Search

Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently. In this visionary paper, we embark on a comprehensive exploration of representative architectures to address the requirement. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS). The potential relation-centric architecture aims to represent a large-scale tensor computation through relational operators. While each of these architectures demonstrates promise in specific use scenarios, we identify urgent requirements for seamless integration of these architectures and the middle ground in-between these architectures. We delve into the gaps that impede the integration and explore innovative strategies to close them. We present a pathway to establish a novel RDBMS for enabling a broad class of data-intensive DL inference applications.

Qianfeng Liu,* Kangbi Wu, Xiaofang Lin, Kali Xiang,* Jing Wang* Department of Pulmonary and Critical Care Medicine, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture, Enshi City, Hubei, People’s Republic of China*These authors contributed equally to this workCorrespondence: Kali Xiang; Jing Wang, Department of Pulmonary and Critical Care Medicine, The Central Hospital of Enshi Tujia and Miao Autonomous Prefecture, No. 158 Wuyang Avenue, Enshi City, Hubei, 445000, People’s Republic of China, Email xkl18963926688@163.com; 366413620@qq.comBackGround: Considerable studies have demonstrated a significant association between red blood cell distribution width (RDW) and clinical adverse events in cardiovascular or respiratory diseases, infections, and pulmonary embolism. However, there are limited data on prognostic predictions for patients suffering from chronic obstructive pulmonary disease (COPD).Methods: This study conducted a retrospective cohort analysis using data gathered from patients who diagnosed with COPD in the respiratory department of The Central hospital of Enshi Tujia and Miao Autonomous Prefecture between 2018 and 2021. Specifically, the RDW was recorded on their first admission. Multivariate logistic regression analysis were employed to examine the correlation between RDW and deterioration of COPD within one-year period.Results: The cohort of 1799 patients in the study comprised 74.7% male and had an average age of 68.9 ± 9.9 years. The fully adjusted model revealed that, the RDW-middle group (≤ 13.7,> 12.8; OR 1.5, 95% CI 1.0– 2.3, p=0.055) and the RDW-high group (> 13.7; OR 1.7, 95% CI 1.1– 2.6, p=0.013) had a 50% and 70% increased risk of deterioration within 1 year, respectively, in comparison with the RDW-low group (≤ 12.8). Subgroup analysis indicated that this trend was more significant in patients with hypertension (p for interaction = 0.016), and the probability of deterioration within 1 year in the RDW-high group was 3.3 times higher compared to the RDW-low group (OR 3.3, 95% CI 1.4– 7.9, p=0.008).Conclusion: A significant association was observed between the increase in RDW and the heightened risk of deterioration within a year in patients diagnosed with COPD. Most importantly, our findings suggested the importance of RDW in enhancing the risk stratification and prevention of deterioration of COPD.Keywords: red blood cell distribution width, COPD, prognosis, deterioration, risk stratification

Junhai Zhen,1 Chuan Liu,2 Jixiang Zhang,2 Fei Liao,2 Huabing Xie,1 Cheng Tan,2 Ping An,2 Zhongchun Liu,3 Changqing Jiang,4 Jie Shi,5 Kaichun Wu,6 Weiguo Dong2 1Department of General Practice, Renmin Hospital of Wuhan University, Wuhan, Hubei Province, 430060, People’s Republic of China; 2Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, Hubei Province, 430060, People’s Republic of China; 3Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, 430060, People’s Republic of China; 4Department of Clinical Psychology, Beijing Anding Hospital, Capital Medical University, Beijing, 100088, People’s Republic of China; 5Department of Medical Psychology, Chinese People’s Liberation Army Rocket Army Characteristic Medical Center, Beijing, 100032, People’s Republic of China; 6Department of Gastroenterology, Xijing Hospital, Air Force Medical University, Xi’an, 710032, People’s Republic of ChinaCorrespondence: Kaichun Wu, Department of Gastroenterology, Xijing Hospital, Air Force Medical University, Xi’an, 710032, People’s Republic of China, Tel/Fax +8629-84771600, Email kaicwu@fmmu.edu.cn Weiguo Dong, Department of Gastroenterology, Renmin Hospital of Wuhan University, 99 Zhangzhidong Road, Wuhan, Hubei Province, 430060, People’s Republic of China, Tel/Fax +8627-88041911, Email dongweiguo@whu.edu.cnPurpose: Impaired quality of life (QOL) is common in patients with inflammatory bowel disease (IBD). A tool to more quickly identify IBD patients at high risk of impaired QOL improves opportunities for earlier intervention and improves long-term prognosis. The purpose of this study was to use a machine learning (ML) approach to develop risk stratification models for evaluating IBD-related QOL impairments.Patients and Methods: An online questionnaire was used to collect clinical data on 2478 IBD patients from 42 hospitals distributed across 22 provinces in China from September 2021 to May 2022. Eight ML models used to predict the risk of IBD-related QOL impairments were developed and validated. Model performance was evaluated using a set of indexes and the best ML model was explained using a Local Interpretable Model-Agnostic Explanations (LIME) algorithm.Results: The support vector machine (SVM) classifier algorithm-based model outperformed other ML models with an area under the receiver operating characteristic curve (AUC) and an accuracy of 0.80 and 0.71, respectively. The feature importance calculated by the SVM classifier algorithm revealed that glucocorticoid use, anxiety, abdominal pain, sleep disorders, and more severe disease contributed to a higher risk of impaired QOL, while longer disease course and the use of biological agents and immunosuppressants were associated with a lower risk.Conclusion: An ML approach for assessing IBD-related QOL impairments is feasible and effective. This mechanism is a promising tool for gastroenterologists to identify IBD patients at high risk of impaired QOL.Keywords: clinical research, artificial intelligence, model development, clinical decision support system

Qiming Gan,1,* Quanzhen Liu,1,2,* Yanjuan Wu,1,* Xiaofeng Zhu,1,2 Jingcun Wang,1 Xiaofen Su,1 Dongxing Zhao,1 Nuofu Zhang,1 Kang Wu1 1State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Disease, Department of Sleep Medicine Center, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong, 510160, People’s Republic of China; 2Nanshan School, Guangzhou Medical University, Guangzhou, Guangdong, 511436, People’s Republic of China*These authors contributed equally to this workCorrespondence: Kang Wu; Nuofu Zhang, Department of Pulmonary and Critical Care Medicine, Sleep Medicine Center, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, No. 28 Qiaozhong Mid Road, Guangzhou, Guangdong, 510160, People’s Republic of China, Email d102_wk@126.com; nfzhanggird@163.comPurpose: Obstructive sleep apnea (OSA) had been associated with asthma in observational studies, but the effect of OSA on the onset of asthma in childhood or adulthood remains unclear, and the causal inferences have not been confirmed. This study aims to investigate the potential causal association between OSA with asthma, including different age-of-onset subtypes, providing reliable basis for the clinical treatment of OSA and asthma.Patients and Methods: Causality between OSA and asthma was assessed using a two-sample bi-directional Mendelian randomization (MR) analysis. OSA data were obtained from the FinnGen consortium R9, while asthma and its subtypes (adult-onset asthma, child-onset asthma, and moderate-to-severe asthma) were sourced from the IEU OpenGWAS project. The inverse-variance weighted (IVW) method was chosen as the primary analysis and was complemented by various sensitivity analyses. The MR-PRESSO outlier test was employed to systematically identify and remove outlier variants, mitigating heterogeneity and potential effects of horizontal pleiotropy.Results: The MR analyses provided evidence of genetically predicted OSA having a promoting effect on child-onset asthma (OR,1.49; 95% CI, 1.05– 2.11; P=0.025) and moderate-to-severe asthma (OR,1.03; 95% CI, 1.00– 1.06; P=0.046). However, no causal association between OSA with asthma and adult-onset asthma was observed.Conclusion: Our study revealed a causal association between OSA and child asthma, but not in adults. Moderate-to-severe asthma may have a potential promoting effect on OSA. These findings underscore the importance of age-specific considerations in managing asthma and suggests the need for personalized approaches in clinical practice.Keywords: asthma, obstructive sleep apnea, Mendelian randomization, genetic

