Search

Today, the rapid growth of vehicles connected to the Internet enables provides various services to consumers, including traffic management, traffic safety, and entertainment. Vehicular Ad-Hoc Network (VANET) is one of the most prominent and emerging technologies on the Internet of Vehicular Things (IoVT). This technology offers to fulfill requirements such as robust information exchange, and infotainment among vehicles for the smart city environment. Still, it has some challenges such as centralization, storage, security, and privacy because all city vehicular networks send vehicles and road-related information data directly to the cloud. This article proposes BIIoVT: Blockchain-based Secure Storage Architecture for Intelligent Internet of Vehicular Things (IIVoT) to mitigate the above-mention issues. Blockchain provides security and privacy at each city's vehicular networks and decentralized storage at the cloud layer with a Distributed Hash Table (DHT). It also examines how the vehicular network offers a secure platform. The validation results of the proposed architecture show an outstanding balance of secure storage and efficiency for the IoVT compared to existing methods.

Model compression is a promising approach for reducing the model size of pretrained-language-models (PLMs) on low resource edge devices and applications. Unfortunately, the compression process always accompanies a cost of performance degradation, especially for the low resource downstream tasks, i.e., multiple-choice question answering. To address the degradation issue of model compression on PLMs, we proposed an end-to-end reptile (ETER) meta-learning approach to improving the performance of PLMs on the low resource multiple-choice question answering task. Specifically, our ETER improves the traditional two-stage meta-learning to an end-to-end manner, integrating the target finetuning stage into the meta training stage. To strengthen the generic meta-learning, ETER employs two-level meta-task construction from instance-level and domain-level to enrich its task generalization. What is more, ETER optimizes meta-learning by parameter constraints to reduce its parameter learning space. Experiments demonstrate that ETER significantly improved the performance of compressed PLMs and achieved large superiority over the baselines on different datasets.

Unmanned Aerial Vehicles (UAVs) are being used in different emerging domains for accomplishing many critical tasks. However, due to the various constraints like – battery life, computational resources, etc., an UAV under a mission (M-UAV) often needs assistance from an edge/cloud server that is reachable from the M-UAV’s location. A connection between an M-UAV and edge server can be established via an access point or AP. Therefore, before sharing any sensitive information with the edge server, it is essential for an M-UAV to determine the legitimacy of the selected AP. Recently, some works in this direction indicate that a rogue UAV (R-UAV) can successfully mimic a legitimate AP for intercepting the communication channel. Hence, there should be a robust detection mechanism in place for addressing such a threat scenario. In this paper, considering one of the emerging domains – the Internet of Vehicle (IoV) networks, at first, we show that communication in the IoV networks can get benefit from the presence of M-UAVs. However, as the link between the M-UAV and edge server can be intercepted by an R-UAV, the adversary may access the sensitive information from the IoV networks. Followed by this, we propose a timing-based algorithm for identifying the presence of rogue APs (or R-UAVs) in the channel. The M-UAV executes the timing-based algorithm, and the detection method does not require any auxiliary hardware or any modification to the network protocols for meeting the objective. Supported by an extensive evaluation study, we show that without any rigid restriction on the M-UAV’s speed (e.g., by limiting it to almost static) the proposed approach significantly enhances the detection accuracy (at least by a margin of 29.7% and 16.65%) compared to the state-of-the-art methods.

Password is one of the most well-known authentication methods in accessing many Internet of Things (IoT) devices. The usage of passwords, however, inherits several drawbacks and emerging vulnerabilities in the IoT platform. However, many solutions have been proposed to tackle these limitations. Most of these defense strategies suffer from a lack of computational power and memory capacity and do not have immediate cover in the IoT platform. Motivated by this consideration, the goal of this paper is fivefold. First, we analyze the feasibility of implementing a honeyword-based defense strategy to prevent the latest developed server-side threat on the IoT domain’s password. Second, we perform thorough cryptanalysis of a recently developed honeyword-based method to evaluate its advancement in preventing the threat and explore the best possible way to incorporate it in the IoT platform. Third, we verify that we can add a honeyword-based solution to the IoT infrastructure by ensuring specific guidelines. Forth, we propose a generic attack model, namely matching attack utilizing the compromised password-file to perform the security check of any legacy-UI approach for meeting the all essential flatness security criterion. Last, we compare the matching attack’s performance with the corresponding one of a benchmark technological methods over the legacy-UI model and confirm that our attack has 5%~22% more vulnerable than others.

Accumulated studies have discovered that circular RNAs (CircRNAs) are closely related to many complex human diseases. Due to this close relationship, CircRNAs can be used as good biomarkers for disease diagnosis and therapeutic targets for treatments. However, the number of experimentally verified circRNA-disease associations are still fewer and also conducting wet-lab experiments are constrained by the small scale and cost of time and labour. Therefore, effective computational methods are required to predict associations between circRNAs and diseases which will be promising candidates for small scale biological and clinical experiments. In this paper, we propose novel computational models based on Graph Convolution Networks (GCN) for the potential circRNA-disease association prediction. Currently most of the existing prediction methods use shallow learning algorithms. Instead, the proposed models combine the strengths of deep learning and graphs for the computation. First, they integrate multi-source similarity information into the association network. Next, models predict potential associations using graph convolution which explore this important relational knowledge of that network structure. Two circRNA-disease association prediction models, GCN based Node Classification (GCN-NC) and GCN based Link Prediction (GCN-LP) are introduced in this work and they demonstrate promising results in various experiments and outperforms other existing methods. Further, a case study proves that some of the predicted results of the novel computational models were confirmed by published literature and all top results could be verified using gene-gene interaction networks.

A drug-drug interaction (DDI) is defined as an association between two drugs where the pharmacological effects of a drug are influenced by another drug. Positive DDIs can usually improve the therapeutic effects of patients, but negative DDIs cause the major cause of adverse drug reactions and even result in the drug withdrawal from the market and the patient death. Therefore, identifying DDIs has become a key component of the drug development and disease treatment. In this study, we propose a novel method to predict DDIs based on the integrated similarity and semi-supervised learning (DDI-IS-SL). DDI-IS-SL integrates the drug chemical, biological and phenotype data to calculate the feature similarity of drugs with the cosine similarity method. The Gaussian Interaction Profile kernel similarity of drugs is also calculated based on known DDIs. A semi-supervised learning method (the Regularized Least Squares classifier) is used to calculate the interaction possibility scores of drug-drug pairs. In terms of the 5-fold cross validation, 10-fold cross validation and de novo drug validation, DDI-IS-SL can achieve the better prediction performance than other comparative methods. In addition, the average computation time of DDI-IS-SL is shorter than that of other comparative methods. Finally, case studies further demonstrate the performance of DDI-IS-SL in practical applications.

