roads parallel to the arterials was shown to be associated with fewer crashes than those without parallel collectors. Higher signal density and access density also tended to increase crash frequencies on arterials.

stat.AP↗