Search

Objectives: Cigarette smoking is involved in the pathogenesis of head and neck squamous cell carcinoma (HNSCC). However, the underlying molecular mechanisms of cigarette smoking-induced HNSCC carcinogenesis are unclear and may involve cancer stem-like cell generation. We examined the effects of cigarette smoke condensate (CSC) on the formation of cancer stem-like cells, which are rich in octamer-binding transcription factor (OCT)-4, inhibitor of differentiation 1 (ID1), nuclear factor (NF)-κB, and B lymphoma Mo-MLV insertion region 1 homolog (BMI-1). Materials and Methods: We used in vitro, in vivo, and archival human HNSCC tissue analysis to evaluate the effects of CSC on cancer stem-like cell formation. Results: We found that CSC regulated OCT-4 expression, which subsequently regulated ID1 and NF-κB, at the promoter, mRNA, and protein levels in vitro. Furthermore, OCT-4 knockdown with siRNA reduced ID1 expression. ID1 and NF-κB synergistically increased the expression of BMI-1 and stimulated keratinocyte sphere generation. In vivo, ID1 and NF-κB acted together to generate malignant xenograft tumors, which were aggressive locally and systemically metastatic. Clinical data confirmed that ID1- and NF-κB-positive patients had poor clinical outcomes and 5-year disease-free survival. Conclusion: Our data suggest that smoking cigarettes promoted cancer stem-like cell generation in the head and neck area via the OCT-4/ID1/NF-κB/BMI-1 signaling pathway.

In this paper1, we proposed an explainable deep neural networks (DNN)-based method for automatic detection of COVID-19 symptoms from chest radiography (CXR) images, which we call 'DeepCOVIDExplainer'. We used 15,959 CXR images of 15,854 patients, covering normal, pneumonia, and COVID-19 cases. CXR images are first comprehensively preprocessed and augmented before classifying with a neural ensemble method, followed by highlighting class-discriminating regions using gradient-guided class activation maps (Grad-CAM ++) and layer-wise relevance propagation (LRP). Further, we provide human-interpretable explanations for the diagnosis. Evaluation results show that our approach can identify COVID-19 cases with a positive predictive value (PPV) of 91.6%, 92.45%, and 96.12%, respectively for normal, pneumonia, and COVID-19 cases, respectively, outperforming recent approaches.1Read longer version of this paper: https://arxiv.org/pdf/2004.04582.pdf

Complex Event Processing (CEP) is a powerful paradigm for scalable data management that is employed in many real-world scenarios such as detecting credit card fraud in banks. The so-called complex events are expressed using a specification language that is typically implemented and executed on a specific runtime system. While the tight coupling of these two components has been regarded as the key for supporting CEP at high performance, such dependencies pose several inherent challenges as follows. (1) Application development atop a CEP system requires extensive knowledge of how the runtime system operates, which is typically highly complex in nature. (2) The specification language dependence requires the need of domain experts and further restricts and steepens the learning curve for application developers. In this paper, we propose CEPLESS, a scalable data management system that decouples the specification from the runtime system by building on the principles of serverless computing. CEPLESS provides operator as a service and offers flexibility by enabling the development of CEP application in any specification language while abstracting away the complexity of the CEP runtime system. As part of CEPLESS, we designed and evaluated novel mechanisms for in-memory processing and batching that enables the stateful processing of CEP operators even under high rates of ingested events. Our evaluation demonstrates that CEPLESS can be easily integrated into existing CEP systems like Apache Flink while attaining similar throughput under a high scale of events (up to 100K events per second) and dynamic operator update in up to 238 ms., 10 pages, Published in the Proceedings of the IEEE International Conference on Big Data

Sensor-based applications using Big Data are of increasing importance in various fields. A typical example of such use cases is building health-care applications [1], [2]. A typical scenario is where a patient's heart rate is monitored by a smartwatch. A smartphone can then analyze the gathered data and identify patterns in the patient's heart rate. However, if the data analysis is too complex to be performed on a smartphone, the computation could be offloaded to a nearby cloudlet or a remote cloud. A decision usually follows the analysis, and actuation is performed accordingly (e.g., a message is sent to either the patient or the doctor). Developing such an application is intrinsically complex, as the programmer needs to reconcile different APIs specific to different platforms.