Deep neural networks have achieved great success in both computer vision and natural language processing tasks. How to improve the gradient flows is crucial in training very deep neural networks. To address this challenge, a gradient enhancement approach is proposed through constructing the short circuit neural connections. The proposed short circuit is a unidirectional neural connection that back propagates the sensitivities rather than gradients in neural networks from the deep layers to the shallow layers. Moreover, the short circuit is further formulated as a gradient truncation operation in its connecting layers, which can be plugged into the backbone models without introducing extra training parameters. Extensive experiments demonstrate that the deep neural networks, with the help of short circuit connection, gain a large margin of improvement over the baselines on both computer vision and natural language processing tasks. The work provides the promising solution to the low‐resource scenarios, such as, intelligence transport systems of computer vision, question answering of natural language processing.

Brown adipocytes share the same developmental origin with skeletal muscle. Here we find that a brown adipocyte-to-myocyte remodeling also exists in mature brown adipocytes, and is induced by prolonged high fat diet (HFD) feeding, leading to brown fat dysfunction. This process is regulated by the interaction of epigenetic pathways involving histone and DNA methylation. In mature brown adipocytes, the histone demethylase UTX maintains persistent demethylation of the repressive mark H3K27me3 at Prdm16 promoter, leading to high Prdm16 expression. PRDM16 then recruits DNA methyltransferase DNMT1 to Myod1 promoter, causing Myod1 promoter hypermethylation and suppressing its expression. The interaction between PRDM16 and DNMT1 coordinately serves to maintain brown adipocyte identity while repressing myogenic remodeling in mature brown adipocytes, thus promoting their active brown adipocyte thermogenic function. Suppressing this interaction by HFD feeding induces brown adipocyte-to-myocyte remodeling, which limits brown adipocyte thermogenic capacity and compromises diet-induced thermogenesis, leading to the development of obesity., Brown adipocytes contribute to energy balance, and adipocyte development and brown adipocyte thermogenesis are in part regulated by epigenetic modifications. Here the authors report that the histone demethylase Utx maintains brown adipocyte identity via demethylation of PRDM16, which in turn represses myogenic remodelling via DNMT1-mediated Myod1 promoter hypermethylation in mice.

Knowledge of protein functions plays an important role in biology and medicine. With the rapid development of high-throughput technologies, a huge number of proteins have been discovered. However, there are a great number of proteins without functional annotations. A protein usually has multiple functions and some functions or biological processes require interactions of a plurality of proteins. Additionally, Gene Ontology provides a useful classification for protein functions and contains more than 40,000 terms. We propose a deep learning framework called DeepGOA to predict protein functions with protein sequences and protein-protein interaction (PPI) networks. For protein sequences, we extract two types of information: sequence semantic information and subsequence-based features. We use the word2vec technique to numerically represent protein sequences, and utilize a Bi-directional Long and Short Time Memory (Bi-LSTM) and multi-scale convolutional neural network (multi-scale CNN) to obtain the global and local semantic features of protein sequences, respectively. Additionally, we use the InterPro tool to scan protein sequences for extracting subsequence-based information, such as domains and motifs. Then, the information is plugged into a neural network to generate high-quality features. For the PPI network, the Deepwalk algorithm is applied to generate its embedding information of PPI. Then the two types of features are concatenated together to predict protein functions. To evaluate the performance of DeepGOA, several different evaluation methods and metrics are utilized. The experimental results show that DeepGOA outperforms DeepGO and BLAST.

BACKGROUND: Measles is a highly-contagious, serious diseases that can lead to potentially fatal illness, disability and death . We conducted an investigation to calculate the economic burden of measles cases from 2018 to 2019 and to analyze factors that influenced the total costs of measles cases in Fujian Province, China. METHODS: We investigated confirmed cases of measles by telephone interview, from 2018 to 2019, including demographic characteristics, therapeutic measures, self-treatment and nutritional supplement expenditure, transportation fees, and lost wages. Medical expenses in the hospitals were obtained from the hospital service charge system. RESULTS: A total of 131 measles cases were investigated, the average direct cost, indirect cost, and total cost were $518, $284, and $802, respectively. The total cost was 15.5% of Annual Per Capita Disposable Income of Households ($5 162) in Fujian. Hospitalization (OR = 98.6, 95%CI: 21.1 ~ 460.6) and complication (OR = 8.7, 95%CI: 1.3 ~ 58.0) significantly influenced the total cost according to binary logistic regression, and an outbreak of measles may pose a significant threat to household finances in a short term. CONCLUSIONS: The economic burden of measles was high when compared with Annual Per Capita Disposable Income of Households. The resurgence of measles and measles outbreaks increased economic burden of household finances.

Crystalline covalent organic frameworks (COFs) are porous polymeric semiconductors with network topologies, which are built from the integration of selected organic blocks with covalent bond linkages. They have shown great promise for artificial photosynthesis, owing to broad light harvesting, high crystallinity, and high carrier mobility. This Minireview introduces state-of-the-art COF photocatalysts based on different linkages and discusses the origin of photocatalytic activities for hydrogen evolution. Three typical COF photocatalysts, with linkages including imine (-C=N-), β-ketoenamine (O=C-C=C-NH-), and vinylene (-C=C-), are discussed with a particular focus on the advancements in synthetic methodologies and structural design, as well as photoelectronic properties that are relevant to photocatalytic performance. The Minireview is expected to elucidate their structure-property relationships and the way to design photoactive COFs with enhanced performances.

Excessive alcohol use* is associated with disease, injury, and poor pregnancy outcomes and is responsible for approximately 95,000 deaths in the United States each year (1). Binge drinking (five or more drinks on at least one occasion for men or four or more drinks for women) is the most common and costly pattern of excessive alcohol use (2). CDC analyzed data from the 2018 Behavioral Risk Factor Surveillance System (BRFSS) to estimate past 30-day binge drinking prevalence, frequency, and intensity (number of drinks per occasion), overall and by select characteristics and state. The overall unadjusted prevalence of binge drinking during the past 30 days was 16.6%, representing an estimated 38.5 million U.S. adults aged ≥18 years; prevalence was highest (26.0%) among those aged 25-34 years. The age-standardized binge drinking prevalence was higher among men (22.5%) than among women (12.6%), increased with income, and was highest among non-Hispanic White adults and adults in the Midwest Census region. State-level age-standardized binge drinking prevalence ranged from 10.5% (Utah) to 25.8% (Wisconsin). Among adults who reported binge drinking, 25.0% did so at least weekly, on average, and 25.0% consumed at least eight drinks on an occasion. To reduce binge drinking, the Community Preventive Services Task Force recommends increasing alcohol taxes and implementing strategies that strengthen regulations to reduce alcohol availability.† The U.S. Preventive Services Task Force recommends clinicians screen adults for alcohol misuse in primary care settings and provide counseling as needed.§.