Shulin Wei,1,2,* Mingxing Li,1,2,* Qin Wang,1,2,* Yueshui Zhao,1,2 Fukuan Du,1,2 Yu Chen,1,2 Shuai Deng,1,2 Jing Shen,1,2 Ke Wu,1,2 Jiayue Yang,1,2 Yuhong Sun,1 Li Gu,1 Xiaobing Li,1 Wanping Li,1 Meijuan Chen,1 Xiao Ling,3 Lei Yu,3 Zhangang Xiao,1,2 Lishu Dong,3 Xu Wu1,2 1Cell Therapy & Cell Drugs of Luzhou Key Laboratory, Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan, 646100, People’s Republic of China; 2South Sichuan Institute of Translational Medicine, Luzhou, Sichuan, 646100, People’s Republic of China; 3Department of Obstetrics, Luzhou Maternal & Child Health Hospital (Luzhou Second People’s Hospital), Luzhou, Sichuan, 646100, People’s Republic of China*These authors contributed equally to this workCorrespondence: Lishu Dong, Department of Obstetrics, Luzhou Maternal & Child Health Hospital (Luzhou Second People’s Hospital), Luzhou, Sichuan, 646100, People’s Republic of China, Email 1275607519@qq.com Xu Wu, Cell Therapy & Cell Drugs of Luzhou Key Laboratory, Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan, 646100, People’s Republic of China, Email wuxulz@126.comAbstract: Inflammatory bowel disease (IBD) is a chronic inflammatory disease of the gastrointestinal tract, which has a high recurrence rate and is incurable due to a lack of effective treatment. Mesenchymal stromal cells (MSCs) are a class of pluripotent stem cells that have recently received a lot of attention due to their strong self-renewal ability and immunomodulatory effects, and a large number of experimental and clinical models have confirmed the positive therapeutic effect of MSCs on IBD. In preclinical studies, MSC treatment for IBD relies on MSCs paracrine effects, cell-to-cell contact, and its mediated mitochondrial transfer for immune regulation. It also plays a therapeutic role in restoring the intestinal mucosal barrier through the homing effect, regulation of the intestinal microbiome, and repair of intestinal epithelial cells. In the latest clinical trials, the safety and efficacy of MSCs in the treatment of IBD have been confirmed by transfusion of autologous or allogeneic bone marrow, umbilical cord, and adipose MSCs, as well as their derived extracellular vesicles. However, regarding the stable and effective clinical use of MSCs, several concerns emerge, including the cell sources, clinical management (dose, route and frequency of administration, and pretreatment of MSCs) and adverse reactions. This article comprehensively summarizes the effects and mechanisms of MSCs in the treatment of IBD and its advantages over conventional drugs, as well as the latest clinical trial progress of MSCs in the treatment of IBD. The current challenges and future directions are also discussed. This review would add knowledge into the understanding of IBD treatment by applying MSCs.Keywords: mesenchymal stem cells, immunomodulation, inflammatory bowel disease, ulcerative colitis, Crohn’s disease, cell therapy

Jing-Chun Xia,1,2,* Yu-Cheng Huang,1,2,* Ke Wu,1,2 Jian Pang,1,2 Ying Shi1,2 1Shi’s Center of Orthopedics and Traumatology, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, People’s Republic of China; 2Institute of Traumatology & Orthopedics, Shanghai Academy of Traditional Chinese Medicine, Shanghai, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jian Pang; Ying Shi, Email pangjian@shutcm.edu.cn; shiying1974@126.comPurpose: Chinese herbal medicine and electroacupuncture (EA) have been used to control pain for many decades in China. We aim to explore the efficacy of intervening patients whose discogenic sciatica symptoms lasting longer than 3 months with these conservative treatments.Patients and Methods: This is a single-center, parallel-group, patient-unblinded Randomized Controlled Trial (RCT) with blinded outcome assessment and statistician. One hundred and twenty-four patients will be assigned randomly into 2 groups including conservative treatment group (Shenxie Zhitong capsule combined with EA treatment) and Nonsteroidal Anti-inflammatory Drugs (Nonsteroidal Anti-inflammatory Drugs, NSAIDs) control group (Celecoxib) in a 1:1 ratio. The trial involves a 4-week treatment along with follow-up for 6 months. The primary outcome is the leg pain intensity measured by the visual analogue scale (VAS) at 6 months after randomization. Secondary outcomes include leg pain intensity at other time points, back pain intensity, leg pain and back pain frequency, functional status, quality of life, return to work status and satisfaction of patients. Adverse events will also be recorded.Strengths and Limitations of This Study: Through this study, we want to observe the efficacy of electroacupuncture combined with Chinese herbal medicine on pain intensity for chronic sciatica secondary to Lumbar Disc Herniation. If the final results are favorable, it is expected to be a safe, economical, and effective treatment for patients. The study design has the following limitations: the setup of control group was less than perfect; patients and doctors could not be blinded in this trial; we skipped the feasibility study. We have tried our best to minimize adverse impacts.Trial Registration: ChiCTR2300070884 (Chinese Clinical Trial Registry, http://www.chictr.org.cn, registered on 25th April 2023).Keywords: sciatica of lumbar disc herniation, shenxie zhitong capsule, electroacupuncture treatment, celecoxib, single-center randomized controlled trial, protocol

Kangze Wu, Feizhuan Lin Department of Hepatobiliary Surgery, Shaoxing People’s Hospital, Shaoxing, People’s Republic of ChinaCorrespondence: Feizhuan Lin, Department of Hepatobiliary Surgery, Shaoxing People’s Hospital, Shaoxing, People’s Republic of China, Email linfeizhuan@163.comAbstract: Hepatocellular carcinoma (HCC) stands as a severe malignant tumor with a profound impact on overall health, often accompanied by an unfavorable prognosis. Despite some advancements in the diagnosis and treatment of this disease, improving the prognosis of HCC remains a formidable challenge. It is noteworthy that lipid metabolism plays a pivotal role in the onset, development, and progression of tumor cells. Existing research indicates the potential application of targeting lipid metabolism in the treatment of HCC. This review aims to thoroughly explore the alterations in lipid metabolism in HCC, offering a detailed account of the potential advantages associated with innovative therapeutic strategies targeting lipid metabolism. Targeting lipid metabolism holds promise for potentially enhancing the prognosis of HCC.Keywords: cholesterol, fatty acid, hepatocellular carcinoma, lipid uptake, lipid catabolism, lipid synthesis

