A review on the attention mechanism of deep learning

Community detection, aiming at determining correct affiliation of each node in a network, is a critical task of complex network analysis. Owing to its high efficiency, Symmetric and Non-negative Matrix Factorization (SNMF) is frequently adopted to handle this task. However, existing SNMF models mostly focus on a network's first-order topological information described by its adjacency matrix without considering the implicit associations among involved nodes. To address this issue, this study proposes a Pointwise mutual information-incorporated and Graph-regularized SNMF (PGS) model. It uses a) Pointwise Mutual Information to quantify implicit associations among nodes, thereby completing the missing but crucial information among critical nodes in a uniform way; b) graph-regularization to achieve precise representation of local topology, and c) SNMF to implement efficient community detection. Empirical studies on eight real-world social networks generated by industrial applications demonstrate that a PGS model achieves significantly higher accuracy gain in community detection than state-of-the-art community detectors.

Highly-Accurate Community Detection via Pointwise Mutual Information-Incorporated Symmetric Non-Negative Matrix Factorization

Technologies that accelerate the delivery of reliable battery-based energy storage will not only contribute to decarbonization such as transportation electrification, smart grid, but also strengthen the battery supply chain. As battery inevitably ages with time, losing its capacity to store charge and deliver it efficiently. This directly affects battery safety and efficiency, making related health management necessary. Recent advancements in automation science and engineering raised interest in AI-based solutions to prolong battery lifetime from both manufacturing and management perspectives. This paper aims at presenting a critical review of the state-of-the-art AI-based manufacturing and management strategies towards long lifetime battery. First, AI-based battery manufacturing and smart battery to benefit battery health are showcased. Then the most adopted AI solutions for battery life diagnostic including state-of-health estimation and ageing prediction are reviewed with a discussion of their advantages and drawbacks. Efforts through designing suitable AI solutions to enhance battery longevity are also presented. Finally, the main challenges involved and potential strategies in this field are suggested. This work will inform insights into the feasible, advanced AI for the health-conscious manufacturing, control and optimization of battery on different technology readiness levels. 

Towards Long Lifetime Battery: AI-Based Manufacturing and Management

Technologies that accelerate the delivery of reliable battery-based energy storage will not only contribute to decarbonization such as transportation electrification, smart grid, but also strengthen the battery supply chain. As battery inevitably ages with time, losing its capacity to store charge and deliver it efficiently. This directly affects battery safety and efficiency, making related health management necessary. Recent advancements in automation science and engineering raised interest in AI-based solutions to prolong battery lifetime from both manufacturing and management perspectives. This paper aims at presenting a critical review of the state-of-the-art AI-based manufacturing and management strategies towards long lifetime battery. First, AI-based battery manufacturing and smart battery to benefit battery health are showcased. Then the most adopted AI solutions for battery life diagnostic including state-of-health estimation and ageing prediction are reviewed with a discussion of their advantages and drawbacks. Efforts through designing suitable AI solutions to enhance battery longevity are also presented. Finally, the main challenges involved and potential strategies in this field are suggested. This work will inform insights into the feasible, advanced AI for the health-conscious manufacturing, control and optimization of battery on different technology readiness levels.

A comprehensive survey on robust image watermarking

High-dimensional and sparse (HiDS) matrices are frequently found in various industrial applications. A latent factor analysis (LFA) model is commonly adopted to extract useful knowledge from an HiDS matrix, whose parameter training mostly relies on a stochastic gradient descent (SGD) algorithm. However, an SGD-based LFA model's learning rate is hard to tune in real applications, making it vital to implement its self-adaptation. To address this critical issue, this study firstly investigates the evolution process of a particle swarm optimization algorithm with care, and then proposes to incorporate more dynamic information into it for avoiding accuracy loss caused by premature convergence without extra computation burden, thereby innovatively achieving a novel position-transitional particle swarm optimization (P2SO) algorithm. It is subsequently adopted to implement a P2SO-based LFA (PLFA) model that builds a learning rate swarm applied to the same group of LFs. Thus, a PLFA model implements highly efficient learning rate adaptation as well as represents an HiDS matrix precisely. Experimental results on four HiDS matrices emerging from real applications demonstrate that compared with an SGD-based LFA model, a PLFA model no longer suffers from a tedious and expensive tuning process of its learning rate to achieve higher prediction accuracy for missing data.