Background Despite multiple available fixed-dose combinations (FDCs) of inhaled long-acting β2-agonists (LABAs) plus long-acting muscarinic antagonists (LAMAs) and LABAs plus inhaled corticosteroids (ICS) for COPD, uncertainty remains regarding their comparative effects. Research Question Can comparative effectiveness and safety of LABA plus LAMA (LABA/LAMA) and LABA plus ICS (LABA/ICS) FDCs vary by different individual components of the dual combinations in COPD? Study Design and Methods We conducted a new user, propensity score-inverse probability of treatment weighting cohort study to compare the effectiveness and safety of two frequently used LABA/LAMA FDCs (indacaterol plus glycopyrronium [IND/GLY] and vilanterol plus umeclidinium [VI/UMEC]) vs three commonly prescribed LABA/ICS FDCs (salmeterol plus fluticasone propionate [SAL/FP], formoterol fumarate plus budesonide [FF/BUD], and formoterol fumarate plus beclomethasone dipropionate [FF/BDP]) using the Taiwanese nationwide health care claims from 2014 through 2017. The primary effectiveness outcome was the annual moderate to severe exacerbation rate, and safety outcomes included risks of severe pneumonia and cardiovascular disease requiring hospitalization. Weighted generalized linear mixed models and Cox proportional hazard models were used to assess the effectiveness and safety outcomes, respectively. Results Patients with COPD initiating IND/GLY and VI/UMEC showed an 11% (incidence rate ratio [IRR], 0.89; 95% CI, 0.80-0.98) and 20% (IRR, 0.80; 95% CI, 0.71-0.90) reduced annual rate of moderate to severe exacerbations, respectively, than those initiating SAL/FP, but showed a similar rate as those initiating FF/BUD or FF/BDP. Both LABA/LAMA FDCs, compared with SAL/FP and VI/UMEC vs FF/BDP, were associated with a 27% (hazard ratio [HR], 0.73; 95% CI, 0.59-0.90) to 42% (HR, 0.58; 95% CI, 0.48-0.70) reduced pneumonia risk. Cardiovascular risk was comparable in five groups. An intraclass difference existed in rates of moderate to severe COPD exacerbation and risks of pneumonia among LABA/ICS FDCs, but not between LABA/LAMA FDCs. Interpretation Both LABA/LAMAs vs SAL/FP are associated with a lower exacerbation rate and pneumonia risk, but exhibit similar effectiveness and safety outcomes compared with FF/BDP or FF/BUD, suggesting that comparative effects may differ by individual components of the dual therapies in COPD.

Objective: Large volume radiological text data have been accumulated since the incorporation of electronic health record (EHR) systems in clinical practice. We aimed to determine whether deep natural language processing algorithms could aid radiologists in improving thyroid cancer diagnosis. Methods: Sonographic EHR data were obtained from the EHR database. Pathological reports were used as the gold standard for diagnosing thyroid cancer. We developed thyroid cancer diagnosis based on natural language processing (THCaDxNLP) to interpret unstructured sonographic text reports for thyroid cancer diagnosis. We used the area under the receiver operating characteristic curve (AUROC) as the primary metric to measure the performance of the THCaDxNLP. We compared the performance of thyroid ultrasound radiologists aided with THCaDxNLP vs. those without THCaDxNLP using 5 independent test sets. Results: We obtained a total number of 788,129 sonographic radiological reports. The number of thyroid sonographic data points was 132,277, 18,400 of which were thyroid cancer patients. Among the 5 test sets, the numbers of patients per set were 439, 186, 82, 343, and 171. THCaDxNLP achieved high performance in identifying thyroid cancer patients (the AUROC ranged from 0.857–0.932). Thyroid ultrasound radiologists aided with THCaDxNLP achieved significantly higher performances than those without THCaDxNLP in terms of accuracy (93.8% vs. 87.2%; one-sided t-test, adjusted P = 0.003), precision (92.5% vs. 86.0%; P = 0.018), and F1 metric (94.2% vs. 86.4%; P = 0.007). Conclusions: THCaDxNLP achieved a high AUROC for the identification of thyroid cancer, and improved the accuracy, sensitivity, and precision of thyroid ultrasound radiologists. This warrants further investigation of THCaDxNLP in prospective clinical trials.

Fracture-type buried-hill reservoirs refer to dual media which have a fast breakthrough speed and a low sweep efficiency in the process of gas injection displacement. In order to overcome this problem, in this paper, a new profile control and oil displacement technology of pre-slug deep plugging by injection of different levels of nano-microspheres and natural gas was proposed. The mercury intrusion experiments were used to compare the fractal characteristics of the pore structures of the matrix and artificial fractured cores in the buried-hill reservoir. The results show that the heterogeneous characteristics of pores and fractures are the main factors leading to excessive gas breakthrough. Three nano-microsphere systems (WJ1, WJ2, and WJ3) with good temperature resistance, salt resistance, swelling properties, and stability were prepared using the inverse emulsion method. Core plugging performance tests show that WJ3 has the best plugging effect among the three nano-microsphere systems, followed by WJ2 and WJ1. According to the scanning electron microscopy observations, it was found that the sealing mechanism of nano-microspheres includes direct sealing, bridging sealing, adhesive sealing, direct pass, deformed pass, and crushing pass. Finally, the displacement experiments with a composite fractured core showed that compared with pure natural gas injection, the breakthrough time of the combined displacement process of nano-microspheres and natural gas was greatly extended, and the final oil displacement efficiency was increased to greater than 80%.

Generative Adversarial Networks (GANs) have promoted a variety of applications in computer vision and natural language processing, among others, due to its generative model’s compelling ability to generate realistic examples plausibly drawn from an existing distribution of samples. GAN not only provides impressive performance on data generation-based tasks but also stimulates fertilization for privacy and security oriented research because of its game theoretic optimization strategy. Unfortunately, there are no comprehensive surveys on GAN in privacy and security, which motivates this survey to summarize systematically. The existing works are classified into proper categories based on privacy and security functions, and this survey conducts a comprehensive analysis of their advantages and drawbacks. Considering that GAN in privacy and security is still at a very initial stage and has imposed unique challenges that are yet to be well addressed, this article also sheds light on some potential privacy and security applications with GAN and elaborates on some future research directions.

