Search

BACKGROUND Depression has a high detection ratio among young adults, especially during the COVID-19 pandemic, which, however, occupies a low utilization of health services. Mental health chatbot is a novel digital technology to provide fully automated intervention for depression symptoms. OBJECTIVE The purpose of this study is to test the clinical effectiveness and nonclinical performance of the cognitive behavioral therapy (CBT)-based mental health chatbot (XiaoE) for young adults with depression symptoms during the COVID-19 pandemic. METHODS In a single-blind, three-arm, randomized controlled trial, participants manifesting depression symptoms aged 17-34 years recruited from a university in China were randomly assigned to mental health chatbot (XiaoE; n = 49), e-book (n = 49) or general chatbot (Xiaoai; n = 50), in a ratio of 1:1:1. The primary outcome was the reduction of depression symptoms according to the 9-item Patient Health Questionnaire (PHQ-9) at 1 week later (T1) and 1 month later (T2). Both intention-to-treat analyses and per-protocol analyses were conducted under analysis of covariance (ANCOVA) models adjusting for baseline data. Controlled multiple imputation and δ-based sensitivity analysis were performed for missing data. The secondary outcome was the level of working alliance measured using Working Alliance Questionnaire (WAQ), usability measured using the Usability Metric for User Experience-LITE (UMUX-LITE) and acceptability measured using Acceptability Scale (AS). RESULTS Intent-to-treat analysis revealed a moderate short-term effect of group diversity on the reduction of depression symptoms (PHQ-9) at T1 (F2, 136 = 17.011, P < .001, d = 0.51), while a light long-term effect at T2 (F2, 136 = 5.477, P= .005, d = 0.31). Better working alliance (WAQ, F2, 145 = 3.407, P = .036) and acceptability (AS, F2, 145 = 4.322, P = .015) was discovered with XiaoE, while no significant difference among arms was found on usability (UMUX-LITE, F2, 145 = 0.968, P = .382). CONCLUSIONS This novel intervention conducting CBT provides a feasible and engaging digital therapeutic that allows easy accessibility and self-guided mental health assistance for young adults with depression symptoms. A systematic evaluation of nonclinical metrics for mental health chatbot is established in this study. In the future, concern with both clinical outcomes and nonclinical metrics is necessary to explore the mechanism by which the mental health chatbots work on patients. Further evidence is required to confirm the long-term effectiveness via trails replicated with a longer dose as well as exploration on its stronger efficacy in comparison with other active controls. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR2100052532; http://www.chictr.org.cn/showproj.aspx?proj=135744.

Background Depression has a high prevalence among young adults, especially during the COVID-19 pandemic. However, mental health services remain scarce and underutilized worldwide. Mental health chatbots are a novel digital technology to provide fully automated interventions for depressive symptoms. Objective The purpose of this study was to test the clinical effectiveness and nonclinical performance of a cognitive behavioral therapy (CBT)–based mental health chatbot (XiaoE) for young adults with depressive symptoms during the COVID-19 pandemic. Methods In a single-blind, 3-arm randomized controlled trial, participants manifesting depressive symptoms recruited from a Chinese university were randomly assigned to a mental health chatbot (XiaoE; n=49), an e-book (n=49), or a general chatbot (Xiaoai; n=50) group in a ratio of 1:1:1. Participants received a 1-week intervention. The primary outcome was the reduction of depressive symptoms according to the 9-item Patient Health Questionnaire (PHQ-9) at 1 week later (T1) and 1 month later (T2). Both intention-to-treat and per-protocol analyses were conducted under analysis of covariance models adjusting for baseline data. Controlled multiple imputation and δ-based sensitivity analysis were performed for missing data. The secondary outcomes were the level of working alliance measured using the Working Alliance Questionnaire (WAQ), usability measured using the Usability Metric for User Experience-LITE (UMUX-LITE), and acceptability measured using the Acceptability Scale (AS). Results Participants were on average 18.78 years old, and 37.2% (55/148) were female. The mean baseline PHQ-9 score was 10.02 (SD 3.18; range 2-19). Intention-to-treat analysis revealed lower PHQ-9 scores among participants in the XiaoE group compared with participants in the e-book group and Xiaoai group at both T1 (F2,136=17.011; P Conclusions A CBT-based chatbot is a feasible and engaging digital therapeutic approach that allows easy accessibility and self-guided mental health assistance for young adults with depressive symptoms. A systematic evaluation of nonclinical metrics for a mental health chatbot has been established in this study. In the future, focus on both clinical outcomes and nonclinical metrics is necessary to explore the mechanism by which mental health chatbots work on patients. Further evidence is required to confirm the long-term effectiveness of the mental health chatbot via trails replicated with a longer dose, as well as exploration of its stronger efficacy in comparison with other active controls. Trial Registration Chinese Clinical Trial Registry ChiCTR2100052532; http://www.chictr.org.cn/showproj.aspx?proj=135744