Position-Transitional Particle Swarm Optimization-incorporated Latent Factor Analysis

An adaptive latent factor model via particle swarm optimization

Background The adverse effects of 2.5-μm particulate matter (PM2.5) exposure on public health have become an increasing concern worldwide. However, epidemiological findings on the effects of PM2.5-bound metals on children's respiratory health are limited and inconsistent because PM2.5 is a complicated mixture. Objectives Given the vulnerability of children's respiratory system, aim to pediatric respiratory health, this study evaluated the potential sources, health risks, and acute health effects of ambient PM2.5-bound metals among children in Guangzhou, China from January 2017 to December 2019. Methods Potential sources of PM2.5-bound metals were detected using positive matrix factorization (PMF). A health risk assessment was conducted to investigate the inhalation risk of PM2.5-bound metals in children. The associations between PM2.5-bound metals and pediatric respiratory outpatient visits were examined with a quasi-Poisson generalized additive model (GAM). Results During 2017–2019, the daily mean concentrations of PM2.5 was 53.39 μg/m3, and the daily mean concentrations of PM2.5-bound metals range 0.03 ng/m3 [thorium (Th) and beryllium (Be)] from to 396.40 ng/m3 [iron (Fe)]. PM2.5-bound metals were mainly contributed by motor vehicles and street dust. PM2.5-bound arsenic (As), cadmium (Cd), cobalt (Co), chromium (Cr)(VI), nickel (Ni), and lead (Pb) were found to pose a carcinogenic risk (CR). A quasi-Poisson GAM was constructed that showed there were significant associations between PM2.5 concentrations and pediatric outpatient visits for respiratory diseases. PM2.5 was significantly associated with pediatric outpatient visits for respiratory diseases. Moreover, with a 10 μg/m3 increase in Ni, Cr(VI), Ni, and As concentrations, the corresponding pediatric outpatient visits for respiratory diseases increased by 2.89% (95% CI: 2.28–3.50%), acute upper respiratory infections (AURIs) increased by 2.74% (2.13–3.35%), influenza and pneumonia (FLU&PN) increased by 23.36% (20.09–26.72%), and acute lower respiratory infections (ALRIs) increased by 16.86% (15.16–18.60%), respectively. Conclusions Our findings showed that PM2.5 and PM2.5-bound As, Cd, Co, Cr(VI), Ni, and Pb had adverse effects on pediatric respiratory health during the study period. New strategies are required to decrease the production of PM2.5 and PM2.5-bound metals by motor vehicles and to reduce levels of street dust to reduce children's exposure to these pollutants and thereby increase child health.

/pdf/association-between-pm2-5-bound-metals-and-pediatric-306uq16e.pdf

Association between PM2.5-bound metals and pediatric respiratory health in Guangzhou: An ecological study investigating source, health risk, and effect

This study examined the short-term relationship between ambient air pollutants and children's outpatient visits, and identified the effect of modifications by season. Daily recordings of air pollutants (CO, NO2, O3, SO2, PM10, and PM2.5) and children's outpatient visit data were collected in Guangzhou from 2015 to 2019. A generalized additive model adjusted for potential confounding was introduced to verify the association between ambient air pollution and outpatient visits for children. Subgroup analysis by season was performed to evaluate the potential effects. A total of 5,483,014 children's outpatient visits were recorded. The results showed that a 10 μg/m3 increase in CO, NO2, O3, SO2, PM10, and PM2.5 corresponded with a 0.19% (95% CI: 0.15–0.24%), 2.46% (2.00–2.92%), 0.27% (0.07–0.46%), 7.16% (4.80–9.57%), 1.16% (0.83–1.49%), and 1.35% (0.88–1.82%) increase in children's outpatient visits on the lag0 of exposure, respectively. The relationships were stronger for O3, PM10, and PM2.5 in the warm seasons, and for CO, NO2, and SO2 in the cool seasons. When adjusting for the co-pollutants, the effects of CO, NO2, and PM10 were robust. The results of this study indicate that six air pollutants might increase the risk of children's outpatient visits in Guangzhou, China, especially in the cool season. Graphical Abstract

Sili Chen

Papers

Position-Transitional Particle Swarm Optimization-incorporated Latent Factor Analysis

An adaptive latent factor model via particle swarm optimization

Association between PM2.5-bound metals and pediatric respiratory health in Guangzhou: An ecological study investigating source, health risk, and effect

Short-term effect of ambient air pollution on outpatient visits for children in Guangzhou, China