Pipeline Of Steps Research Articles

Prediction of Attention Groups and Big Five Personality Traits from Gaze Features Collected from an Outlier Search Game.

This study explores the intersection of personality, attention and task performance in traditional 2D and immersive virtual reality (VR) environments. A visual search task was developed that required participants to find anomalous images embedded in normal background images in 3D space. Experiments were conducted with 30 subjects who performed the task in 2D and VR environments while their eye movements were tracked. Following an exploratory correlation analysis, we applied machine learning techniques to investigate the predictive power of gaze features on human data derived from different data collection methods. Our proposed methodology consists of a pipeline of steps for extracting fixation and saccade features from raw gaze data and training machine learning models to classify the Big Five personality traits and attention-related processing speed/accuracy levels computed from the Group Bourdon test. The models achieved above-chance predictive performance in both 2D and VR settings despite visually complex 3D stimuli. We also explored further relationships between task performance, personality traits and attention characteristics.

Parasagittal dural volume correlates with cerebrospinal fluid volume and developmental delay in children with autism spectrum disorder

BackgroundThe parasagittal dura, a tissue that lines the walls of the superior sagittal sinus, acts as an active site for immune-surveillance, promotes the reabsorption of cerebrospinal fluid, and facilitates the removal of metabolic waste products from the brain. Cerebrospinal fluid is important for the distribution of growth factors that signal immature neurons to proliferate and migrate. Autism spectrum disorder is characterized by altered cerebrospinal fluid dynamics.MethodsIn this retrospective study, we investigated potential correlations between parasagittal dura volume, brain structure volumes, and clinical severity scales in young children with autism spectrum disorder. We employed a semi-supervised two step pipeline to extract parasagittal dura volume from 3D-T2 Fluid Attenuated Inversion Recovery sequences, based on U-Net followed by manual refinement of the extracted parasagittal dura masks.ResultsHere we show that the parasagittal dura volume does not change with age but is significantly correlated with cerebrospinal fluid (p-value = 0.002), extra-axial cerebrospinal fluid volume (p-value = 0.0003) and severity of developmental delay (p-value = 0.024).ConclusionsThese findings suggest that autism spectrum disorder children with severe developmental delay may have a maldeveloped parasagittal dura that potentially perturbs cerebrospinal fluid dynamics.

Design and Implementation of a Model Selection Pipeline for Prognostics and Health Management in the Operational Environment

Model selection is a crucial aspect of Prognostics and Health Management (PHM). However, many PHM models are de- veloped for specific datasets and lack flexibility to adapt to different datasets with varying data quality considerations. To address this gap, we propose a generalizable model selection pipeline for PHM. Our approach involves creating a pipeline for testing models that users can tune in various ways. We designed a sequential pipeline of steps for model selection with a focus on implementation considerations which include recommendations for handling environmental variables, ca- pabilities for remote and local work environments, and stor- age considerations of the serialized pipeline. Performance metrics are designed to consider data quality characteristics such as ambiguous labeling. We illustrate the generalizability of our approach through a case study of our model selection pipeline applied to a field dataset with ambiguous labels. Our design accommodates data characteristics commonly found in field data, such as ambiguous labels and data wrangling. Our contribution fills a gap in real-world implementations of PHM by offering technology considerations and recommen- dations for effective deployment.

Towards an Integrated Methodology and Toolchain for Machine Learning-Based Intrusion Detection in Urban IoT Networks and Platforms