Enyi Zhu,1,2,* Ming Zhong,3,* Tiantian Liang,4,* Yu Liu,3,* Keping Wu,1,2 Zhijuan Zhang,1,2 Shuping Zhao,1,2 Hui Guan,5 Jiasi Chen,6 Li-Zhen Zhang,7 Yimin Zhang1,2 1The Division of Nephrology, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Guangzhou, Guangdong, 510000, People’s Republic of China; 2Biomedical Innovation Center, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Guangzhou, Guangdong, 510000, People’s Republic of China; 3Department of Nephrology, Center of Kidney and Urology, The Seventh Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong, 517108, People’s Republic of China; 4Nephrology Division, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, 510630, People’s Republic of China; 5Department of Radiation Oncology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, 450000, People’s Republic of China; 6Department of Nephrology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong, 510030, People’s Republic of China; 7Department of Urology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, 510080, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yimin Zhang, The Division of Nephrology, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Guangzhou, People’s Republic of China, Email zhangyim@mail.sysu.edu.cn Li-Zhen Zhang, Department of Urology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of China, Email zhanglzh3@mail2.sysu.edu.cnObjective: Diabetic nephropathy (DN) represents the principal cause of end-stage renal diseases worldwide, lacking effective therapies. Fatty acid (FA) serves as the primary energy source in the kidney and its dysregulation is frequently observed in DN. Nevertheless, the roles of FA metabolism in the occurrence and progression of DN have not been fully elucidated.Methods: Three DN datasets (GSE96804/GSE30528/GSE104948) were obtained and combined. Differentially expressed FA metabolism-related genes were identified and subjected to DN classification using “ConsensusClusterPlus”. DN subtypes-associated modules were discovered by “WGCNA”, and module genes underwent functional enrichment analysis. The immune landscapes and potential drugs were analyzed using “CIBERSORT” and “CMAP”, respectively. Candidate diagnostic biomarkers of DN were screened using machine learning algorithms. A prediction model was constructed, and the performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). The online tool “Nephroseq v5” was conducted to reveal the clinical significance of the candidate diagnostic biomarkers in patients with DN. A DN mouse model was established to verify the biomarkers’ expression.Results: According to 39 dysregulated FA metabolism-related genes, DN samples were divided into two molecular subtypes. Patients in Cluster B exhibited worse outcomes with a different immune landscape compared with those in Cluster A. Ten potential small-molecular drugs were predicted to treat DN in Cluster B. The diagnostic model based on PRKAR2B/ANXA1 was created with ideal predictive values in early and advanced stages of DN. The correlation analysis revealed significant association between PRKAR2B/ANXA1 and clinical characteristics. The DN mouse model validated the expression patterns of PRKAR2B/ANXA1.Conclusion: Our study provides new insights into the role of FA metabolism in the classification, immunological pathogenesis, early diagnosis, and precise therapy of DN.Keywords: diabetic nephropathy, fatty acid metabolism, molecular subtypes, immune landscape, pharmacotherapy, diagnostic model

Wei W, Mo X, Yan L, et al. Cancer Manag Res. 2020;12:15–30. We, the Editor and Publisher of the journal Cancer Management and Research have retracted the published article. Following publication, concerns were raised regarding the use of non-verifiable cell lines described in the article. The concerns related specifically to the use of cell lines which were found to be either contaminated, wrongly identified, improperly indexed, unavailable through external cell line repositories, and/or lacking publications describing their establishment. Overall, these concerns raised doubts about the validity of the findings described in the article. The corresponding author did not respond to our queries and was unable to provide information relating to the use of these cell lines or provide original data relating to the study. As verifying the validity of published work is core to the integrity of the scholarly record, the Publisher and Editor requested to retract the article and the corresponding author was notified of this decision. We have been informed in our decision-making by our editorial policies and COPE guidelines. The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as “Retracted”.

Enyu Tong,1,* Ying Zhou,1,* Zhengwei Liu,2 Yelei Zhu,2 Mingwu Zhang,2 Kunyang Wu,2 Junhang Pan,2 Jianmin Jiang1– 3 1School of Public Health, Hangzhou Normal University, Hangzhou, 311100, People’s Republic of China; 2Tuberculosis Control Department, Zhejiang Provincial Center for Disease Control and Prevention, Hangzhou, 310051, People’s Republic of China; 3Key Laboratory of Vaccine, Prevention and Control of Infectious Disease of Zhejiang Province, Hangzhou, 310051, People’s Republic of China*These authors contributed equally to this workCorrespondence: Junhang Pan; Jianmin Jiang, Email jhpan@cdc.zj.cn; jmjiang@cdc.zj.cnPurpose: This study aimed to determine the prevalence and molecular characterization of bedaquiline (BDQ) resistance among rifampicin-resistant tuberculosis (RR-TB) isolates collected from Zhejiang, China.Patients and Methods: A total of 245 RR-TB isolates were collected from 19 municipal TB hospitals in Zhejiang province, China between January and December 2021. Microplate assays were used to determine the minimum inhibitory concentrations (MIC) of BDQ. Whole-genome sequencing (WGS) was performed on isolates with MIC values for BDQ ≥ 0.25 μg/mL.Results: Five (2.04%) BDQ-resistant strains were isolated from 245 tuberculosis patients. The resistance rate of BDQ was not correlated to the sex, age, treatment history, or occupation of patients. Four BDQ-resistant isolates and three BDQ-sensitive isolates were found to carry Rv0678 mutations, and one BDQ-resistant strain carried both Rv0678 and pepQ mutations. No mutations within the atpE and Rv1979c genes were observed.Conclusion: BDQ demonstrated strong in vitro antibacterial activity against RR-TB isolates, and the Rv0678 gene was identified as the primary mechanism contributing to BDQ resistance among RR-TB isolates from Zhejiang, China. Furthermore, in addition to the four currently known resistance-associated genes (atpE, Rv0678, Rv1979c, and pepQ), other mechanisms of resistance to BDQ may exist that need further study.Plain language summary: This study looked at a bacterial species called Mycobacterium tuberculosis, which causes the highly problematic disease, tuberculosis. Certain strains of this bacterium have developed resistance to conventional antibiotics used in tuberculosis treatment, necessitating an investigation into the efficacy of the newer antibiotic, bedaquiline. We collected 245 rifampicin-resistant tuberculosis samples from patients in Zhejiang, China, subjecting them to bedaquiline susceptibility testing. Concurrently, we conducted a genetic analysis of the bacteria to pinpoint mutations linked to bedaquiline resistance. Out of the 245 samples, 5 were found to be resistant to bedaquiline. We found that mutations in a gene called Rv0678 were the main reason for this resistance. This gene had mutations in four of the bedaquiline-resistant samples and three of the bedaquiline-susceptible samples. One of the bedaquiline-resistant samples had mutations in both Rv0678 and another gene called pepQ. We also found that bedaquiline was effective at killing drug-resistant tuberculosis bacteria in the lab. However, there may be other genes or mechanisms that make other bacteria resistant to the drug, which will need further study. Overall, this study helps us understand how bedaquiline works against drug-resistant tuberculosis bacteria and identifies a genetic mechanism that can cause resistance to the drug.Keywords: Mycobacterium tuberculosis, rifampicin-resistant tuberculosis, bedaquiline, whole-genome sequencing

