In event-based social networks, such as Meetup, groups refer to self-organized communities that consist of users who share the same interests. many real-world scenarios, usually have group preference and join interested attend events. It is therefore necessary consider influence improve event recommendation performance; however, existing models generally users' individual preferences neglect groups. To this end, we propose a new Bayesian latent factor model SogBmf combines for...

Most of current network representation models are learned in unsupervised fashions, which usually lack the capability discrimination when applied to analysis tasks, such as node classification. It is worth noting that label information valuable for learning discriminative representations. However, labels all training nodes always difficult or expensive obtain and manually labeling inapplicable. Different sets labeled model lead different results. In this paper, we propose a novel method,...

Network embedding has been recently used in social network recommendations by low-dimensional representations of items for recommendation. However, existing item recommendation models networks suffer from two limitations. First, these partially use information and mostly ignore important contextual such as textual content tag information. Second, are learned independent steps without any interaction. To this end, we paper consider based on heterogeneous sources. Specifically, combine...

Ultra-high-performance concrete (UHPC) has attracted much attention in civil engineering. However, the high deadweight of UHPC limits its application. To reduce density UHPC, this study developed an ultra-high-performance lightweight (UHPLC) by combining use shale ceramic sand and nano-materials, according to modified Andreasen Andersen (MAA) model. Taking advantage nanotechnology, graphene oxide (GO) was utilized improve mechanical performance UHPLC, effects GO on workability, properties,...

Studying climate change’s impact on vegetation canopy growth and senescence is significant for understanding predicting dynamics. However, there a lack of adequate research changes across the lifecycles different types. Using GLASS LAI (leaf area index) data (2001–2020), we investigated development (April–June), maturity (July–August), (September–October) rates in Northeast China, focusing their responses to preseason climatic factors. We identified that early stages saw acceleration, with...

The leaf area index (LAI) serves as a significant vegetation growth indicator and plays an essential role in vegetation's feedback to climate change. Currently, artificial intelligence (e.g., deep learning) algorithms possess strong capabilities constructing complex relationships demonstrate successful integration with remote sensing for LAI inversion. Among these algorithms, the long short-term memory (LSTM) network excels handling sequence data features multi-layer nonlinear structure that...

In many time-aware item recommender systems, modeling the accurate evolution of both user profiles and contents items over time is essential. However, most existing methods focus on learning users' dynamic interests, where are assumed to be stable time. They thus fail capture changes in item's contents. this paper, we present a novel method CDUE for recommendation, which captures user's interests information via topic dynamics. Specifically, propose sparse model track topics items' adapt...

Rare earth elements (REEs) that are key to new technologies and green innovations critical life in modern societies. China continues dominate the global REEs market despite several international trade disputes fluctuations. Pressured by an increasingly difficult situation, Chinese government has been carrying out industry restructuring introduced regulatory reforms recent years promote healthy development of rare industry. This paper reviews literature on analyzes reform policies, combining...

Ultra-high-performance concrete (UHPC) has promising applications in civil engineering. However, the elastic modulus of UHPC is relatively low compared with its compressive strength, which may result insufficient stiffness service. This work was carried out to explore feasibility producing high by nano-Al2O3 (NA). Based on particle densely packing theory, initial mixture designed via modified Andreasen and Andersen model. An experimental investigation conducted systematically examine effects...

The recommender system is of great significance to alleviate information overload. rise online social networks leads a promising direction—social recommendation. By injecting the interaction influence among users, recommendation performance has been further improved. Successful as they are, we argue that most methods are still not sufficient make full use network information. Existing solutions typically either considered only local neighbors or treat neighbors' equally, even both. However,...

The brushless DC motor (BLDCM) will be suffered the impact of chaos at certain conditions. Therefore, This paper proposes a nonlinear state control method to suppress and emergence chaotic motion based on Lyapunov stability theory. Firstly, We analyze dynamic characteristics equation BLDCM system, prove that it appear phenomenon some parameters. Finally, feedback controller is designed theory, proved can make system asymptotically stable equilibrium point. And further, simulation results are...

The combination of relay system and orthogonal frequency division multiplexing (OFDM) modulation is a promising way to increase capacity coverage area. We consider several joint subcarrier matching power allocation schemes maximize channel capacity, where the strategy decode-and-forward. formulate optimally problem as an optimization problem, which prohibitive in terms complexity. By separating allocation, with low complexity are proposed. proposed scheme 1 close upper bound very 2 higher...

With the extensive inclusion of document, especially text, in business systems, data mining does not cover full scope Business Intelligence. Data cannot deliver its impact on extracting useful details from large collection unstructured and semi-structured written materials based natural languages. The most pressing issue is to draw potential intelligence text. In order gain competitive advantages for business, it necessary develop new powerful tool, text mining, expand intelligence. this...

This paper concentrates on the quaternion-based attitude synchronisation problems of networked rigid bodies under fixed and undirected communication topology without relative angular measurements in presence actuator saturation. We first consider leaderless problem with zero final velocity. In this case, we not only discuss performance acyclic proposed bounded control algorithm, but also analyse that if there exist cycles topology, algorithm guarantees all equilibrium points are unstable...

This paper proposes a novel automatic image-segmentation system, which improves the traditional marker-based watershed transform. A new marker-extracted approach is proposed to extract regional minima from low frequency components in gradient map. The extracted constitute binary marker image. Then original map modified by suppressing its all-intrinsic around these markers. Thus, compared with approach, both spurious are more effectively removed and meanwhile boundaries of objects protected....

H.264 adopts variable block size motion estimation and rate-distortion-optimization based mode decision to improve video quality compression ratio. These techniques have made better than other existing coding standards. However, they are computationally intensive time-consuming. In this paper, a fast selection scheme is proposed for inter prediction. Firstly, the first few frames encoded thresholds acquired through statistical learning process. Then, rest of frames, only performed candidate...