The constant increase in volume and wide variety of available Internet of Things (IoT) devices leads to highly diverse software and hardware stacks, which opens new avenues for exploiting previously unknown vulnerabilities. The ensuing risks are amplified by the inherent IoT resource constraints both in terms of performance and energy expenditure. At the same time, IoT devices often generate or collect sensitive, real-time data used in critical application scenarios (e.g., health monitoring, transportation, smart energy, etc.). All these factors combined make IoT networks a primary target and potential victim of malicious actors. In this paper, we presented a brief overview of existing attacks and defense strategies and used this as motivation for proposing an integrated methodology for developing protection mechanisms for smart city IoT networks. The goal of this work was to lay out a theoretical plan and a corresponding pipeline of steps, i.e., a development and implementation process, for the design and application of cybersecurity solutions for urban IoT networks. The end goal of following the proposed process is the deployment and continuous improvement of appropriate IoT security measures in real-world urban IoT infrastructures. The application of the methodology was exemplified on an OMNET++-simulated scenario, which was developed in collaboration with industrial partners and a municipality.

Interpreting the order of operations in a sociophonetic analysis

Abstract Sociophonetic data analysis involves a pipeline of processing steps to convert a raw spreadsheet of acoustic measurements to interpretable results. While most studies report the steps used in their pipeline, very few explicitly report their order in which those steps were applied. This study analyzes a dataset containing vowel formant data from 53 speakers by processing it 5,040 unique ways, each representing a different permutation of seven processing steps. To analyze the effect that an order has on the overall results, pairs of pipelines that differed only by swapping two adjacent steps were compared. The most important steps in the pipeline were when normalization happened, how outliers were detected, and when good data was excluded. This study illustrates what happens when these steps are rearranged relative to each other in order to justify and recommend the following order of operations: classifying allophones, removing outliers, normalizing, and then subsetting.

Area Optimal Polygonization Using Simulated Annealing

We describe a practical method to find near-optimal solutions for the area-optimal simple polygonization problem: Given a set of points S in the plane, the objective is to find a simple polygon of minimum or maximum area defined by S . Our approach is based on the celebrated metaheuristic Simulated Annealing. The method consists of a modular pipeline of steps, where each step can be implemented in various ways and with several parameters controlling it. We have implemented several different algorithms and created an application that computes a polygon with minimal (or maximal) area. We experimented with the various algorithmic options and with the controlling parameters of each algorithm to tune up the pipeline. Then, we executed the application on each of the benchmark instances, exploiting a grid of servers, to obtain near optimal results.

Enhancing object detection in aerial images.

Unmanned Aerial Vehicles have proven to be helpful in domains like defence and agriculture and will play a vital role in implementing smart cities in the upcoming years. Object detection is an essential feature in any such application. This work addresses the challenges of object detection in aerial images like improving the accuracy of small and dense object detection, handling the class-imbalance problem, and using contextual information to boost the performance. We have used a density map-based approach on the drone dataset VisDrone-2019 accompanied with increased receptive field architecture such that it can detect small objects properly. Further, to address the class imbalance problem, we have picked out the images with classes occurring fewer times and augmented them back into the dataset with rotations. Subsequently, we have used RetinaNet with adjusted anchor parameters instead of other conventional detectors to detect aerial imagery objects accurately and efficiently. The performance of the proposed three step pipeline of implementing object detection in aerial images is a significant improvement over the existing methods. Future work may include improvement in the computations of the proposed method, and minimising the effect of perspective distortions and occlusions.

ICU admission and mortality classifiers for COVID-19 patients based on subgroups of dynamically associated profiles across multiple timepoints