Federated Learning (FL) with mobile computing and the Internet of Things (IoT) is an effective cooperative learning approach. However, several technical challenges still need to be addressed. For instance, dividing the training process among several devices may impact the performance of Machine Learning (ML) algorithms, often significantly degrading prediction accuracy compared to centralized learning. One of the primary reasons for such performance degradation is that each device can access only a small fraction of data (that it generates), which limits the efficacy of the local ML model constructed on that device. The performance degradation could be exacerbated when the participating devices produce different classes of events, which is known as the class balance problem. Moreover, if the participating devices are of different types, each device may never observe the same types of events, which leads to the device heterogeneity problem. In this study, we investigate how data augmentation can be applied to address these challenges and improving detection performance in an anomaly detection task using IoT datasets. Our extensive experimental results with three publicly accessible IoT datasets show the performance improvement of up to 22.9% with the approach of data augmentation, compared to the baseline (without relying on data augmentation). In particular, stratified random sampling and uniform random sampling show the best improvement in detection performance with only a modest increase in computation time, whereas the data augmentation scheme using Generative Adversarial Networks is the most time-consuming with limited performance benefits.

Guanglan Li,1,2 Jing Yu,1,2 Simin Jiang,1,2 Kefei Wu,1,2 Yiping Xu,1,2 Xiaohui Lu,1,2 Yating Wang,1,2 Jianxiong Lin,1,2 Xiao Yang,1,2 Zhibin Li,3 Haiping Mao1,2 1Department of Nephrology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, 510080, China; 2NHC Key Laboratory of Clinical Nephrology (Sun Yat-sen University) and Guangdong Provincial Key Laboratory of Nephrology, Guangzhou, 510080, China; 3Epidemiology Research Unit, Translational Medicine Research Center, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, 361005, ChinaCorrespondence: Haiping Mao, Department of Nephrology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, 510080, China, Email maohp@mail.sysu.edu.cnPurpose: The prognosis of patients receiving peritoneal dialysis (PD) is associated with inflammation. Systemic immune-inflammation index (SII) is one of inflammatory markers, and the role in predicting clinical outcomes in PD patients is unclear. We aimed to investigate the relationship between the SII and all-cause and cardiovascular-specific mortalities in patients undergoing PD.Patients and Methods: A total of 1419 PD patients from the First Affiliated Hospital of Sun Yat-sen University between January 1, 2007 and December 31, 2019 were retrospectively included at baseline, and the patients were followed up until November 31, 2021. SII was calculated as platelet count×neutrophil count/lymphocyte count. Kaplan–Meier curves and Cox proportional hazards regression models were used to determine the relationship between SII levels and all-cause and cardiovascular-specific mortalities.Results: During follow-up (median period was 42 months), 321 patients died (171 died of cardiovascular disease). With adjustment for the potential confounding factors, each 1-SD increase in the SII was associated with 20.2% increase in all-cause mortality (hazard ratio [HR]: 1.202, 95% confidence interval [CI]: 1.088– 1.327, P< 0.001) and 28.0% increase in cardiovascular-specific mortality (HR: 1.280, 95% CI: 1.126– 1.456, P< 0.001). High SII (vs low SII) was significantly associated with increased risks of all-cause mortality (HR: 1.391, 95% CI: 1.066– 1.815, P-value: 0.015) and cardiovascular-specific mortality (HR: 1.637, 95% CI: 1.185– 2.261, P-value: 0.003). Subgroups analyses showed similar results for those younger than 65-year-old only.Conclusion: Elevated SII level was independently associated with increased risks of all-cause and cardiovascular-specific mortalities in PD patients, especially for those younger than 65-year-old.Keywords: all-cause mortality, cardiovascular mortality, peritoneal dialysis, systemic immune-inflammation index

Yajun Jiang,1 Longfang Huang,1 Yu Guo,1 Qin Yang,2 Haixia Li,1 Huiling Zhou,1 Ke Wu3 1College of Tourism & Landscape Architecture, Guilin University of Technology, Guangxi, 541004, People’s Republic of China; 2School of Preschool Education, Changsha Normal University, Changsha, 410100, People’s Republic of China; 3School of Economics & Management, Hunan University of Science and Technology, Yongzhou, 425199, People’s Republic of ChinaCorrespondence: Ke Wu, School of Economics & Management, Hunan University of Science and Technology, Yongzhou, 425199, People’s Republic of China, Tel +15674662800, Email huse_chn@163.comPurpose: The COVID-19 has greatly affected the tourism industry in China, leading to an increase in psychological distress among tour guides. This study explores the mechanisms by which tour guides’ fear of the COVID-19 affects psychological distress, using job insecurity as a mediating variable and psychological resilience as a moderating variable.Patients and Methods: From August 11 to 30, 2022, 447 Chinese tour guides were invited online to fill in a questionnaire, and SPSS and Mplus tools were used for statistical analysis and hypothesis testing to conduct an empirical analysis of the relationship between COVID-19 fear and psychological distress.Results: A total of 417 questionnaires (effective rate was 93.3%) were collected, among which female (n = 243) and male (41.7%) (n =174). The age concentration of participants was 46.5% between 26 and 35 years old, 9.1% under 25 years old, and 9.8% over 46 years old. Guides’ fear of COVID-19 positively and significantly influenced psychological distress (β= 0.3051), and the relationship between fear of COVID-19 and psychological distress was mediated by job insecurity (β=0.196, 95% CI = 0.141, 0.255). In addition, psychological resilience significantly moderated the pathway from fear of COVID-19 to job insecurity and from fear of COVID-19 to guided psychological distress (β= 0.1371; β=0.116).Conclusion: The diversion of fear of COVID-19 and job insecurity can alleviate the psychological distress of tour guides; strengthening their own psychological construction also helps to alleviate the effects of fear of COVID-19 on job insecurity and psychological distress. The findings of the study can provide theoretical support for the prevention and counseling of psychological problems of tourism employees in public health crises.Keywords: fear of COVID-19, job insecurity, psychological distress, psychological resilience

