Search

As algorithms replace a growing number of tasks performed by humans in the markets, there have been growing concerns about an increased likelihood of cascading events, similar to the Flash Crash of May 6, 2010. To address these concerns, researchers have employed a number of scientific data analysis tools to monitor the risk of such cascading events. As an example, the authors of this article investigate the natural gas (NG) futures market in the frequency domain and the interaction between weather forecasts and NG price data. They observe that Fourier components with high frequencies have become more prominent in recent years and are much stronger than could be expected from an analytical model of the market. Additionally, a significant amount of trading activity occurs in the first few seconds of every minute, which is a tell-tale sign of time-based algorithmic trading. To illustrate the potential of cascading events, the authors further study how weather forecasts drive NG prices and show that, after separating the time series by season to account for the different mechanisms that relate temperature to NG price, the temperature forecast is indeed cointegrated with NG price. They also show that the variations in temperature forecasts contribute to a significant percentage of the average daily price fluctuations, which confirms the possibility that a forecast error could significantly affect the price of NG futures. TOPICS:Statistical methods, simulations, big data/machine learning Key Findings • High-frequency components in the trading data are stronger than expected from a model assuming uniform trading during market hours. • The dominance of the high-frequency components have been increasing over the years. • Relatively small changes in temperature could create a large price fluctuation in natural gas futures contracts.

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

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

In the previous chapter, we have introduced the motivation for a big data analysis system and its essential components: data model and programming model. We have also clearly stated the reasons why FasTensor chooses the multi-dimensional array as its data model. In this chapter, we continue to provide more details on the FasTensor’s programming model using the multi-dimensional array data model. The crucial constructs of a programming model for the data analysis include an abstract data type and a set of generic operators. The abstract data type allows users to define input and output data structures that their data analysis functions use. The abstract data type is defined on the top of the array data model. The set of generic operators should allow users to formulate a workflow with a wide range of data analysis functions. Through the abstract data type and these generic operators, a standard protocol between users and a data analysis system is established. On one hand, users can format their data with the abstract data type and express their data analysis with these generic operators. On the other hand, based on the abstract data type and these generic operators, the data analysis system can easily build its functions for generic data management functions, parallelization, and other tasks.

In this chapter, we describe the user interface of the FasTensor library, a C++ implementation of the FasTensor programming model presented in previous chapters. Hence, the term FasTensor will mostly refer to the FasTensor library that implements the FasTensor programming model. Currently, the FasTensor programming model is available in C++. Support for other languages, such as Java, Python, and Julia, are planned.

In this chapter, we describe two scientific applications to demonstrate the capability of FasTensor. The first application is from the earth science, where we show how FasTensor implement the self-similarity computation to detect useful signal from the data collected with distributed acoustic sensing (DAS). The second application is from plasma physics, where we apply FasTensor to analyze the hydro data from a VPIC simulation.

Moving loads such as cars and trains are very useful sources of seismic waves, which can be analyzed to retrieve information on the seismic velocity of subsurface materials using the techniques of ambient noise seismology. This information is valuable for a variety of applications such as geotechnical characterization of the near-surface, seismic hazard evaluation, and groundwater monitoring. However, for such processes to converge quickly, data segments with appropriate noise energy should be selected. Distributed Acoustic Sensing (DAS) is a novel sensing technique that enables acquisition of these data at very high spatial and temporal resolution for tens of kilometers. One major challenge when utilizing the DAS technology is the large volume of data that is produced, thereby presenting a significant Big Data challenge to find regions of useful energy. In this work, we present a highly scalable and efficient approach to process real, complex DAS data by integrating physics knowledge acquired during a data exploration phase followed by deep supervised learning to identify "useful" coherent surface waves generated by anthropogenic activity, a class of seismic waves that is abundant on these recordings and is useful for geophysical imaging. Data exploration and training were done on 130~Gigabytes (GB) of DAS measurements. Using parallel computing, we were able to do inference on an additional 170~GB of data (or the equivalent of 10 days' worth of recordings) in less than 30 minutes. Our method provides interpretable patterns describing the interaction of ground-based human activities with the buried sensors., Accepted at the IEEE BigData 2020 conference

Author(s): Godoy, WF; Podhorszki, N; Wang, R; Atkins, C; Eisenhauer, G; Gu, J; Davis, P; Choi, J; Germaschewski, K; Huck, K; Huebl, A; Kim, M; Kress, J; Kurc, T; Liu, Q; Logan, J; Mehta, K; Ostrouchov, G; Parashar, M; Poeschel, F; Pugmire, D; Suchyta, E; Takahashi, K; Thompson, N; Tsutsumi, S; Wan, L; Wolf, M; Wu, K; Klasky, S | Abstract: We present ADIOS 2, the latest version of the Adaptable Input Output (I/O) System. ADIOS 2 addresses scientific data management needs ranging from scalable I/O in supercomputers, to data analysis in personal computer and cloud systems. Version 2 introduces a unified application programming interface (API) that enables seamless data movement through files, wide-area-networks, and direct memory access, as well as high-level APIs for data analysis. The internal architecture provides a set of reusable and extendable components for managing data presentation and transport mechanisms for new applications. ADIOS 2 bindings are available in C++11, C, Fortran, Python, and Matlab and are currently used across different scientific communities. ADIOS 2 provides a communal framework to tackle data management challenges as we approach the exascale era of supercomputing.