The COVID-19 pandemic has generated an overall slowdown in hospital activities that might lead to delays in healthcare interventions, and the scarcity of resources can raise concerns about ventilators allocation criteria. These circumstances could lead to lawsuits against hospitals and healthcare professionals: together with Regions and States, they may be vulnerable to legal actions, due to the breach of right to health, to physical integrity and right to life, to the manifestation of the informed consent in the medical field or on the basis of contractual or Aquilian obligations. In this context, predicting the litigation rate could be useful to assess the economic impact of a dispute at a local and national level, so that hospital managers and public institutions can perform multi-dimensional and cost/benefit evaluations to decide whether to invest resources to increase critical care surge capacity. In this work we present CLIP (COVID-19 LItigation Prediction), a modeling approach supported by swarm intelligence designed to forecast the occupancy of intensive care units using COVID-19 time-series. CLIP fits a logistic model of COVID-19 patients admission in order to estimate the future number of patients, and then exploits a probabilistic model to predict the number of occupied intensive care beds, whose parameters are calibrated by means of Fuzzy Self-Tuning Particle Swarm Optimization. We assume that each individual rejected from an intensive care unit due to the lack of resources should be considered a potential plaintiff. The development and the availability of such a predictive model, that could further be used within other clinical conditions and important diseases, could help policy-makers in taking decisions under conditions of uncertainty.

Active learning is a technique that helps to minimize the annotation budget required for the creation of a labeled dataset while maximizing the performance of a model trained on this dataset. It has been shown that active learning can be successfully applied to sequence tagging tasks of text processing in conjunction with deep learning models even when a limited amount of labeled data is available. Recent advances in transfer learning methods for natural language processing based on deep pre-trained models such as ELMo and BERT offer a much better ability to generalize on small annotated datasets compared to their shallow counterparts. The combination of deep pre-trained models and active learning leads to a powerful approach to dealing with annotation scarcity. In this work, we investigate the potential of this approach on clinical and biomedical data. The experimental evaluation shows that the combination of active learning and deep pre-trained models outperforms the standard methods of active learning. We also suggest a modification to a standard uncertainty sampling strategy and empirically show that it could be beneficial for annotation of very skewed datasets. Finally, we propose an annotation tool empowered with active learning and deep pre-trained models that could be used for entity annotation directly from Jupyter IDE.

GDPR (General Data Protection Regulation) is a new regulation of the European Union that superimposes strict privacy constraints on storing, accessing and processing user data, as a way to ensure that personal user data are not violated neither disclosed without an explicit consent. As a consequence, business processes that interact with large amounts of such data may easily cause GDPR violations, due to the typical complexity of such processes. Inspired by these considerations, this paper highlights the challenges and critical aspects associated with the GDPR compliance journey when opting for naïve straight-forward solutions. We propose a business-aware GDPR compliance journey using online process mining. Using several large log files generated based on a real scenario, we show that the proposed tool is both effective and efficient. As such, it proves to be a powerful concept for usage in incremental GDPR compliance environments.

To help scholars to extract meaning, knowledge and value from large volumes of archival content, such as the Dutch Common Lab Research Infrastructure for the Arts and Humanities (CLARIAH), we need to provide more ‘generous’ access to the data than can be provided with generalised search and visualisation tools alone. Our approach is to use Jupyter Notebooks in combination with the existing archive APIs (Application Programming Interface). This gives access to both the archive metadata and a wide range of analysis and visualisation techniques. We have created notebooks and modules of supporting functions that enable the overview, investigation and analysis of the archive. We demonstrate the value of our approach in preliminary tests of its use in scholarly research, and give our observations of the potential value for archivists. Finally, we show that good archive knowledge is essential to create correct and meaningful visualisations and statistics.

Computerized safety checklist systems designed for improving care-givers' situation awareness are emerging in recent years. These systems are proved to be effective for improving adherence to guidelines while keeping high user acceptance. However, most of these systems are still hard-coded since it is yet unclear to what extent can existing guideline modeling languages capture the requirements for such a type of systems. This paper answers this research question by carrying out three case studies using three distinct and representative type of guideline languages. The expressiveness, interoperability, and maintainability of these three languages are compared against the requirements of typical computerized safety checklists. The results indicate all of these languages can partially support the requirements of computerized safety checklists. Whereas some important features of computerized checklists are not yet covered these languages.