Rong Yu,1,&ast; Chuan Liu,1,&ast; Jixiang Zhang,1,&ast; Jiao Li,1,&ast; Shan Tian,2 Fugui Ding,1 Zhengru Liu,3 Ting Wang,4 Zhongchun Liu,5 Changqing Jiang,6 Jie Shi,7 Kaichun Wu,8 Weiguo Dong1 1Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, 430060, People’s Republic of China; 2Department of Infectious Diseases, Union Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430000, People’s Republic of China; 3Department of Gastroenterology, First Affiliated Hospital of Kunming Medical University, Kunming, 650032, People’s Republic of China; 4Department of Gastroenterology, First Affiliated Hospital of Hainan Medical College, Haikou, 570102, People’s Republic of China; 5Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, 430060, People’s Republic of China; 6Department of Clinical Psychology, Beijing Anding Hospital, Capital Medical University, Beijing, 100088, People’s Republic of China; 7Department of Medical Psychology, Chinese People’s Liberation Army Rocket Army Characteristic Medical Center, Beijing, 100088, People’s Republic of China; 8Department of Gastroenterology, Xijing Hospital, Air Force Medical University, Xi’an, 710032, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Weiguo Dong, Department of Gastroenterology, Renmin Hospital of Wuhan University, No. 99 Zhangzhidong Road, Wuhan, Hubei Province, 430060, People’s Republic of China, Tel +86 027-88041911, Email dongweiguo@whu.edu.cn Kaichun Wu, Department of Gastroenterology, Xijing Hospital, Air Force Medical University, No. 127 West Changle Road, Xi’an, Shaanxi Province, 710032, People’s Republic of China, Tel +86 029-84771600, Email kaicwu@fmmu.edu.cnObjective: To explore the correlation between disease activity and anxiety, depression, sleep quality, and quality of life in patients with inflammatory bowel disease (IBD).Methods: The disease activity of IBD patients was evaluated by 66 gastroenterologists from 42 hospitals in 22 provinces in China from September 2021 to May 2022. Anxiety, depression, sleep quality and quality of life of IBD patients were investigated and statistically analyzed by different scales, including Generalized Anxiety Disorder 7-item Scale (GAD-7), Patient Health Questionnaire-9 (PHQ-9), Pittsburgh Sleep Quality Index (PSQI), and Inflammatory Bowel Disease Quality-of-Life Questionnaire (IBD-Q).Results: A total of 2478 IBD patients were included, of which 1532 (61.8%) were in active stage and 946 (38.2%) were in remission. The proportions of active IBD with anxiety, depression, sleep disturbance, and poor quality of life were 29.5%, 29.7%, 71.1%, and 50.1%, respectively, while the proportions of remission IBD with anxiety, depression, sleep disturbance, and poor quality of life were 19.1%, 24.4%, 69.3%, and 17.4%, respectively. IBD patients who also had anxiety, depression, sleep disturbances and poor quality of life had 80 cases (8.46%) in remission and 114 cases (7.44%) in active stage, with 54 cases (9.18%) in mild activity, 51 cases (6.95%) in moderate activity and 9 cases (4.49%) in severe activity. IBD patients with different disease activity levels differed in GAD-7 scores, PHQ-9 scores, PSQI scores, and IBD-Q scores (all P< 0.001). In IBD patients, anxiety, depression, and sleep disturbance, which interact with each other, can further aggravate their disease activity (all P< 0.001).Conclusion: Anxiety, depression, sleep disturbances, and quality of life are strongly correlated with disease activity in IBD patients, and IBD patients with psychological disturbances are most often in the active stage and have a poor quality of life.Keywords: inflammatory bowel disease, disease activity, anxiety, depression, sleep quality, quality of life, survey

This report provides an introduction to the Computational Intelligence and Forecasting Technologies (CIFT) project at Lawrence Berkeley National Laboratory (LBNL). The main objective of CIFT is to promote the use of high-performance computing (HPC) tools and techniques for analysis of streaming data. After noticing the data volume being given as the explanation for the five-month delay for SEC and CFTC to issue their report on the 2010 Flash Crash, LBNL started the CIFT project to apply HPC technologies to manage and analyze financial data. Making timely decisions with streaming data is a requirement for many different applications, such as avoiding impending failure in the electric power grid or a liquidity crisis in financial markets. In all these cases, the HPC tools are well suited in handling the complex data dependencies and providing timely solutions. Over the years, CIFT has worked on a number of different forms of streaming data, including those from vehicle traffic, electric power grid, electricity usage, and so on. The following sections explain the key features of HPC systems, introduce a few special tools used on these systems, and provide examples of streaming data analyses using these HPC tools.

Automated network intrusion detection systems (NIDS) continuously monitor the network traffic to detect attacks or/and anomalies. These systems need to be able to detect attacks and alert network engineers in real-time. Therefore, modern NIDS are built using complex machine learning algorithms that require large training datasets and are time-consuming to train. The proposed work shows that machine learning algorithms from the RAPIDS cuML library on Graphics Processing Units (GPUs) can speed-up the training process on large scale datasets. This approach is able to reduce the training time while providing high accuracy and performance. We demonstrate the proposed approach on a large subset of data extracted from the Aegean Wi-Fi Intrusion Dataset (AWID). Multiple classification experiments were performed on both CPU and GPU. We achieve up to 65x acceleration of training several machine learning methods by moving most of the pipeline computations to the GPU and leveraging the new cuML library as well as the GPU version of the CatBoost library.

Large scientific projects are increasing relying on analyses of data for their new discoveries; and a number of different data management systems have been developed to serve this scientific projects. In the work-in-progress paper, we describe an effort on understanding the data access patterns of one of these data management systems, dCache. This particular deployment of dCache acts as a disk cache in front of a large tape storage system primarily containing high-energy physics data. Based on the 15-month dCache logs, the cache is only accessing the tape system once for over 50 file requests, which indicates that it is effective as a disk cache. The on-disk files are repeated used, more than three times a day. We have also identified a number of unusual access patterns that are worth further investigation.

The volume of data moving through a network increases with new scientific experiments and simulations. Network bandwidth requirements also increase proportionally to deliver data within a certain time frame. We observe that a significant portion of the popular dataset is transferred multiple times to different users as well as to the same user for various reasons. In-network data caching for the shared data has shown to reduce the redundant data transfers and consequently save network traffic volume. In addition, overall application performance is expected to improve with in-network caching because access to the locally cached data results in lower latency. This paper shows how much data was shared over the study period, how much network traffic volume was consequently saved, and how much the temporary in-network caching increased the scientific application performance. It also analyzes data access patterns in applications and the impacts of caching nodes on the regional data repository. From the results, we observed that the network bandwidth demand was reduced by nearly a factor of 3 over the study period.

The widely-adopted practice is to train deep learning models with specialized hardware accelerators, e.g., GPUs or TPUs, due to their superior performance on linear algebra operations. However, this strategy does not employ effectively the extensive CPU and memory resources - which are used only for preprocessing, data transfer, and scheduling - available by default on the accelerated servers. In this paper, we study training algorithms for deep learning on heterogeneous CPU+GPU architectures. Our two-fold objective - maximize convergence rate and resource utilization simultaneously - makes the problem challenging. In order to allow for a principled exploration of the design space, we first introduce a generic deep learning framework that exploits the difference in computational power and memory hierarchy between CPU and GPU through asynchronous message passing. Based on insights gained through experimentation with the framework, we design two heterogeneous asynchronous stochastic gradient descent (SGD) algorithms. The first algorithm - CPU+GPU Hogbatch - combines small batches on CPU with large batches on GPU in order to maximize the utilization of both resources. However, this generates an unbalanced model update distribution which hinders the statistical convergence. The second algorithm - Adaptive Hogbatch - assigns batches with continuously evolving size based on the relative speed of CPU and GPU. This balances the model updates ratio at the expense of a customizable decrease in utilization. We show that the implementation of these algorithms in the proposed CPU+GPU framework achieves both faster convergence and higher resource utilization than TensorFlow on several real datasets.