Pine seedlings exhibit heteroblastic foliage (primary and secondary needles) during seedling development. However, few trials have studied how heteroblastic foliage influences pine seedling growth by seasonal variation. This study first investigated the anatomical differences between the primary and secondary needles of one-year-old Pinus massoniana seedlings. We measured chlorophyll fluorescence (ChlF) and evaluated the photoprotective mechanisms and light energy partitioning of these heteroblastic leaves from September to November. The results showed that the primary needles, as juvenile foliage, had a greater fraction of mesophyll tissue and stomata. In addition, the primary needles had two vascular bundles, and shorter distance from xylem and phloem to mesophyll cells, exhibiting a luxury growth strategy of rapidly obtaining high returns. The ChlF parameters indicated that the primary needles maintained a relatively high level of photoprotection by thermal dissipation (nonphotochemical quenching (NPQ)) and nonregulated energy dissipation (Y(NO)). The secondary needles, representing mature foliage, had greater area of xylem and phloem tissues. The contents of Chl b and carotenoids (Car) significantly increased in November, promoting φPo and photoprotection, which suggested that the secondary needles were more resistant to low temperatures. During the whole light response process of secondary needles, the increases in the electron transfer rate (ETR) and light energy utilization efficiency (α) helped to increase the actual photosynthetic quantum yield (Y(II)) by reducing energy dissipation by decreasing the proportion of regulated energy dissipation (Y(NPQ)) and Y(NO). Given the sensitivity of this heteroblastic foliage to environmental changes, the practical use and extension of P. massoniana for afforestation purposes should be carried out with caution.

As one of the largest B2C e-commerce platforms in China, JD.com also powers a leading advertising system, serving millions of advertisers with fingertip connection to hundreds of millions of customers. In our system, as well as most e-commerce scenarios, ads are displayed with images. This makes visual-aware Click Through Rate (CTR) prediction of crucial importance to both business effectiveness and user experience. Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR. Despite being extensively studied, this field still face two key challenges. First, although encouraging progress has been made in offline studies, applying CNNs in real systems remains non-trivial, due to the strict requirements for efficient end-to-end training and low-latency online serving. Second, the off-the-shelf CNNs and late fusion architectures are suboptimal. Specifically, off-the-shelf CNNs were designed for classification thus never take categories as input features. While in e-commerce, categories are precisely labeled and contain abundant visual priors that will help the visual modeling. Unaware of the ad category, these CNNs may extract some unnecessary category-unrelated features, wasting CNN's limited expression ability. To overcome the two challenges, we propose Category-specific CNN (CSCNN) specially for CTR prediction. CSCNN early incorporates the category knowledge with a light-weighted attention-module on each convolutional layer. This enables CSCNN to extract expressive category-specific visual patterns that benefit the CTR prediction. Offline experiments on benchmark and a 10 billion scale real production dataset from JD, together with an Online A/B test show that CSCNN outperforms all compared state-of-the-art algorithms. We also build a highly efficient infrastructure to accomplish end-to-end training with CNN on the 10 billion scale real production dataset within 24 hours, and meet the low latency requirements of online system (20ms on CPU). CSCNN is now deployed in the search advertising system of JD, serving the main traffic of hundreds of millions of active users.

The preventive monitoring and sustainable conservation of large-scale cultural heritage sites require satellite-based Earth observations. In this study, we present the first monitoring and thematic mapping results of the Badaling Great Wall (Beijing, China) using deformation indicators calculated from very high-resolution (VHR) multi-temporal spotlight TerraSAR-X data. The proposed coarse–fine search algorithm achieved high computational efficiency for calculating the unknown parameters of the two-tier network persistent scatterer synthetic aperture radar (SAR) interferometry (PSInSAR) approach. The spatiotemporal deformation anomalies, characterized by the absolute velocity, deformation deviation and acceleration, are informative to identify suspected hotspots for prioritizing monitoring activities. We provide an understandable method for thematic mapping and subsequent sustainable conservation of heritage sites by synergistically exploiting impacts from natural degradation and the tourism industry. We determine that the optimum tourist capacity of the site could be 1.0 million per month based on comparing pre- and post-COVID data (2019–2020). This study demonstrates the potential and performance of spaceborne PSInSAR tools for the intelligent management of large-scale architectural heritage sites by integrating InSAR deformation products with environmental and social data.

