Conversion rate (CVR) prediction is essential in recommender systems, facilitating precise matching between recommended items and users’ preferences. However, the sample selection bias (SSB) and data sparsity (DS) issues pose challenges to accurate ...

We propose an efficient boosting algorithm for multiclass classification, called AdaBoost.Iter, that extends SAMME and AdaBoost. The algorithm iteratively applies the weak learnability condition of SAMME to eliminate classes to find the correct ...

Malaria is a significant health concern worldwide, particularly in Africa where its prevalence is still alarmingly high. Using artificial intelligence algorithms to diagnose cells with malaria provides great convenience for clinicians. In this ...

Identifying electrical signatures preceding a ventricular arrhythmia from the implantable cardioverter-defibrillators (ICDs) can help predict an upcoming ICD shock. To achieve this, we first deployed a large-scale study (N=326) to continuously monitor ...

Multi-agent systems (MAS) based on reinforcement learning have shown impressive performance in complex tasks. However, they are still weak when it comes to addressing tasks without any samples. In this paper, we design a 2D ground and a 3D ...

• Device-edge-cloud collaboration architecture.
• Keyframe extraction of video streams, remove non-keyframes.
• Graphics compression and reconstruction algorithms.
• Extract the region of interest of the face.

The driver's emotional state directly affects safe driving. Under the "vehicle-human-road-cloud" integrated control framework, we propose an end-edge-cloud collaborative emotion perception network model (EEC-Net). The end side extracts the key ...

Display Omitted

As one of the prevalent topic mining methods, neural topic modeling has attracted a lot of interests due to the advantages of low training costs and strong generalisation abilities. However, the existing neural topic models may suffer ...

Aligning images is one of the main goals of image stitching. Limited by matching accuracy and deformability, the results of current mainstream stitching approaches in large parallax scenes usually contain obvious stitching errors. A misalignment-...

The advent of industry 4.0 has put forward higher requirements for flexible manufacturing. When work changes, the system has to be reprogrammed and the robot needs to follow a specific trajectory to finish the pick and place task. Therefore, it is urgent ...

Topic models have been widely used for learning the latent explainable representation of documents, but most of the existing approaches discover topics in a flat structure. In this study, we propose an effective hierarchical neural topic model ...

Research in the field of image super-resolution in recent years has shown that convolutional neural networks are conducive to improving the quality of image restoration. In the deep network, simply increasing the number of network layers cannot ...

Control of a robotic arm using a brain–computer interface (BCI) for reach and grasp activities is one of the most fascinating applications for some severely disabled people, which is especially challenging for the non-invasive BCIs ...

Blur measurement of partially blurred image is still far from being resolved. This calls for more distinctive blur features and, even more importantly, a global refinement strategy that has not been considered by existing studies. In this paper we ...

In this paper, we study the problem of distributed relay selection in wireless networks using a game theoretic approach. Specifically, we consider a system model where one relay node can be shared by multiple source-destination pairs. Our objective is ...

We introduce TeamGen, an interactive team formation system, to form project teams interactively by leveraging professional social network information of potential members. Unlike earlier approaches that focused on creating flat teams, i.e., teams ...

Based on matching game theory, this paper puts forward a novel-distributed relay-assignment approach to optimise the throughput satisfaction of source nodes, which is scarcely investigated in former works. The assignment problem is modelled as a matching ...

Chloroanilines are toxic substances listed as typical pollutants of the environment. The photolysis in sunlight is a possible route for it elimination. The photolysis rate constant of p-chloroaniline (p-CA) in pure water and in wetland soil (C) was ...

Growth condition of p-chloroaniline (p-CA) degrading Bacillus licheniformis named strain ycsd02 which was isolated from rhizosphere soil in phragmites wetland and stored in our labrary was studied. The result showed that the optimal culture temperature, ...

A bacterium(strain ycsd03) capable of growing with p-chlorophenol(p-CP) as sole carbon and energy sources was isolated from rhizosphere soil in phragmites wetland by using the enrichment culture contaminated with p-CP concentration gradient of 20, 40, ...

In natural attenuation processes, biological soil enzyme activities may change with time and the concentration of the contaminant(s) whose transformation were naturally catalyzed. Short-term irrigation in the laboratory was carried out to evaluate the ...