The coronavirus disease 2019 (COVID-19) which is caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) is consistently causing profound wounds in the global healthcare system due to its increased transmissibility. Currently, there is an urgent unmet need to identify the underlying dynamic associations among COVID-19 patients and distinguish patient subgroups with common clinical profiles towards the development of robust classifiers for ICU admission and mortality. To address this need, we propose a four step pipeline which: (i) enhances the quality of multiple timeseries clinical data through an automated data curation workflow, (ii) deploys Dynamic Bayesian Networks (DBNs) for the detection of features with increased connectivity based on dynamic association analysis across multiple points, (iii) utilizes Self Organizing Maps (SOMs) and trajectory analysis for the early identification of COVID-19 patients with common clinical profiles, and (iv) trains robust multiple additive regression trees (MART) for ICU admission and mortality classification based on the extracted homogeneous clusters, to identify risk factors and biomarkers for disease progression. The contribution of the extracted clusters and the dynamically associated clinical data improved the classification performance for ICU admission to sensitivity 0.83 and specificity 0.83, and for mortality to sensitivity 0.74 and specificity 0.76. Additional information was included to enhance the performance of the classifiers yielding an increase by 4% in sensitivity and specificity for mortality. According to the risk factor analysis, the number of lymphocytes, SatO2, PO2/FiO2, and O2 supply type were highlighted as risk factors for ICU admission and the percentage of neutrophils and lymphocytes, PO2/FiO2, LDH, and ALP for mortality, among others. To our knowledge, this is the first study that combines dynamic modeling with clustering analysis to identify homogeneous groups of COVID-19 patients towards the development of robust classifiers for ICU admission and mortality.

Dirty Pixels: Towards End-to-end Image Processing and Perception

Real-world, imaging systems acquire measurements that are degraded by noise, optical aberrations, and other imperfections that make image processing for human viewing and higher-level perception tasks challenging. Conventional cameras address this problem by compartmentalizing imaging from high-level task processing. As such, conventional imaging involves processing the RAW sensor measurements in a sequential pipeline of steps, such as demosaicking, denoising, deblurring, tone-mapping, and compression. This pipeline is optimized to obtain a visually pleasing image. High-level processing, however, involves steps such as feature extraction, classification, tracking, and fusion. While this silo-ed design approach allows for efficient development, it also dictates compartmentalized performance metrics without knowledge of the higher-level task of the camera system. For example, today’s demosaicking and denoising algorithms are designed using perceptual image quality metrics but not with domain-specific tasks such as object detection in mind. We propose an end-to-end differentiable architecture that jointly performs demosaicking, denoising, deblurring, tone-mapping, and classification (see Figure 1). The architecture does not require any intermediate losses based on perceived image quality and learns processing pipelines whose outputs differ from those of existing ISPs optimized for perceptual quality, preserving fine detail at the cost of increased noise and artifacts. We show that state-of-the-art ISPs discard information that is essential in corner cases, such as extremely low-light conditions, where conventional imaging and perception stacks fail. We demonstrate on captured and simulated data that our model substantially improves perception in low light and other challenging conditions, which is imperative for real-world applications such as autonomous driving, robotics, and surveillance. Finally, we found that the proposed model also achieves state-of-the-art accuracy when optimized for image reconstruction in low-light conditions, validating the architecture itself as a potentially useful drop-in network for reconstruction and analysis tasks beyond the applications demonstrated in this work. Our proposed models, datasets, and calibration data are available at https://github.com/princeton-computational-imaging/DirtyPixels .

Multiple perspective attention based on double BiLSTM for aspect and sentiment pair extract

Aspect category sentiment analysis has attracted increasing attention because of its outstanding performance in mining the fine-grained sentiment expression of users. In recent years, a new aspect category and sentiment pair extraction (ASPE) task has been proposed to simultaneously extract aspect categories and sentiment pairs. Most existing research works are designed in a two step pipeline, that is, they first perform aspect category detection, and subsequently conduct aspect category sentiment analysis. However, the pipeline method can clearly lead to error propagation from previous step. In this work, we propose a new framework for multiple perspective attention based on double BiLSTM with a novel joint strategy for ASPE to alleviate the accumulation of errors in the pipeline method. The experimental results on benchmark datasets SemEval and BDCI-2018 demonstrate the effectiveness of the proposed approach in terms of both accuracy and explainability for the ASPE task.

No One is Perfect: Analysing the Performance of Question Answering Components Over the Dbpedia Knowledge Graph

Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question answering for user interaction. DBpedia has been the most prominently used knowledge graph in this setting and most approaches currently use a pipeline of processing steps connecting a sequence of components. In this article, we analyse and micro evaluate the behaviour of 29 available QA components for the DBpedia knowledge graph that were released by the research community since 2010. As a result, we provide a perspective on collective failure cases, suggest characteristics of QA components that prevent them from performing better and provide future challenges and research directions in the field.

