Search

Cloud computing provides scalable and elastic resources to customers as a low-cost, on-demand utility service. Multivariate time series anomaly detection is crucial to promise the overall performance of cloud computing systems. However, due to the complexity and high dynamics of cloud environments, anomaly detections caused by irre gular fluctuations in data and the robustness of models are a challenge. To address these issues, we propose a deep learning-based anomaly detection method for multivariate time series for real-world operational clouds: Correlative-GNN with Multi-Head Self-Attention and Auto-Regression Ensemble Method (CGNNMHSA- AR). Our method utilizes two parallel graph neural networks (GNN) to learn the time and feature inter-dependencies to achieve fewer false positives. Our approach leverages a multi-head self-attention, GRU, and AR model to capture multipledimensional information, leading to better detection robustness. CGNN-MHSA-AR can also provide an abnormal explanation based on the prediction error of its constituent univariate series. We compare the detection performance of CGNN-MHSA-AR with seven baseline methods on seven public datasets. The evaluation shows that the proposed CGNN-MHSA-AR outperforms its competitors with an F1-Score of 0.871 on average and is 19.9% better than state-of-the-art baseline methods. In addition, CGNN-MHSA-AR also offers to correctly identify the root cause of detected anomalies with up to 74.1% accuracy.

Juan Chen,1,* Qiqiang Liang,1,* Shuo Ding,1 Yongshan Xu,1 Yanting Hu,1 Jingyu Chen,2,3 Man Huang1,3 1Department of General Intensive Care Unit, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, People’s Republic of China; 2Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, Jiangsu, People’s Republic of China; 3Department of Lung Transplantation, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, People’s Republic of China*These authors contributed equally to this workCorrespondence: Man Huang, Department of General Intensive Care Unit, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, People’s Republic of China, Tel/Fax +86 571 89713427, Email huangman@zju.edu.cn Jingyu Chen, Wuxi Lung Transplant Center, Wuxi People’s Hospital affiliated to Nanjing Medical University, Wuxi, Jiangsu, People’s Republic of China, Email chenjy@wuxiph.comBackground: Experience of ceftazidime-avibactam (CAZ/AVI) for carbapenem-resistant Pseudomonas aeruginosa (CRPA) infection in recipients after lung transplantation (LT) is relatively limited.Methods: A retrospective observational study was conducted on lung transplant recipients receiving CAZ/AVI therapy for CRPA infection. The primary outcomes were the 14-day and 30-day mortality. The secondary outcomes were clinical cure and microbiological cure.Results: Among 183 LT recipients, a total of 15 recipients with CRPA infection who received CAZ/AVI therapy were enrolled in this study. The mean age of recipients was 54 years and 73.3% of recipients were male. The median time from infection onset to initiation of CAZ/AVI treatment was 4 days (IQR, 3– 7) and the mean duration of CAZ/AVI therapy was 10 days. CAZ/AVI was mainly administered as monotherapy in LT recipients (80%). Among these eligible recipients, 14-day and 30-day mortality were 6.7% and 13.3%, respectively. The clinical cure and microbiological cure rates of CAZ/AVI therapy were 53.3% and 60%, respectively. Three recipients (20%) experienced recurrent infection. In addition, the mean lengths of ICU stay and hospital stay were 24 days and 35 days, respectively, among LT recipients.Conclusion: CAZ/AVI may be an alternative and promising regimen for CRPA eradiation in lung transplant recipients.Keywords: carbapenem-resistantPseudomonas aeruginosa, ceftazidime/avibactam, lung transplantation, infection, efficacy, mortality

Purpose This study aims to investigate how high-speed railway (HSR) development affects urban construction investment (UCI) bond yield spreads based on China’s background. Design/methodology/approach This study constructs a quasi-natural experiment and adopts regression analyses to empirically examine the relation between HSR development and UCI bond yield spreads. The empirical analysis is based on a Chinese sample of 15,109 bond offering observations from 2008 to 2019. Findings The results show that HSR development reduces UCI bond yield spreads. Mechanistic analysis shows that HSR development increases land prices and the level of urbanization, which in turn lowers the UCI bond yield spreads. In addition, the impact of HSR development on UCI bond yield spreads is more significant at higher marketization levels and lower degrees of dependence on land finance cities where UCI corporations are located. Research limitations/implications The results imply that transportation infrastructure improvement, such as HSR development, helps to enhance the credit of local governments and the solvency of UCI corporations and ultimately reduces the financing cost of UCI bonds. Originality/value This paper provides theoretical support and empirical evidence for the impact of transportation infrastructure construction on the implicit debt risks of local governments in China, which enriches the research on the “HSR economy” from a micro perspective and expands the research on the influencing factors of local governments’ debt risk.