Homozygous and heterozygous deletions commonly exist in the human genome. For current structural variation detection tools, it is significant to determine whether a deletion is homozygous or heterozygous. However, the problems of sequencing errors, micro-homologies, and micro-insertions prohibit common alignment tools from identifying accurate breakpoint locations, and often result in detecting false structural variations. In this study, we present a novel deletion detection tool called Sprites2. Comparing with Sprites, Sprites2 makes the following modifications: (1) The distribution of insert size is used in Sprites2, which can identify the type of deletions and improve the accuracy of deletion calls. (2) A precise alignment method based on AGE (one algorithm simultaneously aligning 5’ and 3’ ends between two sequences) is adopted in Sprites2 to identify breakpoints, which is helpful to resolve the problems introduced by sequencing errors, micro-homologies, and micro-insertions. In order to test and verify the performance of Sprites2, some simulated and real datasets are adopted in our experiments, and Sprites2 is compared with five popular tools. The experimental results show that Sprites2 can improve the performance of deletion detection. Sprites2 can be downloaded from https://github.com/zhangzhen/sprites2 .

Due to the rapid development of information and communication technologies with several emerging computing paradigms, such as ubiquitous computing, social computing, and mobile computing, modeling of information diffusion becomes an increasingly significant issue in the big data era. In this study, we focus on a periodic-aware intelligent prediction method based on a comprehensive modeling of user and contagion features, which can be applied to support information diffusion across social networks in accordance with users’ adoption behaviors. In particular, the Dynamically Socialized User Networking (DSUN) model and sentiment-Latent Dirichlet Allocation (LDA) topic model, which consider a series of social factors, including user interests and social roles, semantic topics and sentiment polarities, are constructed and integrated together to facilitate the information diffusion process. A periodic-aware preception mechanism usingreinforcement learning with a newly designed reward rule based on topic distribution is then designed to detect and classify different periods into the so-called routine period and emergency period. Finally, a deep learning scheme based on multi-factor analysis is developed for adoption behavior prediction within the identified different periods. Experiments using the real-world data demonstrate the effectiveness and usefulness of our proposed model and method in heterogenous social network environments.

Coronavirus disease 2019 (COVID‐19), caused by severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2), has become a global pandemic worldwide. Long non‐coding RNAs (lncRNAs) are a subclass of endogenous, non‐protein‐coding RNA, which lacks an open reading frame and is more than 200 nucleotides in length. However, the functions for lncRNAs in COVID‐19 have not been unravelled. The present study aimed at identifying the related lncRNAs based on RNA sequencing of peripheral blood mononuclear cells from patients with SARS‐CoV‐2 infection as well as health individuals. Overall, 17 severe, 12 non‐severe patients and 10 healthy controls were enrolled in this study. Firstly, we reported some altered lncRNAs between severe, non‐severe COVID‐19 patients and healthy controls. Next, we developed a 7‐lncRNA panel with a good differential ability between severe and non‐severe COVID‐19 patients using least absolute shrinkage and selection operator regression. Finally, we observed that COVID‐19 is a heterogeneous disease among which severe COVID‐19 patients have two subtypes with similar risk score and immune score based on lncRNA panel using iCluster algorithm. As the roles of lncRNAs in COVID‐19 have not yet been fully identified and understood, our analysis should provide valuable resource and information for the future studies.

Computational drug repositioning, which is an efficient approach to find potential indications for drugs, has been used to increase the efficiency of drug development. The drug repositioning problem essentially is a top-K recommendation task that recommends most likely diseases to drugs based on drug and disease related information. Therefore, many recommendation methods can be adopted to drug repositioning. Collaborative metric learning (CML) algorithm can produce distance metrics that capture the important relationships among objects, and has been widely used in recommendation domains. By applying CML in drug repositioning, a joint metric space is learned to encode drug's relationships with different diseases. In this study, we propose a novel drug repositioning computational method using Collaborative Metric Learning to predict novel drug-disease associations based on known drug and disease related information. Specifically, the proposed method learns latent vectors of drugs and diseases by applying metric learning, and then predicts the association probability of one drug-disease pair based on the learned vectors. The comprehensive experimental results show that CMLDR outperforms the other state-of-the-art drug repositioning algorithms in terms of precision, recall, and AUPR.

In the era of the Internet of Things (IoT), people access many applications through smartphones for controlling smart devices. Therefore, such a centralized node must follow a robust access control mechanism so that an intruder cannot control the connected devices. Recent reports suggest that password can be used as an authentication factor for accessing the smart setups. However, this static information can be compromised under the light of different machine learning (ML)-empowered attack mechanisms. Alarmingly, different sensors used in the IoT setup can also expose this static information to the adversaries. Password-based authentication that uses a challenge–response strategy is an effective solution for handling such threat scenarios. In this article, at first, we show that no existing usable challenge–response protocol is safe to be used in the public area network. Following this, we propose a challenge–response protocol that is more secure to use in the public domain. By using eight classifiers, we show that a learning-based threat specific to our protocol has a marginal impact on the method’s security standard. The discussion in this article also suggests that the proposed protocol has usability and security advantages compared to the existing state of the art (e.g., reduces the number of interactions between the user and verifier by a factor of 0.5).

Single-cell RNA sequencing (scRNA-seq) technology provides quantitative gene expression profiles at single-cell resolution. As a result, researchers have established new ways to explore cell population heterogeneity and genetic variability of cells. One of the current research directions for scRNA-seq data is to identify different cell types accurately through unsupervised clustering methods. However, scRNA-seq data analysis is challenging because of their high noise level, high dimensionality and sparsity. Moreover, the impact of multiple latent factors on gene expression heterogeneity and on the ability to accurately identify cell types remains unclear. How to overcome these challenges to reveal the biological difference between cell types has become the key to analyze scRNA-seq data. For these reasons, the unsupervised learning for cell population discovery based on scRNA-seq data analysis has become an important research area. A cell similarity assessment method plays a significant role in cell clustering. Here, we present BioRank, a new cell similarity assessment method based on annotated gene sets and gene ranks. To evaluate the performances, we cluster cells by two classical clustering algorithms based on the similarity between cells obtained by BioRank. In addition, BioRank can be used by any clustering algorithm that requires a similarity matrix. Applying BioRank to 12 public scRNA-seq datasets, we show that it is better than or at least as well as several popular similarity assessment methods for single cell clustering.