WhiskEras: A New Algorithm for Accurate Whisker Tracking.

Rodents engage in active touch using their facial whiskers: they explore their environment by making rapid back-and-forth movements. The fast nature of whisker movements, during which whiskers often cross each other, makes it notoriously difficult to track individual whiskers of the intact whisker field. We present here a novel algorithm, WhiskEras, for tracking of whisker movements in high-speed videos of untrimmed mice, without requiring labeled data. WhiskEras consists of a pipeline of image-processing steps: first, the points that form the whisker centerlines are detected with sub-pixel accuracy. Then, these points are clustered in order to distinguish individual whiskers. Subsequently, the whiskers are parameterized so that a single whisker can be described by four parameters. The last step consists of tracking individual whiskers over time. We describe that WhiskEras performs better than other whisker-tracking algorithms on several metrics. On our four video segments, WhiskEras detected more whiskers per frame than the Biotact Whisker Tracking Tool. The signal-to-noise ratio of the output of WhiskEras was higher than that of Janelia Whisk. As a result, the correlation between reflexive whisker movements and cerebellar Purkinje cell activity appeared to be stronger than previously found using other tracking algorithms. We conclude that WhiskEras facilitates the study of sensorimotor integration by markedly improving the accuracy of whisker tracking in untrimmed mice.

Insights into Exploration and Exploitation Power of Optimization Algorithm Using DSCTool

When making statistical analysis of single-objective optimization algorithms’ performance, researchers usually estimate it according to the obtained optimization results in the form of minimal/maximal values. Though this is a good indicator about the performance of the algorithm, it does not provide any information about the reasons why it happens. One possibility to get additional information about the performance of the algorithms is to study their exploration and exploitation abilities. In this paper, we present an easy-to-use step by step pipeline that can be used for performing exploration and exploitation analysis of single-objective optimization algorithms. The pipeline is based on a web-service-based e-Learning tool called DSCTool, which can be used for making statistical analysis not only with regard to the obtained solution values but also with regard to the distribution of the solutions in the search space. Its usage does not require any special statistic knowledge from the user. The gained knowledge from such analysis can be used to better understand algorithm’s performance when compared to other algorithms or while performing hyperparameter tuning.

Robotic Process Mining: Vision and Challenges

Robotic process automation (RPA) is an emerging technology that allows organizations automating repetitive clerical tasks by executing scripts that encode sequences of fine-grained interactions with Web and desktop applications. Examples of clerical tasks include opening a file, selecting a field in a Web form or a cell in a spreadsheet, and copy-pasting data across fields or cells. Given that RPA can automate a wide range of routines, this raises the question of which routines should be automated in the first place. This paper presents a vision towards a family of techniques, termed robotic process mining (RPM), aimed at filling this gap. The core idea of RPM is that repetitive routines amenable for automation can be discovered from logs of interactions between workers and Web and desktop applications, also known as user interactions (UI) logs. The paper defines a set of basic concepts underpinning RPM and presents a pipeline of processing steps that would allow an RPM tool to generate RPA scripts from UI logs. The paper also discusses research challenges to realize the envisioned pipeline.