Atmospheric ammonia (NH3) can affect nitrogen deposition, particle acidity, and gas-particle partitioning. Although the inorganic chemistry of NH3 in fine particulate (PM2.5) formation are well-constrained, the understanding of interactions between NH3 and secondary organic aerosol (SOA) are rather insufficient until recently. Laboratory studies indicate that NH3 molecule can react with SOA then forms nitrogen-containing organic compounds (NOCs), which can further react to form heterocyclic organic compounds. In this study, we use a modified version of the CMAQ model to simulate the potential importance of the SOA-ammonia uptake mechanism on air quality over China in summer and winter 2017, considering a range of assumed NH3 uptake coefficients (10−3–10−5). Our results show that uptake of NH3 by SOA leads to a decrease in gas-phase NH3 mixing ratio, by as much as 27.5% and 19.0% for the highest uptake coefficient scenario (10−3) in summer and winter, respectively. The largest reduction of ammonia occurs over the Sichuan Basin and the North China Plain. The reduction of gas-phase NH3 engenders a decrease of ammonium nitrate, by up to 30%, but has little impact on the ammonium sulfate concentration. Uptake of NH3 does not significantly affect SOA concentrations owing to overall moderate changes in aerosol acidity, and thus small effects on SOA formation from isoprene. Altogether, NH3 uptake led to a reduction in the average PM2.5 concentration up to 8.9% and 8.7% for the highest uptake coefficient (10−3) in summer and winter, respectively. These results highlight the need for better constraints on the NH3-SOA interactions.

To meet the exascale I/O requirements for the High-Performance Computing (HPC), a new I/O subsystem, Burst Buffer, based on solid state drives (SSD), has been developed. However, the diverse HPC workloads and the bursty I/O pattern cause severe data fragmentation that requires costly garbage collection (GC) and increases the number of bytes written to the SSD. To address this data fragmentation challenge, a new multi-stream feature has been developed for SSDs. In this work, we develop an I/O Separation scheme called BIOS to leverage this multi-stream feature to group the I/O streams based on the user IDs. We propose a stream-aware scheduling policy based on burst buffer pools in the workload manager, and integrate the BIOS with the workload manager to optimize the I/O separation scheme in burst buffer. We evaluate the proposed framework with a burst buffer I/O traces from Cori Supercomputer including a diverse set of applications. Experimental results show that the BIOS could improve the performance by 1.44x on average and reduce the Write Amplification Factor (WAF) by up to 1.20x. These demonstrate the potential benefits of the I/O separation scheme for solid state storage systems.

Donghao Wang,1,&ast; Yingying Ren,2,&ast; Riken Chen,1,&ast; Xiangxia Zeng,1,&ast; Qiming Gan,1,&ast; Zhiyang Zhuang,1 Xiaofen Su,1 Kang Wu,1 Sun Zhang,1 Yongkang Tang,1 Shiwei Li,1 Haojie Zhang,1,3 Yanyan Zhou,1 Nuofu Zhang,1 Dongxing Zhao1 1State Key Laboratory of Respiratory Disease, Sleep Medicine Center, Guangzhou Institute of Respiratory Health, National Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, People’s Republic of China; 2Medical Records and Statistics Room, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, People’s Republic of China; 3The Clinical Medicine Department, Henan University, Zhengzhou, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Dongxing Zhao; Nuofu Zhang, State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Sleep Medicine Center, Guangzhou Institute of Respiratory Health, National Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, People’s Republic of China, Tel +86-13650901411 ; +86-13600460056, Email rieast@msn.com; nfzhanggird@163.comObjective: Obstructive sleep apnea (OSA) is a common sleep-disordered breathing disease. We aimed to establish an improved screening questionnaire without physical examinations for OSA named the CNCQ-OSA (Chinese community questionnaire for OSA).Methods: A total of 2585 participants who visited sleep medicine center and underwent overnight polysomnography were grouped into two independent cohorts: derivation (n = 2180) and validation (n = 405). The CNCQ-OSA was designed according to the baseline of patients in derivation cohort. We comprehensively analyzed the data to evaluate the predictive value of the CNCQ-OSA, compared to the GOAL questionnaire, STOP-Bang questionnaire (SBQ) and NoSAS questionnaire.Results: The CNCQ-OSA included seven variables: loud snoring, BMI ≥ 25 kg/m2, male gender, apnea, sleepiness, hypertension and age ≥ 30, with a total score ranging from 7 to 16.7 points (≥ 13.5 points indicating high risk of OSA, ≥ 14.5 points indicating extremely high risk). In the derivation and validation cohorts, the areas under the curve of the CNCQ-OSA were 0.761 and 0.767, respectively. In the validation cohort, the sensitivity and specificity of a CNCQ-OSA score ≥ 13.5 points for the apnea–hypopnea index (AHI) ≥ 5/h were 0.821 and 0.559, respectively (Youden index, 0.380), and the score ≥ 14.5 points were 0.494 and 0.887, respectively (Youden index, 0.375). The CNCQ-OSA had a better predictive value for AHI ≥ 5/h, AHI > 15/h and AHI > 30/h, with the highest Youden index, compared to the other questionnaires.Conclusion: The CNCQ-OSA can effectively identify the risk of OSA, which is appropriate for self-screening at home without physical examinations.Keywords: obstructive sleep apnea, screening, GOAL, STOP-Bang, NoSAS

Meijing Shen,&ast; Xianghao Chen,&ast; Jingyue He, Lin Xiong, Rengui Tian, Guangwu Yang, He Zha, Kaifeng Wu Department of Laboratory Medicine, the First People’s Hospital of Zunyi (The Third Affiliated Hospital of Zunyi Medical University), Zunyi, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Kaifeng Wu; He Zha, Department of Laboratory Medicine, the First People’s Hospital of Zunyi (The Third Affiliated Hospital of Zunyi Medical University), Zunyi, People’s Republic of China, Email kiphoonwu@126.com; zhahe666@126.comPurpose: Carbapenem-resistant Klebsiella pneumoniae (CRKP) has seriously threatened public health worldwide. This study aimed to investigate the antimicrobial resistance patterns, sequence types (STs), virulence and carbapenemase genes of CRKP isolates from patients in Zunyi, China.Methods: CRKP isolates were collected from the First People’s Hospital of Zunyi between January 2018 and December 2020. Antimicrobial susceptibility was determined using a VITEK® 2 analyzer and confirmed using either the broth dilution method, Kirby–Bauer method, or E-test assays. Carbapenemase production was examined using a modified carbapenem inactivation method. STs of the studied isolates were determined by multilocus sequence typing, and the presence of carbapenemase and virulence genes was examined using polymerase chain reaction assays.Results: In total, 94 CRKP isolates were collected. All studied isolates produced carbapenemase, and the most common carbapenemase gene was New Delhi metallo-β-lactamase (NDM; 72.3%), followed by Klebsiella pneumoniae carbapenemase (KPC; 24.5%), and Verona integron-encoded metallo-β-lactamase (VIM; 3.2%). Of the studied isolates, 74.3% exhibited multidrug-resistant (MDR) phenotype, and 25.7% were either pandrug-resistant (PDR) or extensively drug-resistant (XDR) phenotypes. The most prevalent sequence type was ST2407 (37.2%), followed by ST76 (21.3%) and ST11 (11.7%). The NDM gene was present in 97.1% of ST2407 isolates and 90.0% of ST76 isolates, whereas the KPC gene was present in 90.9% of ST11 isolates. The majority of the isolates carried wabG, uge, and fimH virulence genes, with prevalence rates of 94.7%, 92.6%, and 94.7%, respectively.Conclusion: This study describes NDM-producing ST2407 and ST76, as well as KPC-producing ST11, as the major clonal types of CRKP isolates in Zunyi, China. All CRKP isolates were resistant to multiple types of antibiotics, and the majority of isolates carried carbapenemase and virulence genes. Clonal spread of NDM-producing CRKP ST2407 and ST76, and KPC-producing CRKP ST11 should be strictly monitored.Keywords: Klebsiella pneumoniae, antimicrobial resistance patterns, virulence genes, sequence types, carbapenemase genes