Introduction Smoking-attributed mortality is increasing steadily in most developing countries. The aim of the study is to assess the reduction in smoking-associated mortality following cessation. Methods Death data were collected from 2016 to 2017. Cases were deaths from pre-defined diseases of interest (65298); controls were deaths from pre-defined non-smoking-related diseases (13527). Case versus control odds ratios for ex-smokers versus smokers were calculated by age, sex, marital status and education with standardized logistic regression. These are described as mortality rate ratios (RRs, calculated as odds ratios), with a group-specific confidence interval (CI). The statistical analysis of the data was conducted from June to August 2019. Results For deaths from pre-defined non-smoking-related diseases at age 35-59 years, the RRs for quitting smoking 0-4, 5-9 or ≥10 years ago and never smoking were 0.66 (95% CI: 0.55-0.78), 0.58 (95% CI: 0.38-0.88), 0.61 (95% CI: 0.45-0.82), and 0.43 (95% CI: 0.39-0.46), respectively. The same trend was found at ages 60-69 years and 70-79 years. Younger age of quitting (25-44 or 45-64 years) appeared to be associated with greater protection among the age groups: RR was 0.55 (95% CI: 0.42-0.74) and 0.67 (95% CI: 0.56-0.79), respectively, at age 35-59 years. Among the patients who died of lung cancer, the strong protective effect can only be observed when the duration of quitting is ≥10 years. The effect of smoking cessation on the risk of death from cardiovascular disease can be observed when the duration of quitting is 1-5 years. Conclusions Longer durations of smoking cessation are associated with progressively lower mortality rates from the diseases of interest, such as lung cancer and other smoking related cancers. For sustainable monitoring of tobacco-attributed mortality, smoking information over decades, such as smoking duration and quit smoking years, should be recorded during registration of death.

Purpose: Prediction models for acute myeloid leukemia (AML) are useful, but have considerable inaccuracy and imprecision. No current model includes covariates related to immune cells in the AML microenvironment. Here, an immune risk score was explored to predict the survival of patients with AML. Experimental Design: We evaluated the predictive accuracy of several in silico algorithms for immune composition in AML based on a reference of multi-parameter flow cytometry. CIBERSORTx was chosen to enumerate immune cells from public datasets and develop an immune risk score for survival in a training cohort using least absolute shrinkage and selection operator Cox regression model. Results: Six flow cytometry–validated immune cell features were informative. The model had high predictive accuracy in the training and four external validation cohorts. Subjects in the training cohort with low scores had prolonged survival compared with subjects with high scores, with 5-year survival rates of 46% versus 19% (P < 0.001). Parallel survival rates in validation cohorts-1, -2, -3, and -4 were 46% versus 6% (P < 0.001), 44% versus 18% (P = 0.041), 44% versus 24% (P = 0.004), and 62% versus 32% (P < 0.001). Gene set enrichment analysis indicated significant enrichment of immune relation pathways in the low-score cohort. In multivariable analyses, high-risk score independently predicted shorter survival with HRs of 1.45 (P = 0.005), 2.12 (P = 0.004), 2.02 (P = 0.034), 1.66 (P = 0.019), and 1.59 (P = 0.001) in the training and validation cohorts, respectively. Conclusions: Our immune risk score complements current AML prediction models.

In recent times, Unmanned-aerial-vehicles (UAVs) have grasped significant attentions for performing various operations without a constant intervention of the human users. Due to the power and computing constraints, however, it is difficult for an UAV to perform all the tasks independently. Hence, to achieve its goals, a UAV may share various sensitive data with the nearest edge servers through some access points (APs). Prior to sending any sensitive information through an AP, it is very important for an UAV to determine the authenticity of the selected AP. In this paper, we have applied a timing-based algorithm for spotting rogue APs by the UAVs − while selecting an edge server. The timing-based algorithm does not require any additional hardware or any change in the network protocol for detection purpose. This fact, in turn, reduces the effort from UAV’s side for detecting a breach. An extensive experimental study shows that with a little manipulation in speed, an UAV can detect the presence of any rogue AP almost every time with only 6% false-positive rate.

Different biomedical computing methods for cancer-specific gene recognition have been developed in recent years. Currently, building an open-box machine learning system to discover explainable knowledge from gene expression data is a difficult research problem due to a large number of genes, a small number of samples, and noise. Fuzzy systems can be used to deal with data ambiguity and noise issues and extract meaningful knowledge from gene data. In this article, we create a new deep fuzzy neural network to handle the uncertainty in gene data to generate useful knowledge for specific disease diagnosis. A new hybrid algorithm is designed to preprocess data and select informative genes for accurate cancer detection. Various experiments using six different cancer datasets indicate that the new method has better and more reliable performance than the other conventional classification methods with different gene selection methods.

With the popularity of smart mobile equipment, the amount of data requested by users is growing rapidly. The traditional centralized processing method represented by the cloud computing model can no longer satisfy the effective processing of large amounts of data. Therefore, the mobile edge computing (MEC) is used as a new computing model to process the big growing data, which can better meet the service requirements. Similar to the task scheduling problem in cloud computing, an important issue in the MEC environment is task offloading and resource allocation. In this paper, we propose an adaptive task offloading and resource allocation algorithm in the MEC environment. The proposed algorithm uses the deep reinforcement learning (DRL) method to determine whether the task needs to be offloaded and allocates computing resources for the task. We simulate the generation of tasks in the form of Poisson distribution, and all tasks are submitted to be processed in the form of task flow. Besides, we consider the mobility of mobile user equipment (UE) between base stations (BSs), which is closer to the actual application environment. The DRL method is used to select the suitable computing node for each task according to the optimization objective, and the optimal strategy for solving the objective problem is learned in the algorithm training process. Compared with other comparison algorithms in different MEC environments, our proposed algorithm has the best performance in reducing the task average response time and the total system energy consumption, improving the system utility, which meets the profits of users and service providers.

The sustainable growth of bandwidth has been an inevitable tendency in current Data Center Networks (DCN). However, the dramatic expansion of link capacity offers a remarkable challenge to the transport layer protocols of DCN, i.e., how to converge fast and enable data flow to utilize the high bandwidth effectively. Meanwhile, the new protocol should be compatible to the traditional TCP because the applications with old TCP versions are still widely deployed. Therefore, it is important to achieve a trade-off between the aggressiveness and TCP-friendliness in protocol design. In this article, we first empirically investigate why the existing typical data center TCP variants naturally fail to guarantee both fast convergence and TCP friendliness. Then, we design a new transport protocol for DCN, namely Fast and Friendly Converging (FFC), which makes independent decisions and self-adjustment through retrieving the two-dimensional congestion notification from both RTT and ECN. We further present a mathematic model to analyze its competing behavior and converging process. The results from simulation experiments and real implementation show that FFC can achieve fast convergence, thus benefiting the flow completion time. Moreover, when coexisting with the traditional TCP, FFC also presents a moderate behavior, while introducing trivial deployment overhead only at the end-hosts.