Deep Learning-Based Single-Shot and Real-Time Vehicle Detection and Ego-Lane Estimation


 
 
 Vision-based Forward Collision Warning System (FCWS) is a promising assist feature in a car to alleviate road accidents and make roads safer. In practice, it is exceptionally hard to accurately and efficiently develop an algorithm for FCWS application due to the complexity of steps involved in FCWS. For FCWS application, multiple steps are involved namely vehicle detection, target vehicle verification and time-to-collision (TTC). These involve an elaborated FCWS pipeline using classical computer vision methods which limits the robustness of the overall system and limits the scalability of the algorithm. Deep neural network (DNN) has shown unprecedented performance for the task of vision-based object detection which opens the possibility to be explored as an effective perceptive tool for automotive application. In this paper, a DNN based single-shot vehicle detection and ego-lane estimation architecture is presented. This architecture allows simultaneous detection of vehicles and estimation of ego-lanes in a single-shot. SSD-MobileNetv2 architecture was used as a backbone network to achieve this. Traffic ego- lanes in this paper were defined as semantic regression points. We collected and labelled 59,068 images of ego-lane datasets and trained the feature extractor architecture MobileNetv2 to estimate where the ego- lanes are in an image. Once the feature extractor is trained for ego-lane estimation the meta-architecture single-shot detector (SSD) was then trained to detect vehicles. Our experimental results show that this method achieves real-time performance with test results of 88% total precision on the CULane dataset and 91% on our dataset for ego-lane estimation. Moreover, we achieve a 63.7% mAP for vehicle detection on our dataset. The proposed architecture shows that an elaborate pipeline of multiple steps to develop an algorithm for the FCWS application is eliminated. The proposed method achieves real-time at 60 fps performance on standard PC running on Nvidia GTX1080 proving its potential to run on an embedded device for FCWS.
 
 

Computational Study of Gas-Solid Flow in a Horizontal Stepped Pipeline

In this paper, the mechanism governing the particle-fluid flow characters in the stepped pipeline is studied by the combined discrete element method (DEM) and computational fluid dynamics (CFD) model (CFD-DEM) and the two fluid model (TFM). The mechanisms governing the gas-solid flow in the horizontal stepped pipeline are investigated in terms of solid and gas velocity distributions, pressure drop, process performance, the gas-solid interaction forces, solid-solid interaction forces, and the solid-wall interaction forces. The two models successfully capture the key flow features in the stepped pipeline, such as the decrease of gas velocity, solid velocity, and pressure drop, during and after the passage of gas-solid flow through the stepped section. What is more important, the reason of the appearance of large size solid dune and pressure surge phenomena suffered in the stepped pipeline is investigated macroscopically and microscopically. The section in which the blockage problem most likely occurs in the stepped pipeline is confirmed. The pipe wall wearing problem, which is one of the most common and critical problems in pneumatic conveying system, is analysed and investigated in terms of interaction forces. It is shown that the most serious pipe wall wearing problem happened in the section which is just behind the stepped part.

Phase Prediction of Supercritical Carbon Dioxide and its Application in Fracturing Oil Wellbores

In recent oil and gas exploration, the most reservoirs are low permeability with abundant reserves. Conventional mining of low permeability reservoir is commonly utilizing the hydraulic fracturing technology, whereas, it encounters various technical issues, such as clay expansion and water lock damage. Using the fluid of supercritical carbon dioxide (S-CO2) to exploit the low permeability oil and gas reservoirs is attracting more attention. The implementation of S-CO2, without liquid phase, can help avoid the aforementioned problems. Nevertheless, the phase change of CO2 during fracturing is complicate, and it is difficult to accurately predict the CO2 phase transition. In this work, first, the physical properties of S-CO2 were analyzed by the Span-Wagner model and Vesovic model. Next, S-CO2 was applied to a typical oilfield, and an unsteady coupling model of heat transfer and pressure drop was developed. Then the staggered grid method and iteration procedures were used for numerical solutions, and the temperature and pressure distributions of wellbores were investigated. The results indicate that the temperature control of a wellbore is the key to the phase prediction of S-CO2; CO2 within the single-diameter pipeline below 2300 m can maintain the supercritical state, while CO2 within the stepped pipeline can maintain the supercritical state at the depth of 2280 m. Moreover, compared with the single-diameter pipeline, the bottom pressure of the stepped pipeline is lower and the bottom temperature is higher. By analyzing the flow and heat transfer of S-CO2 in the wellbores, the phase state of S-CO2 was well predicted, which is helpful to improve the exploring performance of low permeability oil and gas reservoirs.