Yang Liu,1 Chao Zhang,2 Qianwen Wang,1 Kangze Wu,3 Zhouyi Sun,1 Zhe Tang,1 Bo Zhang3 1The Fourth Affiliated Hospital, Zhejiang University School of Medicine, Yiwu, Zhejiang, 322000, People’s Republic of China; 2Center for Evidence-Based Medicine and Clinical Research, Taihe Hospital, Hubei University of Medicine, Shiyan, Hubei, 442000, People’s Republic of China; 3The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, 310000, People’s Republic of ChinaCorrespondence: Bo Zhang, The Second Affiliated Hospital, Zhejiang University School of Medicine, 88 Jiefang Road, Hangzhou, Zhejiang, 310000, People’s Republic of China, Tel/Fax +86-0571-87783563, Email jjs10@zju.edu.cnBackground: This study aimed to evaluate the global colorectal cancer(CRC) trend and the relevant risk factors from 1990 to 2019 and for better policymaking and resource allocation.Methods: Data on CRC, including incidence, mortality and disability adjusted life year (DALY) rates, were extracted from the 2019 Global Burden of Disease (GBD) study. The estimated annual percentage changes (EAPCs) were calculated to assess the temporal trend of incidence, mortality and DALYs. The Bayesian age-period-cohort model(BAPC) was used to predict the future burden of CRC.Results: In 2019, a total of 2.17 million CRC cases were reported worldwide, a 157% increase from 1990. In high-social demographic index (SDI) regions, the trend of age-standardized incidence rate(ASIR) tended to decrease, while the proportion of people under 50 years of age tended to increase. Although the number of deaths and DALYs increased, the age-standardized death rate (ASDR) and age-standardized DALY rate decreased. The CRC burden was growing fastest in middle-SDI regions, especially in East Asia, followed by low SDI regions. In addition, the milk intake, High-BMI and high fasting plasma glucose play a more important role in on CRC. The predicted cases and deaths in global continued to increase to 2044. And there is an upward trend in ASIR for both men and women.Conclusion: In developed regions, the CRC burden continues to decrease, while the CRC burden become more and more severe in developing regions. Overall, the burden of CRC will rising in the near future. Therefore, reasonable resource allocation and prevention policies should be implemented. Developing countries needs more attention.Keywords: global burden of disease, colorectal cancer, disability-adjusted life year, estimated annual percentage change, age-standardized incidence rate, Bayesian age-period-cohort

While federated learning (FL) has gained great attention for mobile and Internet of Things (IoT) computing with the benefits of scalable cooperative learning and privacy protection capabilities, there still exist a great deal of technical challenges to make it practically deployable. For instance, the distribution of the training process to a myriad of devices limits the classification performance of machine learning (ML) algorithms, often showing a significantly degraded accuracy compared to centralized learning. In this paper, we investigate the problem of performance limitation under FL and present the benefit of data augmentation with an application of anomaly detection using an IoT dataset. Our initial study reveals that one of the critical reasons for the performance degradation is that each device sees only a small fraction of data (that it generates), which limits the efficacy of the local ML model (constructed by the device). This becomes more critical if the data holds the class imbalance problem, observed not infrequently in practice (e.g., a small fraction of anomalies). Moreover, device heterogeneity with respect to data quantity is an open challenge in FL. Based on these observations, we examine the impact of data augmentation on detection performance in FL settings (both homogeneous and heterogeneous). Our experimental results show that even a simple random oversampling can improve detection performance with manageable learning complexity.

To understand behaviors of natural and man-made events, such as energy consumption of buildings, which accounts for 40% of energy uses in the US, we deploy automated monitoring devices to record periodic observations. However, such experimental and observation data often contains problems and irregularities that have to be cleaned up before analyses. Due to various conditions affecting sensor operations, the communication channels, recording steps, or the recording media, the recorded data might have missing values, errors, or anomalous values. An effective way to clean up these problems is to replace these missing values, errors and anomalous values with expected values, a process generally known as imputation. In this work, we survey commonly used missing value imputation techniques and compare their performance on a set of building monitoring data. To compare the different types of sensor measurements with widely varying characteristics, we use normalized root mean squared error (NRMSE) as the key metric for the effectiveness of the imputation methods. We additionally consider periodicity and run time when considering comparing methods. Through extensive testing, we find that for small gap sizes, up to 8 consecutive missing values, linear interpolation performs the best; for larger gaps stretching up to 48 consecutive missing values, K-nearest neighbors provides the most accurate imputations; for even larger gaps, more computational intensive methods, such as matrix factorization, achieve the smallest NRMSE. Additionally, we observe that these computationally intensive algorithms not only provide accurate imputations for large gaps, but are also more robust across all types of sensors.

Botnet detection is an active research topic as botnets are a source of many malicious activities, including distributed denial-of-service (DDoS), click-fraud, spamming, and crypto-mining attacks. However, it is getting more complicated to identify botnets due to the continuous evolution of botnet software and families that harness new types of devices and attack vectors. Recent studies employing machine learning (ML) showed improved performance to detect botnets to some extent, but they are still limited and ineffective with the lack of sequential pattern analysis, which is a key to detect various classes of botnets. In this paper, we propose a novel botnet detection method, built upon Recurrent Variational Autoencoder (RVAE), that effectively captures sequential characteristics of botnet anomalies. We validate the feasibility of the proposed method with the CTU-13 dataset that have been widely employed for botnet detection studies, and show that our method is at least comparable to existing techniques in terms of detection accuracy. In addition, our experimental results show that the proposed method can detect previously unseen botnets by utilizing sequential patterns of network traffic. We will also show how our method can detect botnets in the streaming mode, which is the essential requirement to perform real-time, on-line detection.

Streamflow components (e.g., young water vs old water) and hydrological transit times play an important role in water resource and water quality management. We collected a four-year record of stable isotopes of oxygen and hydrogen (δ18O and δ2H) in precipitation, groundwater and stream water for six catchments in the Yongan watershed of eastern China. The stable isotope records were used to identify spatio-temporal variations in the young water fraction (Fyw, defined as the proportion of the transit-time distribution younger than a threshold age) and mean transit time (MTT) based on sine-wave fitting and convolution integral methods, respectively. The Fyw ranged from 14 to 35% in the Yongan watershed. Cumulative transit time showed contrasting distributions, suggesting considerable heterogeneity and a complex interplay between catchment characteristics. Estimated MTTs ranged from 3.2 to 6.3 years and may be explained by catchment characteristics (e.g., elevation and topographic gradient). Observed spatial trends in MTTs likely result from contrasting contributions of different-aged subsurface water flows across the six catchments. The use of Fyw constraints in estimating MTTs reduced uncertainty in some catchments, suggesting the potential benefits of combining multiple approaches (e.g., Fyw) to optimize the results of traditional calibration methods. The relatively low Fyw and long MTTs highlight the importance of groundwater contributions to streamflow generation and imply a considerable lag time in river water quantity and quality responses to catchment-scale water resource management. Coupling multiple metrics (e.g., Fyw and MTT) and isotope models enhances our understanding of watershed-scale hydrologic processes and hydrograph separation.