BACKGROUND Most patients with actinic keratosis (AK) present with more than one lesion. Although histopathological examination is the gold standard for diagnosing this condition, performing an invasive skin biopsy for each AK is impractical. Thus, this study aimed to identify AK's morphological characteristics based on harmonic generation microscopy (HGM). Moreover, the correlation between features observed using HGM and histopathological grading of AK was examined. METHODS Lesions of seven patients were examined using HGM (n = 1, ex vivo and n = 6, in vivo), and histopathological examinations of the biopsy specimens were also performed. The features of each AK, based on HGM, were assessed and compared with corresponding standard histopathological findings. RESULTS Using the histopathological findings as a standard reference, HGM's accuracy in detecting features of AK lesions, such as hyperkeratosis, epidermal thinning, abnormal architecture, and atypical honeycomb pattern, was 100%. Approximately five (72%) patients had similar histopathological grades. Moreover, based on HGM, except for one patient with grade 1 AK, six (85.71%) patients had lesions with intraepidermal dendritic cell-like cells, representing melanocytes. CONCLUSION Harmonic generation microscopy can be used in vivo to provide critical diagnostic information with a resolution comparable to histopathological examination. In addition, intralesional melanocytes in AK, which may be correlated with disease severity, can be specifically enhanced using HGM.

The classification of mild cognitive impairment (MCI), which is a early stage of Alzheimer’s disease and is associated with brain structural and functional changes, is still a challenging task. Recent studies have shown great promise for improving the performance of MCI classification by combining multiple structural and functional features, such as grey matter volume and clustering coefficient. However, extracting which features and how to combine multiple features to improve the performance of MCI classification have always been challenging problems. To address these problems, in this study we propose a new method to enhance the feature representation of multi-modal MRI data by combining multi-view information to improve the performance of MCI classification. Firstly, we extract two structural features (including grey matter volume and cortical thickness) and two functional features (including clustering coefficient and shortest path length) of each cortical brain region based on automated anatomical labeling (AAL) atlas from both T1w MRI and rs-fMRI data of each subject. Then, in order to obtain features that are more helpful in distinguishing MCI subjects, an improved multi-task feature selection method, namely MTFS-gLASSO-TTR, is proposed. Finally, a multi-kernel learning algorithm is adopted to combine multiple features to perform the MCI classification task. Our proposed MCI classification method is evaluated on 315 subjects (including 105 LMCI subjects, 105 EMCI subjects and 105 NCs) with both T1w MRI and rs-fMRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results show that our proposed method achieves an accuracy of 88.5% and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.897 for LMCI/NC classification, an accuracy of 82.7% and an AUC of 0.832 for EMCI/NC classification, and an accuracy of 79.6% and an AUC of 0.803 for LMCI/EMCI classification, respectively. In addition, by comparison, the accuracy and AUC values of our proposed method are better than those of some existing state-of-the-art methods in MCI classification. Overall, our proposed MCI classification method is effective and promising for automatic diagnosis of MCI in clinical practice.

Background During psoriasis initiation and development, deregulations in signalling pathways and gene expression are observed. Methods Herein, we downloaded seven sets of microarray mRNA expression profiles showing differentially expressed genes in psoriasis lesion skin and non-lesion skin tissues and three sets of RNA-seq data and analysed these online data attempting to screen for crucial genes related to keratinocyte proliferation and psoriasis development. The expression of CTNNBIP1 in psoriasis patients and IMQ mouse model skin tissues were examined by RT-PCR, immunoblotting and IHC. The functions of CTNNBIP1 on HaCaT cell proliferation, apoptosis and β-catenin/TCF complex were measured by MTT, EdU, flow cytometry, IF, luciferase assays and immunoblotting. Results The expression of catenin beta interacting protein 1 (CTNNBIP1) was remarkably downregulated within psoriasis lesion skin tissue samples compared to that within non-lesion skin tissues based on both online data and experimental results. In response to a period of different therapies, respectively, CTNNBIP1 expression could be rescued in lesion skin tissues. Within IMQ-induced psoriasis-like dermatitis in mice, CTNNBIP1 silence further aggravated psoriatic phenotypes. In human immortalized keratinocytes, HaCaT cells, CTNNBIP1 silence significantly inhibited cell apoptosis and promoted cell proliferation. Regarding the molecular mechanism, CTNNBIP1 silence in HaCaT cells promoted β-catenin nucleus translocation, enhanced the transcriptional activity of TCF4 and increased β-catenin/TCF complex downstream c-Myc and cyclin D1 proteins, and also increased the expression of cell proliferation marker ki-67. In contrast to CTNNBIP1, the expression of c-Myc and cyclin D1 showed to be dramatically upregulated within psoriasis lesion tissue samples than that within non-lesion tissue samples. Within tissues, c-Myc and cyclin D1 showed to be negatively correlated with CTNNBIP1, respectively. Conclusions We identify CTNNBIP1 as an abnormally downregulated gene in psoriasis. CTNNBIP1 silence significantly disturbs the proliferation of keratinocytes through promoting the transcription of β-catenin/TCF complex downstream genes.

Purpose: Adults with T-cell lymphoblastic lymphoma (T-LBL) generally benefit from treatment with acute lymphoblastic leukemia (ALL)-like regimens, but approximately 40% will relapse after such treatment. We evaluated the value of CpG methylation in predicting relapse for adults with T-LBL treated with ALL-like regimens. Experimental Design: A total of 549 adults with T-LBL from 27 medical centers were included in the analysis. Using the Illumina Methylation 850K Beadchip, 44 relapse-related CpGs were identified from 49 T-LBL samples by two algorithms: least absolute shrinkage and selector operation (LASSO) and support vector machine–recursive feature elimination (SVM-RFE). We built a four-CpG classifier using LASSO Cox regression based on association between the methylation level of CpGs and relapse-free survival in the training cohort (n = 160). The four-CpG classifier was validated in the internal testing cohort (n = 68) and independent validation cohort (n = 321). Results: The four-CpG–based classifier discriminated patients with T-LBL at high risk of relapse in the training cohort from those at low risk (P < 0.001). This classifier also showed good predictive value in the internal testing cohort (P < 0.001) and the independent validation cohort (P < 0.001). A nomogram incorporating five independent prognostic factors including the CpG-based classifier, lactate dehydrogenase levels, Eastern Cooperative Oncology Group performance status, central nervous system involvement, and NOTCH1/FBXW7 status showed a significantly higher predictive accuracy than each single variable. Stratification into different subgroups by the nomogram helped identify the subset of patients who most benefited from more intensive chemotherapy and/or sequential hematopoietic stem cell transplantation. Conclusions: Our four-CpG–based classifier could predict disease relapse in patients with T-LBL, and could be used to guide treatment decision.