A highly automated methodology is described to map locations and heights of high-rise buildings from single high-resolution multi-spectral satellite imagery. The approach involves preliminary shadow detection using the Tsai colour invariant transform and scale space processing to identify candidate building pixels. Application of shadow-building and shadow length constraints led to mapping of the location and height of building candidate objects. The approach has been applied to a winter SPOT 5 scene of Beijing, China. Tests of buildings in a suburban area indicate that a high detection rate (93%) can be achieved for buildings taller than 28 m. A height estimation accuracy of 20 m has also been met for these buildings.

Airborne light detection and range (LiDAR) with three-dimensional product acquisition capabilities has become an important research hot spot. The classification and information extraction of LiDAR were usually carried out with other earth observation (EO) data (VIR/SAR, spaceborne/airborne). However, if these EO data are not always available, a particularly interesting possibility is to use only the products of LiDAR including the digital elevation model, the digital surface model and the intensity image. In this article, at the study site of Beauport, around Lac-Saint-Charles, Quebec, Canada, only airborne LiDAR products are applied to realise land cover interpretation and classification. A two-hierarchy decision-tree classification is suggested and carried out. Six land cover classes are extracted, including water bodies, bare soils, impervious areas, vegetation, buildings and high-voltage electric wires. All the reference and checking data are based on 1:20,000 topographic map of Quebec. According to t...

In this paper, we show that the fractal transform (FT) constitutes a multiresolution approximation to the square-integrable space L2(Td) for d≥1, where T is the interval (-∞,∞). This provides a theoretical basis for the successful applications of the fractal transform algorithms in signal/image encoding. There are many similarities between fractal-based and wavelet-based approximations. However, they are undamentally different from each other in many aspects. Fractal-based multiresolution approximation to signals/images is by a way of self-increasing model complexity, and wavelet-based multiresolution approximation to signals/images is by a way of decomposing data complexity into single (time domain) components.

The urban terrain surface is much more complex to build than mountainous regions-discontinuous, easily covered by other objects as there are high density settlements in urban area. The feature datasets in topographic databases, usually acquired and updated both by photogrammetry and field work, are helpful to build the urban terrain surface. So in the paper, a workflow of urban feature extraction and terrain build with large scale topographic databases was proposed and designed. The two dimension (2D) buildings, road and water body features were extracted from the databases with three dimension (3D) terrain features, a elevation assignment and interpolation method was presented to construct the discontinuous urban terrain surface, the relative sub-modules including feature extraction, elevation points editing, 2D to 3D, elevation interpolation and checking were developed and introduced. At last, based on the urban flood disaster analysis requirements, an experiment was carried out to verify the feasibility of this workflow and the method.

The discovery of new safe and effective pesticides is one of the main means of providing eco-friendly agricultural agents for modern crop protection. To identify new biological molecules based of the anthranilic diamide skeleton of the novel pesticide chlorantraniliprole, which acts on the ryanodine receptor and functional groups in acyl hydrazine insect growth regulators, more than 40 new compounds of 2-acylamino-substituted N'-benzylbenzohydrazide derivatives were designed and synthesized. The structures of the new compounds were characterized using (1)H nuclear magnetic resonance (NMR), high-resolution mass spectrometry (HRMS), or electron impact mass spectrometry (EI-MS), and their biological activities at a concentration of 600 mg L(-1) were determined against cotton aphid (Aphis gossypii Glover), carmine spider mite (Tetranychus cinnabarinus), and diamondback moth (Plutella xylostella). The results of a preliminary assay showed that compounds 6a-I-2 and 6d-III-4 maintained the lethal activity of anthranilic diamide against P. xylostella; compounds 6c-II-4, 6d-I-7, 6d-II-1, and 6d-III-5 exhibited good lethal activity against A. gossypii; and compounds 6a-II-1, 6a-III-1, 6b-I-7, 6c-I-1, and 6c-III-5 retained promising larvicidal activities against T. cinnabarinus. In subsequent further tests against T. cinnabarinus, compounds 6a-II-1, 6a-III-1, 6c-I-1, and 6c-III-5 showed an LC(50) value of

Three dimensional (3D) information acquisitions is one of the advantages of airborne Light Detection and Range (LiDAR) as interpretation data sources and the relative classification and feature extraction algorithms based on the point cloud height are developed. In this paper, in the study site of Lac-Saint-Charles, Quebec, Canada, the 3D accuracy of the airborne LiDAR products, including digital elevation model (DEM), digital surface model (DSM) and intensity image, are evaluated with differential GPS (dGPS) data. An object-oriented interpretation and classification work flow with these products is proposed and carried out: terrain group and up-terrain group are acquired based on the digital height model (DHM) and accuracy assessment result with dGPS data, five different classes including water body, impervious areas, bare soil, vegetation and building are separated based on a multi-window homogeneity Maximum Likelihood Supervised (MLS) classification. Based on accuracy statistics with 965 independent checked data, the final classification result and experimental accuracy analysis demonstrated an efficient attempt in land cover classification with airborne LiDAR products.