We present ADIOS 2, the latest version of the Adaptable Input Output (I/O) System. ADIOS 2 addresses scientific data management needs ranging from scalable I/O in supercomputers, to data analysis in personal computer and cloud systems. Version 2 introduces a unified application programming interface (API) that enables seamless data movement through files, wide-area-networks, and direct memory access, as well as high-level APIs for data analysis. The internal architecture provides a set of reusable and extendable components for managing data presentation and transport mechanisms for new applications. ADIOS 2 bindings are available in C++11, C, Fortran, Python, and Matlab and are currently used across different scientific communities. ADIOS 2 provides a communal framework to tackle data management challenges as we approach the exascale era of supercomputing.

Machine Learning (ML) methods have been widely used in Intrusion Detection Systems (IDS). In particular, many botnet detection methods are based on ML. However, due to the fast-evolving nature of network security threats, it is necessary to frequently retrain the ML tools with up-to-date data, especially because data labeling takes a long time and requires a lot of effort, making it difficult to generate training data. We propose transfer learning as a more effective approach for botnet detection, as it can learn from well curated source data and transfer the knowledge to a target problem domain not seen before. We devise an approach that is effective regardless whether or not the data from the target domain is labeled. More specifically, we train a neural network with the Recurrrent Variation Autoencoder (RVAE) structure on the source data, and use RVAE to compute anomaly scores for data records from the target domain. In an evaluation of this transfer learning framework, we use CTU-13 dataset as a source domain and a fresh set of network monitoring data as a target domain. Tests show that the proposed transfer learning method is able to detect botnets better than semi-supervised learning method that was trained on the target domain data. The area under Receiver Operating Characteristic is 0.810 for transfer learning, and 0.779 for directly using RVAE on the target domain data.

With the growth of 5G wireless technologies and IoT, it become urgent to develop robust network security systems, such as intrusions detection systems (IDS) to keep the networks secure. These IDS systems need to detect unauthorized access and attacks in real-time. However, most of the modern IDS are built based on complex machine learning models that are time-consuming to train. In this work, we propose a methodology using the SHapley Additive exPlanations (SHAP) in combination with tree-based classifiers. SHAP can be used to select consistent and small feature subsets to reduce the execution time and improve classification accuracy. We demonstrate the proposed approach with the Aegean Wi-Fi Intrusion Dataset (AWID) dataset in a series of multi-class classification experiments. Among the four classes ("normal", "injection", "flooding"and "impersonation"), it is well-known that the class impersonation is hard to be classified accurately. Tests show that we can use about 10% of the initial feature set without reducing the overall prediction accuracy. With this reduced set of features, the training time could be reduced as much as a factor of four, while slightly improving the discriminating ability to identify impersonation instances. This study suggests that by reducing the number of features, the classification algorithms are able to focus on key trends that differentiates the "attacks"classes from the "normal"class. Using a reduces subset of features improves IDS's accuracy and performance. Also, SHAP dependence plots capture the relationship between individual features and the classification decision.

Large-scale high performance computing (HPC) systems typically consist of many thousands of CPUs and storage units, while used by hundreds to thousands of users at the same time. Applications from these large numbers of users have diverse characteristics, such as varying compute, communication, memory, and I/O intensiveness. A good understanding of the performance characteristics of each user application is important for job scheduling and resource provisioning. Among these performance characteristics, the I/O performance is difficult to predict because the I/O system software is complex, the I/O system is shared among all users, and the I/O operations also heavily rely on networking systems. To improve the prediction of the I/O performance on HPC systems, we propose to integrate information from a number of different system logs and develop a regression-based approach that dynamically selects the most relevant features from the most recent log entries, and automatically select the best regression algorithm for the prediction task. Evaluation results show that our proposed scheme can predict the I/O performance with up to 84% prediction accuracy in the case of the I/O-intensive applications using the logs from CORI supercomputer at NERSC.

Large high-performance computers (HPC) are expensive tools responsible for supporting thousands of scientific applications. However, it is not easy to determine the best set of configurations for workloads to best utilize the storage and I/O systems. Users typically use the default configurations provided by the system administrators, which typically results in poor performance. In an effort to identify application characteristics more important to I/O performance, we applied several machine learning techniques to characterize these applications. To identify the features that are most relevant to the I/O performance, we evaluate a number of different feature selection methods, e.g., Mutual information regression and F regression, and develop a novel feature selection method based on Min-max mutual information. These feature selection methods allow us to sift through a large set of the real-world workloads collected from NERSC's Cori supercomputer system, and identify the most important features. We employ a number of different clustering algorithms, including KMeans, Gaussian Mixture Model (GMM) and Ward linkage, and measure the cluster quality with Davies Boulder Index (DBI), Silhouette and a new Combined Score developed for this work. The cluster evaluation result shows that the test dataset could be best divided into three clusters, where cluster 1 contains mostly small jobs with operations on standard I/O units, cluster 2 consists of middle size parallel jobs dominated by read operations, and cluster 3 include large parallel jobs with heavy write operations. The cluster characteristics suggest that using parallel I/O library MPI IO and a large number of parallel cores are important to achieve high I/O throughput.

We consider data sources connected to a software defined network (SDN) with heterogeneous link access rates. Deadline-driven data transfer requests are made to a centralized network controller that schedules pacing rates of sources and meeting the request deadline has a pre-assigned value. The goal of the scheduler is to maximize the aggregate value. We design a scheduler (RL-Agent) based on Deep Deterministic Policy Gradient (DDPG). We compare our approach with three heuristics: (i) PFAIR, which shares the bottleneck capacity in proportion to the access rates, (ii) VDRatio, which prioritizes flows with high value-to-demand ratio, and (iii) VBEDF, which prioritizes flows with high value-to-deadline ratio. For equally valued requests and homogeneous access rates, PFAIR is the same as an idealized TCP algorithm, while VBEDF and VDRatio reduce to the Earliest Deadline First (EDF) and the Shortest Job First (SJF) algorithms, respectively. In this scenario, we show that RL-Agent performs significantly better than PFAIR and VDRatio and matches and in over-loaded scenarios out-performs VBEDF. When access rates are heterogeneous, we show that the RL-Agent performs as well as VBEDF even though the RL-Agent has no knowledge of the heterogeneity to start with. For the value maximization problems, we show that the RL-Agent out-performs the heuristics for both homogeneous and heterogeneous access networks. For the general case of heterogeneity with different values, the RL-Agent performs the best despite having no prior knowledge of the heterogeneity and the values, whereas the heuristics have full knowledge of the heterogeneity and VDRatio and VBEDF have partial knowledge of the values through the ratios of value to demand and value to deadline, respectively.