The ten papers in this special section are devoted to the most recent developments and research outcomes addressing the related theoretical and practical aspects of computational intelligence solutions in sustainable computing and aims at presenting latest innovative ideas targeted at the corresponding key challenges, either from a methodological or from an application perspective.

Industrial Internet of Things (IIoT) has been widely used in many fields. Meanwhile, blockchain is considered promising to address the issues of the IIoT. However, the current blockchains have a limited throughput. In this article, we devise an efficient and secure blockchain protocol compacted directed acyclic graph (CoDAG) based on a compacted directed acyclic graph, where blocks are organized in levels and width. New-generated blocks in the CoDAG will be placed appropriately and point to those in the previous level, making it a well-connected channel. Transactions in the network will be confirmed in a deterministic period, and the CoDAG keeps a simple data structure at the same time. We also illustrate the attack strategies by adversary, and it is proved that our protocols are resistant to these attacks. Furthermore, we design a CoDAG-based IIoT architecture to improve the efficiency of the IIoT system. Experimental results show that the CoDAG achieves 164 $\times$ Bitcoin's throughput and 77 $\times$ Ethererum's throughput.

With the development of Internet of Things (IoT), edge computing becomes more and more prevalent currently. However, edge computing needs to deploy a large number of edge servers to reduce the communication latency, which will bring additional costs to the system. Although there exist some idle computing resources at the edge, the owners distrust each other and lack the incentives to contribute to the system. In this article, we propose a new edge computing platform decentralized and trusted platform for edge computing (DeTEC), which provides a unified interface to users, resolves the user’s requests to the most appropriate edge server through domain name server, and returns the computational results to the IoT user. To build a trustworthy system, DeTEC integrates the blockchain technology with edge computing, such that the contributions of each participant could be accounted and rewarded. We formulate the task allocation problem, taking both node capacity and reward fairness into consideration, and solve it through a heuristic algorithm. Finally, to guarantee the trustworthiness of computational results, we utilize a police patrol model and try to optimize the system overall reward. We implement DeTEC based on an open source project and conduct comprehensive experiments to test its performance. The results show that our DeTEC system works well in the IoT scenario.

Purpose: To investigate the effect of bisleuconothine A (BA), alone and in combination with hyperbaric oxygen (HO), on traumatic brain injury (TBI) in rats. Methods: Traumatic brain injury (TBI) was induced by dropping a 200-g weight of steel on the left anterior frontal areas of Sprague-Dawley rats. The synergistic effect of BA and HO was determined by assessing neurological score, as well as parameters of oxidative stress and inflammation, expressions of P2X4 protein and other proteins, and levels of reactive oxygen species (ROS) in the brain tissues of TBI rats. Results: Neurological function score, levels of inflammatory mediators and oxidative stress parameters were significantly reduced in rats treated with BA alone, and in those treated with a combination of BA and HO, when compared with untreated TBI rats (p < 0.01). Moreover, treatment with BA alone, and BA-HO combination attenuated the altered protein expressions of P2X4, Akt, PI3K and TLR-4 in the TBI rats, and also upregulated the mRNA expression of P2X4 in the brain tissue, when compared with untreated TBI rats (p < 0.01). Conclusion: These results suggest that BA, when used alone or in combination with HO, reduces neuronal injury through upregulation of the protein expression of P2X4 in rats with traumatic brain injury. Thus, BA may be used clinically with HO therapy for the management of traumatic injury. Keywords: Bisleuconothine A, Hyperbaric oxygen, Neuronal injury, Oxidative stress, Inflammatory mediators

Cloud computing offers a cost-effective and elastic computing paradigm that facilitates large scale data storage and analytics. By deploying virtualization technologies in the datacenter, cloud enables efficient resource management and isolation for various big data applications. Since the hotspots (i.e., overloaded machines) can degrade the performance of these applications, virtual machine migration has been utilized to perform load balancing in the datacenters to eliminate hotspots and guarantee Service Level Agreements (SLAs). However, the previous load balancing schemes make migration decisions based on deterministic resource demand estimation and workload characterization, without considering their stochastic properties. By studying real world traces, we show that the resource demand and workload of virtual machines are highly dynamic and bursty, which can cause these schemes to make inefficient migrations for load balancing. To address this problem, in this paper we propose a stochastic load balancing scheme which aims to provide probabilistic guarantee against the resource overloading with virtual machine migration, while minimizing the total migration overhead. Our scheme effectively addresses the prediction of the distribution of resource demand and the multidimensional resource requirements with stochastic characterization. Moreover, as opposed to the previous works that measure the migration cost without considering the network topology, our scheme explicitly takes into account the distance between the source physical machine and the destination physical machine for a virtual machine migration. The trace-driven experiments show that our scheme outperforms the previous schemes in terms of SLA violation and the migration cost.

Pulmonary arterial hypertension (PAH) is a rare, but progressive and devastating vascular disease with few treatment options to prevent the advancement to right ventricular dysfunction hypertrophy and failure. Empagliflozin, a sodium-glucose cotransporter 2 (SGLT2) inhibitor, enhances urinary glucose excretion as well as reduces cardiovascular events and mortality in individuals with type 2 diabetes. While empagliflozin has been reported to lower systemic hypertension due to increased diuresis, the effect of empagliflozin on PAH is unknown. We used monocrotaline (MCT)-treated Sprague-Dawley rats to determine if empagliflozin alters PAH-associated outcomes. Compared to vehicle control, daily empagliflozin administration significantly improved survival in rats with severe MCT-induced PAH. Hemodynamic assessments showed that empagliflozin treatment significantly reduced mean pulmonary artery pressure, right ventricular systolic pressure, and increased pulmonary acceleration time. Empagliflozin treatment resulted in reduced right ventricular hypertrophy and fibrosis. Histological and molecular assessments of lung vasculature revealed significantly reduced medial wall thickening and decreased muscularization of pulmonary arterioles after empagliflozin treatment compared to vehicle-treated rats. In summary, SGLT2 inhibition with empagliflozin lowered mortality, reduced right ventricle systolic pressure, and attenuated maladaptive pulmonary remodeling in MCT-induced PAH. Clinical studies evaluating the efficacy of SGLT-2 inhibition should be considered for patients with PAH.