Clinical guidelines, pathways and protocols are introduced to standardize and provide best-practice care. Analyzing deviations of actual care against the documented best practices is useful to find opportunities for complying better in the future. Prior work demonstrates that deviation analyses should be accurate, automated and insightful but only few studies manage to satisfy all three intentions. In this paper, we manage to reconcile accuracy with automation and insightfulness by combining the previously disconnected steps of checking and mining in compliance analysis software. Results are achieved using an algorithm that consists of three steps. We demonstrate the effectiveness of the algorithm via a real-life case from the intensive care unit of a Dutch hospital.

A double-grating rectangular waveguide with a round beam channel is proposed as the slow-wave interaction structure of a 310GHz travelling wave tube (TWT). We describe the fabrication of the slow wave structure and the assembly method of RF windows.

The meaning of the term 'Big Data' is still subject to debate, in spite of being widely used in biomedical publications. This confusion in definition leads to missed opportunities for peers to exchange knowledge and practices. A better understanding of Big Data may help researchers to identify themselves with the Big Data community. In this study, we investigate the most distinguishing features in 'Big Data'-labelled publications by comparing them against publication without this label (non-Big Data), using text mining and machine learning methods. Furthermore, the usage of the term Big Data was analysed over time. Our models could successfully make a distinction between publications labelled with 'Big Data' and those without. The most distinguishing features consisted of terms such as 'omics', 'computing', 'storage', and 'mining'. We observed that publications that do not use the term Big Data may also address topics that fall under well-accepted definitions of Big Data. Trends suggest that, while the use of the term Big Data increased, it is used less reliably now as compared to earlier years.

OSAHS is a common disease with many factors related to the etiology. Airflow plays an important role in the pathogenesis of OSAHS. Previous research has not yielded a sufficient understanding of the relationship between airflow in upper airway and the pathophysiology of OSAHS. Therefore, a better understanding of the flow inside the upper airway in an OSAHS patient is necessary. In this study, ten Chinese adults with OSAHS were recruited. We used the software MIMICS 13.1 to construct 3-dimensional (3-D) models based on the computer tomography scans of them. The numerical simulations were carried out using the software ANSYS 12.0. We found that during the inhalation phase, the vortices and turbulences were located in both the anterior part of the cavity and nasopharynx. But there is no vortex in the whole nasal cavity during the expiratory phase. The airflow velocity is much higher than that of the normal models. The distributions of pressure and wall shear stress are different in two phases. The maximum velocity, pressure and wall shear stress (WSS) are located in velopharynx. It is notable that a strong negative pressure region is found in pharyngeal airway. The maximum velocity is 19.26 ± 12.4 and 19.46 ± 13.1 m/s; the average pressure drop is 222.71 ± 208.84 and 238.5 ± 218.56 Pa and the maximum average WSS is 0.72 ± 0.58 and 1.01 ± 0.61 Pa in inspiratory and expiratory, respectively. The changes of airflow due to the structure changes play an important role in the occurrence of collapse and obstruction of the upper airway, especially, the abnormal pressure changes in velopharyngeal during both inspiratory and expiratory phases. We can say that the airway narrowing in the pharynx may be one of the most important factors driving airway collapse. In addition, the most collapsible region of the pharyngeal airway of the patient with OSAHS may be the velopharynx and oropharynx. In spite of limitations, our results can provide a basis for the further research. On this basis, more about the secret of the pathogenesis of the OSAHS will be revealed.