Chromosomal abnormalities are a common cause of spontaneous abortions, but conventional detection methods (karyotype, FISH, and chromosomal microarray [CMA]) have limitations, and many cryptic balanced chromosomal rearrangements are difficult to detect. We describe a couple who experienced a missed abortion, studied by CMA. CMA of the abortion tissue detected a 1.62-Mb duplication at 14q11.2 and a 5.09-Mb deletion at 21q11.2q21.1, while the couple seemed to have a normal karyotype. Combining the results of CMA, whole-genome sequencing (WGS) breakpoint analysis, Sanger sequencing, and FISH, we found that the father was a 46,XY,t(14;21)(q11.2;q21.1) balanced translocation carrier. Our results indicate that WGS is an efficient and accurate approach to map breakpoints of cryptic reciprocal balanced translocations undetectable by standard karyotype.

Background: The small sample problem widely exists in the fields of the chemical in-dustry, chemistry, biology, medicine, and food industry. It has been a problem in process modeling and system optimization. The aim of this study is to focus on the problems of small sample size in modeling, the process parameters in the ultrasonic extraction of botanical medicinal materials can be obtained by optimizing the extraction rate model. However, difficulty in data acquisition results in problem of small sample size in modeling, which eventually reduces the accuracy of modeling prediction. Methods: A virtual sample generation method based on full factorial design (FFD) is proposed to solve the problem ofa small sample size. The experiments are first conducted according to the Box-Behnken design (BBD) to obtain small-size samples, and the response surface function is establis-hed accordingly. Then, virtual sample inputs are obtained by the FFD, and the corresponding virtual sample outputs are calculated by the response surface function. Furthermore, a screening method of virtual samples is proposed based on an extreme learning machine (ELM). The connection weights of ELM are used for further optimization and screening of the generated virtual samples. Result: The results show that virtual sample data can effectively expand the sample size. The preci-sion of the model trained on semi-synthetic samples (small-size experimental simples and virtual samples) is higher than the model trained merely on small-size experimental samples. Conclusion: The virtual sample generation and screening methods proposed in this paper can effec-tively solve the modeling problem of small samples. The reliable process parameters can be ob-tained by optimizing the model trained by the semi-synthetic samples.

To evaluate potential viral contamination on the surfaces of personal protective equipment (PPE) in COVID-19 wards.Face shields, gloves, the chest area of PPE and shoe soles were sampled at different time points. The samples were tested for the presence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by PCR, and the cycle threshold (CT) values were recorded.The positive rate was 74.7% (239/320) for all PPE specimens. The CT values of the samples were ranked in the following order: face shieldschestsglovesshoe soles (37.08±1.38, 35.48±2.02, 34.17±1.91 and 33.52±3.16, respectively; P for trend.001). After disinfection, the CT values of shoe soles decreased compared with before disinfection (32.78±3.47 vs. 34.3±2.61, P = .037), whereas no significant effect of disinfection on the CT values of face shields, chests and gloves was observed. After disinfection, the CT values of specimens collected from shoe soles gradually increased; before disinfection, the CT values of shoe sole specimens were all less than 35.SARS-CoV-2 can attach to the surfaces of the PPE of healthcare professionals in COVID-19 wards, especially the shoe soles and undisinfected gloves. Shoe soles had the highest SARS-CoV-2 loads among all tested PPE items.

Nowadays, with the rapid development of science and technology, continuous innovation is the basis for enterprises to maintain their vitality, and ambidextrous innovation is a hot topic of enterprise innovation. At present, there is abundant research on ambidextrous innovation at home and abroad. Based on the existing research on ambidextrous innovation, this paper sorts out the relevant literature on the concept, influence mechanism, interaction process, and effect results of ambidextrous innovation, finds out the problems of exploring the theme and single method of ambidextrous innovation research and summarizes and looks forward to the research on ambidextrous innovation.

The aim of the study was to evaluate the long-term efficacy and quality of life concerning SSLF using conventional instruments for Chinese women with symptomatic stage 2 and 3 apical prolapse.This single-arm prospective cohort study was conducted at our hospital between October 2011 and December 2018. Eligible participants were followed up over 3 years after surgery. The primary surgical outcome was composite surgical failure. Secondary outcomes included satisfactory rate, quality of life (QoL) scores and long-term complications.Fifty-nine patients were enrolled (mean age, 57.1 years), of whom 55 (93.22%) completed 3-year follow-up. At year 3, the composite failure rate was 21.34% (95%CI 9.30% -31.79%), and satisfactory rate was 81.40% (95%CI 66.09% -91.08%). Right thigh pain and de novo dyspareunia occurred in 1.8% and 14.6% patients after year 1, but at year 3 there was none. 5.5% patients had lower urinary tract symptoms. Improvement in urinary symptoms and prolapse symptoms was found, but sexual function showed no significant change.Compared with results at year 1, complication rates of SSLF decreased at year 3. The composite failure rate was relatively low and satisfactory rate relatively high at year.3. Prolapse and urinary symptoms improved significantly after surgery.