The TIPE2 (tumor necrosis factor-alpha-induced protein 8-like 2) protein is a major regulator of cancer and inflammatory diseases. The availability of its sequence and structure, as well as the critical amino acids involved in its ligand binding, provides insights into its function and helps greatly identify novel drug candidates against TIPE2 protein. With the current advances in deep learning and molecular dynamics simulation-based drug screening, large-scale exploration of inhibitory candidates for TIPE2 becomes possible. In this work, we apply deep learning-based methods to perform a preliminary screening against TIPE2 over several commercially available compound datasets. Then, we carried a fine screening by molecular dynamics simulations, followed by metadynamics simulations. Finally, four compounds were selected for experimental validation from 64 candidates obtained from the screening. With surprising accuracy, three compounds out of four can bind to TIPE2. Among them, UM-164 exhibited the strongest binding affinity of 4.97 µM and was able to interfere with the binding of TIPE2 and PIP2 according to competitive bio-layer interferometry (BLI), which indicates that UM-164 is a potential inhibitor against TIPE2 function. The work demonstrates the feasibility of incorporating deep learning and MD simulation in virtual drug screening and provides high potential inhibitors against TIPE2 for drug development.

Purpose: To study the clinical effect of combining insulin aspart with different drugs in the treatment oftype 2 diabetes mellitus (T2DM).Methods: Two hundred and thirty-seven T2DM patients admitted to the Endocrinology Department of the Second Affiliated Hospital of Kunming Medical University from March to September 2018 were selected as subjects in this study. Miglitol and metformin were used in combination with insulin aspart in the treatment of T2DM. In addition, data on the effectiveness and safety of different treatment options,such as patient’s weight, waist circumference, blood glucose indicators, indices of heart, liver and kidney functions, and incidence of complications were recorded and compared between the two groups.Results: The use of a combination of miglitol and insulin aspart produced an excellent hypoglycaemic effect, and it significantly reduced the incidence of sensory neuropathy in the eyes and distal limbs (p < 0.05). The use of combination of metformin and insulin aspart effectively protected the heart and kidney, and prevented hypoglycaemia (p < 0.05).Conclusion: These results suggest that treatment with a combination of miglitol and insulin aspart is suitable for patients with T2DM whose blood sugar levels are out of control, while combined treatment with metformin and insulin aspart is more suited for patients who desire to reduce blood sugar and blood lipids through weight loss, and patients with cardiac and renal insufficiency.

In the field of computer vision, the research on 3D point clouds is one of the important tasks of 3D scene understanding, such as target detection, semantic segmentation, etc., which have achieved rich research results. Combining the concepts of target detection and semantic segmentation, it is not only necessary to identify point clouds of different semantics, but also to distinguish instances of the same semantics. Therefore, the research on 3D point cloud instance segmentation will be more challenging. The results of most instance segmentation methods have found that if the distances between different objects of the same semantic are too close, it is difficult to distinguish them from each other, resulting in poor accuracy of instance segmentation. In order to improve this problem, based on the method of a deep learning instance segmentation of the 3D point cloud scene, the 3D object point cloud with the same semantic meaning and the same color label is transferred in to the voxel space. The voxels of an object is then projected onto the 2D image from the top view. At last, the image segmentation for post-processing is utilized to further improve the accuracy of instance segmentation.

Objective: Puerarin has been proven to treat diverse cancers, but its function on ovarian cancer (OC) is still blurry and needs further research.Methods: After OC cells were treated with 10, 20, 40, 80, or 160 μg/mL pue, cell vitality, colony number, apoptosis, the positive expression of P53, migration, and invasion were examined by cell function experiments, TUNEL staining, and immunofluorescence. P53, P21, PTEN, FGF1, GLI2, and ERK1/2-NF-κB pathway-related marker expressions were examined by western blot. Results: Pue weakened the OC cell vitality, colony number, and the positive expression of P53 but enhanced apoptosis in a dose-dependent manner. Next, we discovered that pue enhanced the P53, P21, PTEN, and GLI2 levels but restrained the FGF1 level. Pue also alleviated the OC cell migration and invasion activity. We also confirmed that pue weakened the ERK1/2-NF-κB pathway-related marker expressions.Conclusion: Puerarin restrained the OC progression via modulating P53 and PTEN expressions.

We aimed to establish a discriminative gene-expression-based classifier to predict survival outcomes of T-cell lymphoblastic lymphoma (T-LBL) patients. After exploring global gene-expression profiles of progressive (n = 22) vs. progression-free (n = 28) T-LBL patients, 43 differentially expressed mRNAs were identified. Then an eleven-gene-based classifier was established using LASSO Cox regression based on NanoString quantification. In the training cohort (n = 169), high-risk patients stratified using the classifier had significantly lower progression-free survival (PFS: hazards ratio 4.123, 95% CI 2.565–6.628; p

The dramatic spread of online social network services, such as Facebook, Twitter, Instagram, and Google+, has led to increasing awareness of the power of incorporating social elements into a variety of data-centric applications. These applications, in recent years, apply various sensors with social media platforms to continuously collect massive data that can be directly associated with human interactions. This phenomenon has led to the creation of numerous social sensing systems, such as Biketastic, BikeNet, CarTel, and Pier, which use social sensors (i.e., users) for a variety of social sensing systems and applications. Social sensing has become an emerging and promising sensing paradigm that relies on the voluntary cooperation of users equipped with embedded or integrated sensors.

Cloud computing is recently getting increasingly popular for supporting scientific applications and complex business processes. Clouds are highly potent for executing workflow-based tasks due to the fact that they provide elastic resource provisioning styles through which computational-intensive workflows can obtain requested resources according to their elastic demand and establish execution environment over virtual machines (VMs). However, it remains a challenge to guarantee cost-effectiveness and quality of service of workflow deployed upon clouds due to the fact that real-world cloud infrastructures are usually with fluctuating and time-varying performance. Existing researches mainly consider that cloud infrastructures are with fixed, random, or bounded quality of service (QoS). In this work, however, we consider that scientific computing processes to be supported by decentralized cloud infrastructures with fluctuating QoS and aim at managing the monetary cost of workflows with the completion-time constraint to be satisfied. We address the performance-variation-aware workflow scheduling problem by leveraging a time-series-based prediction model and a Critical-Path-Duration-Estimation-based (CPDE for short) VM Selection strategy. The proposed method is capable of exploiting real-time trends of performance changes of cloud infrastructures and generating dynamic workflow scheduling plans. To prove the effectiveness of our proposed method, we perform extensive experimental case analysis over real-world third-party commercial clouds and show that our method clearly beats existing approaches.