CrowdIA

The increasing volume of text data is challenging the cognitive capabilities of expert analysts. Machine learning and crowdsourcing present new opportunities for large-scale sensemaking, but we must overcome the challenge of modeling the overall process so that many distributed agents can contribute to suitable components asynchronously and meaningfully. In this paper, we explore how to crowdsource the sensemaking process via a pipeline of modularized steps connected by clearly defined inputs and outputs. Our pipeline restructures and partitions information into "context slices" for individual workers. We implemented CrowdIA, a software platform to enable unsupervised crowd sensemaking using our pipeline. With CrowdIA, crowds successfully solved two mysteries, and were one step away from solving the third. The crowd's intermediate results revealed their reasoning process and provided evidence that justifies their conclusions. We suggest broader possibilities to optimize each component, as well as to evaluate and refine previous intermediate analyses to improve the final result.

Гибридные вычислительные кластеры для изучения структуры, функции и регуляции белков

Суплатов Дмитрий Андреевич, к.х.н., с.н.с. НИИ физико-химической биологии имени А.Н. Белозерского, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). Попова Нина Николаевна, к.ф-м.н., доцент Факультета вычислительной математики и кибернетики, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). Копылов Кирилл Евгеньевич, студент Химического факультета, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). Шегай Максим Викторович, аспирант Факультета вычислительной математики и кибернетики, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). Воеводин Владимир Валентинович, чл.-корр. РАН, д.ф.-м.н., зав. кафедрой супер- компьютеров и квантовой информатики Факультета вычислительной математики и кибернетики, зам. директора Научно-исследовательского вычислительного центра, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). Швядас Витас Каятоно, д.х.н., профессор Факультета биоинженерии и биоинформатики и НИИ физико-химической биологии имени А.Н. Белозерского, Московский государственный университет имени М.В. Ломоносова (Москва, Российская Федерация). D.A. Suplatov, N.N. Popova, K.E. Kopylov, M.V. Shegay, Vl.V. Voevodin, V.K. Svedas Lomonosov Moscow State University (GSP-1, Leninskie Gory 1, Moscow, 119991 Russia) E-mail: d.a.suplatov@belozersky.msu.ru, popova@cs.msu.su, kopylov@mail.chem.msu.ru, max.shegai@gmail.com, voevodin@parallel.ru, vytas@belozersky.msu.ru

On the Relevance of Sophisticated Structural Annotations for Disulfide Connectivity Pattern Prediction

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed approaches for this prediction problem adopt the following pipeline: first they enrich the primary sequence with structural annotations, second they apply a binary classifier to each candidate pair of cysteines to predict disulfide bonding probabilities and finally, they use a maximum weight graph matching algorithm to derive the predicted disulfide connectivity pattern of a protein. In this paper, we adopt this three step pipeline and propose an extensive study of the relevance of various structural annotations and feature encodings. In particular, we consider five kinds of structural annotations, among which three are novel in the context of disulfide bridge prediction. So as to be usable by machine learning algorithms, these annotations must be encoded into features. For this purpose, we propose four different feature encodings based on local windows and on different kinds of histograms. The combination of structural annotations with these possible encodings leads to a large number of possible feature functions. In order to identify a minimal subset of relevant feature functions among those, we propose an efficient and interpretable feature function selection scheme, designed so as to avoid any form of overfitting. We apply this scheme on top of three supervised learning algorithms: k-nearest neighbors, support vector machines and extremely randomized trees. Our results indicate that the use of only the PSSM (position-specific scoring matrix) together with the CSP (cysteine separation profile) are sufficient to construct a high performance disulfide pattern predictor and that extremely randomized trees reach a disulfide pattern prediction accuracy of on the benchmark dataset SPX, which corresponds to improvement over the state of the art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3CysBridges.