In urban vehicular ad hoc networks (VANETs), due to the high mobility and uneven distribution of vehicles, how to select an optimal relaying node in an intra-street and how to determine a street selection at the intersection are two challenging issues in designing an efficient routing protocol in complex urban environments. In this paper, we build a link model with a Wiener process to predict the probability of link availability, which considers the stable and unstable vehicle states according to the behavior of vehicles. We introduce a novel concept called the link correlation which represents the influence of different link combinations in network topology to transmit a packet with less network resource consumption and higher goodput. Based on this concept, we design an opportunistic routing metric called the expected transmission cost over a multi-hop path (ETCoP) implemented with our link model as the selection guidance of a relaying node in intra-streets. This metric can also provide assistance for the next street selection at an intersection. Finally, we propose a street-centric opportunistic routing protocol based on ETCoP for VANETs (SRPE). Simulation results show that our proposed SRPE outperforms the conventional protocols in terms of packet delivery ratio, average end-to-end delay, and network yield.

In a vehicular ad hoc network (VANET), high mobility and uneven distribution of vehicles are important factors affecting the performance of routing protocols. The high mobility may cause frequent changes of network topology, whereas the uneven distribution of vehicles may lead to routing failures due to network partition; even high density of vehicles may cause severe wireless channel contentions in an urban environment. In this paper, we propose a novel concept called the microtopology (MT), which consists of vehicles and wireless links among vehicles along a street as a basic component of routing paths and even the entire network topology. We abstract the MT model reflecting the dynamic routing-related characteristics in practical urban scenarios along streets, including the effect of mobility of vehicles, signal fading, wireless channel contention, and existing data traffic. We first analyze the endside-to-endside routing performance in an MT as a basis of routing decision. Then, we propose a novel street-centric routing protocol based on MT (SRPMT) along the streets for VANETs. Simulation results show that our proposed SRPMT protocol achieves higher data delivery rate and shorter average end-to-end delay compared with the performance of greedy perimeter stateless routing (GPSR) and greedy traffic-aware routing (GyTAR).

With the rise of online advertising, e-commerce industries, and new media platforms, recommendation systems have become an essential product form that connects users with a vast number of candidates. A major challenge in recommendation systems is the cold-start problem, where the absence of historical interaction data for new users and items leads to poor recommendation performance. We first analyze the causes of the cold-start problem, highlighting the limitations of existing embedding models when faced with a lack of interaction data. To address this, we classify the features of models into three categories, leveraging the Trans Block mapping to transfer features into the semantic space of missing features. Then, we propose a model-agnostic industrial framework (MAIF) with the Auto-Selection serving mechanism to address the cold-start recommendation problem in few-shot and zero-shot scenarios without requiring training from scratch. This framework can be applied to various online models without altering the prediction for warm entities, effectively avoiding the “seesaw phenomenon” between cold and warm entities. It improves prediction accuracy and calibration performance in three cold-start scenarios of recommendation systems. Finally, both the offline experiments on real-world industrial datasets and the online advertising system on the Dazhong Dianping app validate the effectiveness of our approach, showing significant improvements in recommendation performance for cold-start scenarios.

Palmprint recognition is a challenging task due to the variability in image quality, scale, and angle. Traditional methods often rely on single line features, which may not effectively capture the local bifurcation information critical for accurate recognition. To address these challenges, this paper proposes the Bifurcation Line Direction Coding (BLDC) method, which better captures the local bifurcation characteristics of palmprint images. Our approach leverages an improved Gabor filter for image preprocessing, where the main direction guides the branch direction. By considering both the maximum and minimum direction subscripts of the main direction, we generate robust feature codes that accurately represent the palmprint’s unique structure. Extensive experiments across five challenging palmprint datasets demonstrate that BLDC outperforms existing methods in recognition rate and feature extraction speed, providing a more effective solution for palmprint recognition in practical applications.