Time series classification (TSC) is home to a number of algorithm groups that utilise different kinds of discriminatory patterns. One of these groups describes classifiers that predict using phase dependant intervals. The time series forest (TSF) classifier is one of the most well known interval methods, and has demonstrated strong performance as well as relative speed in training and predictions. However, recent advances in other approaches have left TSF behind. TSF originally summarises intervals using three simple summary statistics. The ‘catch22' feature set of 22 time series features was recently proposed to aid time series analysis through a concise set of diverse and informative descriptive characteristics. We propose combining TSF and catch22 to form a new classifier, the Canonical Interval Forest (CIF). We outline additional enhancements to the training procedure, and extend the classifier to include multivariate classification capabilities. We demonstrate a large and significant improvement in accuracy over both TSF and catch22, and show it to be on par with top performers from other algorithmic classes. By upgrading the interval-based component from TSF to CIF, we also demonstrate a significant improvement in the hierarchical vote collective of transformation-based ensembles (HIVE-COTE) that combines different time series representations. HIVE-COTE using CIF is significantly more accurate on the UCR archive than any other classifier we are aware of and represents a new state of the art for TSC.

Early detection of adverse events at hospitals could be useful in terms of reducing costs, morbidity, and mortality. Therefore, in this paper, we present a personalized real-time hybrid model based on Nonlinear Autoregressive Exogenous (NARX) model and Ensemble Learning (EL) to predict patients' severity during hospitalization at Emergency Departments (ED). This model utilizes vital signs of patients, including Pulse Rate (PR), Respiratory Rate (RR), Arterial Blood Oxygen Saturation (SpO2) and Systolic Blood Pressure (SBP), which are collected automatically during the treatment to predict the illness severity of hospitalized patients at ED in the next hour based on their vital signs of the previous two hours. Two EL algorithms, including Random Forest (RF) and Adaptive Boosting (AdaBoost) are considered to build hybrid models. The performance of NARX-EL models is compared with Auto Regressive Integrated Moving Average (ARIMA), combination of NARX and Linear Regression (LR), Support Vector Regression (SVR) and K-Nearest Neighbors Regression (KNN). The results show that our proposed hybrid models can predict patients' severity with significantly higher accuracy. It is also found that NARX-RF has the best performance in the prediction of sudden changes and unexpected adverse events in patients' vital signs (R 2 score =0.978, NRMSE =6.16%).

Road damages are of great interest for federal road authorities and their infrastructure management as well as the automated driving task and thus safety and comfort of vehicle occupants. Therefore, we are investigating the automatic detection of different types of road damages by images from a front-facing camera in the vehicle. The data basis of our work is provided by the ’IEEE BigData Cup Challenge’ and its dataset ’RDD-2020’ with a large number of labelled images from Japan, India and the Czech Republic. Our Deep Learning approach utilizes the pre-trained Faster Region Based Convolutional Neural Networks (R-CNN). In the first step, we classify the destination of the image followed by expert networks for each region. Between the explanation of our applied Deep Learning methodology, some remaining sources of errors are discussed and further, partly failed approaches during our development period are displayed, which could be of interest for future work. Our results are convincing and we are able to achieve an F1 score of 0 . 487 across all regions for longitudinal and lateral cracks, alligator cracks and potholes.

Deep learning-based technology is a good key to unlock the object detection tasks in our real world. By using deep neural networks, we could break a problem that is dangerous and very time-consuming but has to be done every day like detecting the road state. This paper describes the solution using YOLO to detect the various types of road damage in the IEEE BigData Cup Challenge 2020. Our YOLOv5x based-solution is light-weight and fast, even it has good accuracy. We achieved an F1 score of 0.58 using our ensemble model with TTA, and it could be an adequate candidate for detecting real road damage in real-time.

A ubiquitous problem in aggregating data across different experimental and observational data sources is a lack of software infrastructure that enables flexible and extensible standardization of data and metadata. To address this challenge, we developed HDMF, a hierarchical data modeling framework for modern science data standards. With HDMF, we separate the process of data standardization into three main components: (1) data modeling and specification, (2) data I/O and storage, and (3) data interaction and data APIs. To enable standards to support the complex requirements and varying use cases throughout the data life cycle, HDMF provides object mapping infrastructure to insulate and integrate these various components. This approach supports the flexible development of data standards and extensions, optimized storage backends, and data APIs, while allowing the other components of the data standards ecosystem to remain stable. To meet the demands of modern, large-scale science data, HDMF provides advanced data I/O functionality for iterative data write, lazy data load, and parallel I/O. It also supports optimization of data storage via support for chunking, compression, linking, and modular data storage. We demonstrate the application of HDMF in practice to design NWB 2.0 [13], a modern data standard for collaborative science across the neurophysiology community.