High accurate airborne Light Detection and Range (LiDAR) is widely accepted as one kind of survey data sources. However, with the LiDAR products including Digital Elevation Model (DEM), Digital Surface Model (DSM) and intensity image, land use classifications and feature extractions were generally combined with optical images including satellite images or aerial photos using relative segmentations and feature extraction algorithms. In this paper, a multi-window texture classification and object-oriented feature extraction method is proposed using only airborne LiDAR products. Based on the experimental analysis and accuracy statistics, it is an efficient attempt in land cover classification with airborne LiDAR products.

As environment pollution and health problem became more and more seriously concerned, the electronic packaging industry is facing the challenge of changeover to "green", using the lead-free solder alloy is the trend instead of the traditional 63Sn/37Pb solder. In this paper, a PCB-level drop test for BGA package will be introduced and the mechanism of the solder joint mechanical fatigue failure will be discussed in detail, in order to find out the relevant failure root causes. In addition, comparing the difference between the solder joint performance of lead-free and PbSn BGA package, the reliability of the lead-free one can be evaluated and a feedback link to the lead-free material selections and processing parameters improving will be provided

Image fusion technique has been widely applied to remote sensing image analysis and processing, and methods for quality assessment of image fusion in remote sensing have also become the research issues at home and abroad. Traditional assessment methods combine calculation of quantitative indexes and visual interpretation to compare fused images quantificationally and qualitatively. However, in the existing assessment methods, there are two defects: on one hand, most imdexes lack the theoretic support to compare different fusion methods. On the hand, there is not a uniform preference for most of the quantitative assessment indexes when they are applied to estimate the fusion effects. That is, the spatial resolution and spectral feature could not be analyzed synchronously by these indexes and there is not a general method to unify the spatial and spectral feature assessment. So in this paper, on the basis of the approximate general model of four traditional fusion methods, including Intensity Hue Saturation(IHS) triangle transform fusion, High Pass Filter(HPF) fusion, Principal Component Analysis(PCA) fusion, Wavelet Transform(WT) fusion, a correlation coefficient assessment method based on IHS cylindrical transform is proposed. By experiments, this method can not only get the evaluation results of spatial and spectral features on the basis of uniform preference, but also can acquire the comparison between fusion image sources and fused images, and acquire differences among fusion methods. Compared with the traditional assessment methods, the new methods is more intuitionistic, and in accord with subjective estimation.

An empirical analysis of the login datum of fitness club membership over the past 27 months is implemented, which shows that the interval time distribution of their logins presents obvious power-law properties whether all members, groups or individuals. And the scaling indexes of groups are different and linked with their level of activity. Studies on a certain time further reveal that the statistical characteristics of the same community can not be affected by the length of time. Moreover, the power exponents of individuals are also diverse. A conclusion is given to show that the scaling indexes of interval time distribution is dynamically influenced by the level of activity. Finally, by introducing the interest factor and time threshold parameters into the model, human dynamics model based on habit are obtained in order to explore the production mechanism of exercise behaviour of individuals.

Current empirical results of human dynamics based on temporal characteristics are discussed. By collecting communications data from Sui Gu and Van Gogh, the inter-event time distribution is found to fit a power law with exponent 1.5, which is in accordance with Barabasi’s conclusion. Moreover, it shows that the inter-event time distribution about two men’s letters for five consecutive years also follows power law distribution with the same exponent. Finally, some simulations are given to show the effectiveness.

To generate a fractal by using an iterated function system (IFS) (Barnsley, 1988) is a very efficient and economic way. This led Barnsley to suggest the use of IFSs for data compression. However, the attractor of an IFS is self-affine but real data are not always self-affine. The real break-through for this problem was made in 1988 by Barnsley (Barnsley and Hurd, 1993) who generalized IFS to local IFS which resulted in so-called fractal transform (FT) for the iteration of functions. The coding of real data by fractal transform has generally achieved high-compression ratio with high-fidelity to the data.