Predicting Carpark Prices Indices in Hong Kong Using AutoML

The aims of this study were threefold:1)study the research gap in carpark and price index via big data and natural language processing,2)examine the research gap of carpark indices,and 3)construct carpark price indices via repeat sales methods and predict carpark indices via the AutoML.By researching the keyword“carpark”in Google Scholar,the largest electronic academic database that coversWeb of Science and Scopus indexed articles,this study obtained 999 articles and book chapters from 1910 to 2019.It confirmed that most carpark research threw light on multi-storey carparks,management and ventilation systems,and reinforced concrete carparks.The most common research method was case studies.Regarding price index research,many previous studies focused on consumer,stock,press and futures,with many keywords being related to finance and economics.These indicated that there is no research predicting carpark price indices based on an AutoML approach.This study constructed repeat sales indices for 18 districts in Hong Kong by using 34,562 carpark transaction records from December 2009 to June 2019.Wanchai’s carpark price was about four times that of Yuen Long’s carpark price,indicating the considerable carpark price differences inHong Kong.This research evidenced the features that affected the carpark price indices models most:gold price ranked the first in all 19 models;oil price or Link stock price ranked second depending on the district,and carpark affordability ranked third.

Remote Sensing Data Processing Process Scheduling Based on Reinforcement Learning in Cloud Environment

Task scheduling plays a crucial role in cloud computing and is a key factor determining cloud computing performance.To solve the task scheduling problem for remote sensing data processing in cloud computing,this paper proposes a workflow task scheduling algorithm—Workflow Task Scheduling Algorithm based on Deep Reinforcement Learning(WDRL).The remote sensing data process modeling is transformed into a directed acyclic graph scheduling problem.Then,the algorithm is designed by establishing a Markov decision model and adopting a fitness calculation method.Finally,combine the advantages of reinforcement learning and deep neural networks to minimize make-time for remote sensing data processes from experience.The experiment is based on the development of CloudSim and Python and compares the change of completion time in the process of remote sensing data.The results showthat compared with several traditionalmeta-heuristic scheduling algorithms,WDRL can effectively achieve the goal of optimizing task scheduling efficiency.

Volunteering and Depression among Older Adults: An Empirical Analysis Based on CLASS 2018

Introduction:Older adults are prone to high levels of depression due to their deteriorating physical functions and shrinking social networks after retirement.Volunteering as an important social activity is essential for alleviating depression by building social network.This paper aims to examine the effect of volunteering on depression among older adults by using China Longitudinal Aging Social Survey(CLASS 2018)data.Methods:This study uses descriptive analysis and chi-square tests to show differences in demographic factors of older adults’volun-teerism participation,followed by bivariate correlation analysis to examine the correlation between the vital vari-ables.Afterward,stratified linear regression analysis is used to research the significant level and impact between volunteering and degree of expertise,frequency,and variety of participation.Results:8,459 older adults are included in study.The research reveals that older adults who are younger,live in urban areas,are married,or have a higher degree of education tend to have fewer depressive symptoms.Meanwhile,participation in volun-teering(OR=0.90,95%CI:0.8,1.1,p<0.001),as well as that demands specialized skills(OR=0.51,95%CI:0.30,0.2,p<0.001),more frequency of participation(OR=1.85,95%CI:1.53,2.18,p<0.001),and a wider variety of activities(OR=0.21,95%CI:0.12,0.29,p<0.001),all have a positive influence on depression levels.Discussion/Conclusion:Older adults who participate in voluntary services have lower depression symptoms and should be encouraged to use their professional skills and increase participation frequency and variety in this process.This article suggests that governments should help older adults participate in voluntary services by time bank which will further strengthen social ties,rebuild social networks and alleviate depression symptoms of older adults.

Do Research Incentives Promote Researchers’Mental Health?

Background:Researchers have a higher risk of anxiety and depression than the general population,so it is important to promote researchers’mental health.Method:Based on the data from 3210 global researchers surveyed by the journal Nature in 2021,confirmatory factor analysis,OLS regression and other regressions were used to explore the research incentive dimensions and their effects on researchers’mental health.Results:(1)Material incentive factors,work-family life balance factors,good organizational environment and spiritual motivation had significant positive effects on researchers’mental health.(2)The spiritual motivation could better promote researchers’mental health than the other factors.(3)Heterogeneity analysis showed that material incentive factors and spiritual motivation created more significant stimulating effects on the mental health of humanities and social sciences researchers.Work-family life balance factors were more effective in promoting the mental health of the mid-career group and the overtime group.Conclusion:Application of the four research incentives resulted in lower likelihood of anxiety or depression among researchers,and special attention should be paid to the role of the spiritual motivation.In order to promote researchers’mental health,different incentives should be applied to different researcher groups to better improve researchers’mental health.

Mu-Net:Multi-Path Upsampling Convolution Network for Medical Image Segmentation

Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.

Association between Self-Rated Health and Depressive Symptoms in Rural Chinese Adults:A Cohort Study Based on Propensity Score Matching

Health status is widely regarded as a correlate of depressive symptoms.However,health assessments based on clinical diagnosis in rural areas with poor medical conditions are very limited.Self-rated health(SRH)serves as a simple and convenient evaluation indicator,which may be used as an independent predictor of depressive symptoms.To confirm the relationship between SRH and depressive symptoms in rural adults,a longitudinal survey of rural households in China was conducted using the China Family Panel Studies(CFPS)from 2012 to 2016.Propensity score matching and logistic regression analysis were used to explore the association.After data cleansing,3,127 pairs(6,254 participants)aged 16 and older followed for 4 years were enrolled,of which the average age was(50.02±14.19)years old,and the proportions of male and female were 48.64%and 51.36%,respectively.The incidence rate of depressive symptoms within 4 years was 30.86%(95%CI:29.24–32.48)in the group with fair or poor SRH,and 21.59%(95%CI:20.14–23.03)in the group with good SRH.The difference between the two groups was statistically significant(χ^(2)=69.51,P<0.001).The results of univariate unconditional logistic regression analysis showed that there was a correlation between SRH and depressive symptoms in rural adults aged 30 and above(OR=1.65,95%CI:1.46–1.85,P<0.001).Thus,a simple and practical assessment tool based on SRH and other indicators should be established for early prevention and intervention in rural primary mental health care.

Wearing prediction of stellite alloys based on opposite degree algorithm

In order to predict the wearing of stellite alloys, the related methods of rare metals data processing were discussed. The method of opposite degree （OD） algorithm was put forward to predict the wearing of stellite alloys. OD algorithm is based on prior numerical data, posterior numerical data and the opposite degree between numerical forecast data. To compare the performance of predicted results based on different algorithms, the back propagation （BP） and radial basis function （RBF） neural network methods were introduced. Predicted results show that the relative error of OD algorithm is smaller than those of BP and RBF neural network methods. OD algorithm is an effective method to predict the wearing of stellite alloys and it can be applied in practice.