Energy systems are evolving towards 100% green energy production. The share of green energy in electrical distribution systems is progressively increasing, implying also an increment on the number of renewable energy units in the low-voltage grid. Following this trend, thousands of consumers connected to the power grid in a decentralized manner become small producers, changing the traditional paradigm of energy distribution from top to bottom. Currently, the modern Advanced Metering Infrastructure (AMI) enables the possibility of collecting several types of status data from the end-users which Distribution System Operators (DSOs) can use to their advantage to optimize management and planning operations. As a part of this optimization, having a spatial overview over the low-voltage grid can speed up the monitoring processes and allows to obtain a real-time insight on what is happening in the grid, compared to the traditionally used analysis methods. Many business structures for smart grid cyber physical systems are looking into how to integrate advanced data management models. Such models should provide the means for obtaining meaningful data visualization where only the relevant data is timely processed, filtered and visualized for the operators to efficiently react to grid anomalies in real-time.The purpose of this paper is to investigate how to efficiently design a monitoring/visualization system for low-voltage electrical grids based on the DSOs’ needs and feedback. The proposed system implementation stands on emulating an existing geographic scenario by a virtual AMI integration. The efficiency of the prototype is evaluated versus the traditional monitoring operations derived from user experience studies, such as a reduction in time to perform a specific anomaly detection operation. Furthermore, the advantages of spatial awareness are meant to further strengthen the motivation for integrating measurements into a Geographic Information System (GIS) environment.

Natural Language Inference (NLI) is a fundamental step towards natural language understanding. The task aims to detect whether a premise entails or contradicts a given hypothesis. NLI contributes to a wide range of natural language understanding applications such as question answering, text summarization and information extraction. Recently, the public availability of big datasets such as Stanford Natural Language Inference (SNLI) and SciTail, has made it feasible to train complex neural NLI models. Particularly, Bidirectional Long Short-Term Memory networks (BiLSTMs) with attention mechanisms have shown promising performance for NLI. In this paper, we propose a Combined Attention Model (CAM) for NLI. CAM combines the two attention mechanisms: intra-attention and inter-attention. The model first captures the semantics of the individual input premise and hypothesis with intra-attention and then aligns the premise and hypothesis with inter-sentence attention. We evaluate CAM on two benchmark datasets: Stanford Natural Language Inference (SNLI) and SciTail, achieving 86.14% accuracy on SNLI and 77.23% on SciTail. Further, to investigate the effectiveness of individual attention mechanism and in combination with each other, we present an analysis showing that the intra- and inter-attention mechanisms achieve higher accuracy when they are combined together than when they are independently used.

Machine Learning (ML) techniques now impact a wide variety of domains. Highly regulated industries such as healthcare and finance have stringent compliance and data governance policies around data sharing. Advances in secure multiparty computation (SMC) for privacy-preserving machine learning (PPML) can help transform these regulated industries by allowing ML computations over encrypted data with personally identifiable information (PII). Yet very little of SMC-based PPML has been put into practice so far. In this paper we present the very first framework for privacy-preserving classification of tree ensembles with application in healthcare. We first describe the underlying cryptographic protocols that enable a healthcare organization to send encrypted data securely to a ML scoring service and obtain encrypted class labels without the scoring service actually seeing that input in the clear. We then describe the deployment challenges we solved to integrate these protocols in a cloud based scalable risk-prediction platform with multiple ML models for healthcare AI. Included are system internals, and evaluations of our deployment for supporting physicians to drive better clinical outcomes in an accurate, scalable, and provably secure manner. To the best of our knowledge, this is the first such applied framework with SMC-based privacy-preserving machine learning for healthcare.

The recent boom of big data, coupled with the challenges of its processing and storage gave rise to the development of distributed data processing and storage paradigms like MapReduce, Spark, and NoSQL databases. With the advent of cloud computing, processing and storing such massive datasets on clusters of machines is now feasible with ease. However, there are limited tools and approaches, which users can rely on to gauge and comprehend the performance of their big data applications deployed locally on clusters, or in the cloud. Researchers have started exploring this area by providing benchmarking suites suitable for big data applications. However, many of these tools are fragmented, complex to deploy and manage, and do not provide transparency with respect to the monetary cost of benchmarking an application. In this paper, we present Plug And Play Bench, an infrastructure aware abstraction built to integrate and simplify the deployment of big data benchmarking tools on clusters of machines. PAPB automates the tedious process of installing, configuring and executing common big data benchmark workloads by containerising the tools and settings based on the underlying cluster deployment framework. Our proof of concept implementation utilises HiBench as the benchmark suite, HDP as the cluster deployment framework and Azure as the cloud platform. The paper further illustrates the inclusion of cost metrics based on the underlying Microsoft Azure cloud platform., Comment: 8 pages, Published as a workshop paper in 2017 IEEE International Conference on Big Data in Boston Dec 11 - 14

The classification of graphs is a key challenge within many scientific fields using graphs to represent data and is an active area of research. Graph classification can be critical in identifying and labelling unknown graphs within a dataset and has seen application across many scientific fields. Graph classification poses two distinct problems: the classification of elements within a graph and the classification of the entire graph. Whilst there is considerable work on the first problem, the efficient and accurate classification of massive graphs into one or more classes has, thus far, received less attention. In this paper we propose the Deep Topology Classification (DTC) approach for global graph classification. DTC extracts both global and vertex level topological features from a graph to create a highly discriminate representation in feature space. A deep feed-forward neural network is designed and trained to classify these graph feature vectors. This approach is shown to be over 99% accurate at discerning graph classes over two datasets. Additionally, it is shown to be more accurate than current state of the art approaches both in binary and multi-class graph classification tasks.

The Finnish 5G test network (5GTN) is built to support development and analysis of 5G technologies and new services on top of them. 5GTN includes a holistic monitoring and test generation architecture, enabling generation and collection of diverse test and datasets, analyzing the results and using these as basis for developing new technologies, algorithms, services, and optimizations. Both the combined network and service parameters space, as well as data volume, provide us with several big data problems. In this paper, we describe the overall system architecture, the types of data we collect, the initial analysis we have performed on the data, and what we have learned so far. The network is constantly evolving with new services integrated and tested, and new big data analytics being applied as we learn from our tests. As such, these are preliminary results for ongoing work.

Recent technological advances in modern healthcare have lead to the ability to collect a vast wealth of patient monitoring data. This data can be utilised for patient diagnosis but it also holds the potential for use within medical research. However, these datasets often contain errors which limit their value to medical research, with one study finding error rates ranging from 2.3%???26.9% in a selection of medical databases. Previous methods for automatically assessing data quality normally rely on threshold rules, which are often unable to correctly identify errors, as further complex domain knowledge is required. To combat this, a semantic web based framework has previously been developed to assess the quality of medical data. However, early work, based solely on traditional semantic web technologies, revealed they are either unable or inefficient at scaling to the vast volumes of medical data. In this paper we present a new method for storing and querying medical RDF datasets using Hadoop Map / Reduce. This approach exploits the inherent parallelism found within RDF datasets and queries, allowing us to scale with both dataset and system size. Unlike previous solutions, this framework uses highly optimised (SPARQL) joining strategies, intelligent data caching and the use of a super-query to enable the completion of eight distinct SPARQL lookups, comprising over eighty distinct joins, in only two Map / Reduce iterations. Results are presented comparing both the Jena and a previous Hadoop implementation demonstrating the superior performance of the new methodology. The new method is shown to be five times faster than Jena and twice as fast as the previous approach.

Efficient protection of huge amount of IoT produced data is key for wide scale data analytic services. The most efficient way is to use pure symmetric encryption as that allows both fast decryption at the analytic engine side as well as energy efficient encryption at the IoT side. However, symmetric encryption can only be performed if there is a way to directly map an encrypted object to the correct key. Typically, such mapping require a unique IoT identity, which constitute a privacy problem. In this paper, we present an IoT identity protection scheme for symmetric IoT data encryption. We give basic security definitions for this problem setting, present a new construction and give security proofs of security level achieved with the construction. Performance figures for a proof of concept implementation are also given. The new scheme gives a fair trade-off between identity privacy and complexity.