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

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

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

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

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

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

Quickly identifying astronomical transients from synoptic surveys is critical to many recent astrophysical discoveries. However, each of the data processing pipelines in these surveys contains dozens of stages with highly varying time and space requirements. Properly predicting the resources required to run these pipelines is critical for the allocation of computing resources and reducing the discovery response time. We propose a machine learning strategy for this prediction task and demonstrate its effectiveness using a set of timing measurements from the intermediate Palomar Transient Factory (iPTF) workflow. The proposed model utilizes the spatiotemporal correlation of astronomical images, where nearby patches of the sky (space) are likely to have a similar number of objects of interest and workflows executed in the recent past (time) are likely to use a similar amount of time because the machines and data storage systems are likely to be in similar states. We capture the relationship among these spatial and temporal features in a Bayesian network and study how they impact the prediction accuracy. This Bayesian network helps us to identify the most influential features for predictions. With proper features, our models achieve errors close to the random variance boundary within batches of images taken at the same time, which can be regarded as the intrinsic limit of prediction accuracy.

Recently developed distributed acoustic sensing (DAS) technologies convert fiber-optic cables into large arrays of subsurface sensors, enabling a variety of applications including earthquake detection and environmental characterization. However, DAS systems produce voluminous datasets sampled at high spatial-temporal resolution and consequently, discovering useful geophysical knowledge within these large-scale data becomes a nearly impossible task for geophysicists. It is appealing to use supercomputers for DAS data analysis, as modern supercomputers are capable of performing over a hundred quadrillion FLOPS operations and have access to exabytes of storage space. Unfortunately, the majority of geophysical data processing libraries are not geared towards these supercomputer environments. This paper introduces a parallel DAS Data Storage and Analysis (DASSA) framework to enable easy-to-use and parallel DAS data analysis on modern supercomputers. DASSA uses a hybrid (i.e., MPI and OpenMP) data analysis execution engine that supports a user-defined function (UDF) interface for various operations and automatically parallelizes them for supercomputer execution. DASSA also provides novel data storage and access strategies, such as communication-avoiding parallel I/O, to reduce the cost of retrieving large DAS data for analysis. Compared with existing data analysis pipelines used by the geophysical community, DASSA is 16× faster and can efficiently scale up to 1456 computing nodes with 11648 CPU cores.

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

Upcoming exascale applications could introduce significant data management challenges due to their large sizes, dynamic work distribution, and involvement of accelerators such as graphical processing units, GPUs. In this work, we explore the performance of reading and writing operations involving one such scientific application on two different supercomputers. Our tests showed that the Adaptable Input and Output System, ADIOS, was able to achieve speeds over 1TB/s, a significant fraction of the peak I/O performance on Summit. We also demonstrated the querying functionality in ADIOS could effectively support common selective data analysis operations, such as conditional histograms. In tests, this query mechanism was able to reduce the execution time by a factor of five. More importantly, ADIOS data management framework allows us to achieve these performance improvements with only a minimal amount of coding effort.

A fluorescence-quenching immunochromotographic assay (ICA) was developed for sensitive detection of aflatoxin B1 (AFB1) in soybean sauce based on the inner filter effect (IFE) between flower-like gold nanoparticles (AuNFs) and quantum dots (QDs). QDs were sprayed on the test and control line zones as background fluorescence signals, whereas AuNFs were designed as the fluorescence absorber of QDs because the surface plasma resonance peak of AuNFs totally matched with the maximum emission peak of QDs. Under the optimal conditions, the fluorescence-quenching ICA strip showed a good linear detection for AFB1 in standard AFB1 solution from 0.008 μg/L to 1 μg/L with a low detection limit of 0.004 μg/L. The average recoveries for different concentrations of AFB1-spiked soybean sauce samples ranged from 84.69% to 120.44% with a coefficient of variation ranging from 2.73% to 10.41%. In addition, the reliability of the proposed method was further confirmed by ultra-performance liquid chromatography with fluorescence detection method. In brief, this novel IFE-based strip offers a simple, rapid, sensitive, and accurate strategy for quantitative detection of AFB1 in soybean sauce.

Herein, for the first time we report a novel competitive fluorescence immunoassay for the ultrasensitive detection of aflatoxin B1 (AFB1) using histone-ds-poly(AT) templated copper nanoparticles (His-pAT CuNPs) as the fluorescent indicator. In this immunoassay, glucose oxidase (Gox) was used as the carrier of the competing antigen to catalyze the formation of hydrogen peroxide (H2O2) from glucose. H2O2 was converted to a hydroxyl radical using Fenton's reagent, which further regulated the fluorescence signals of His-pAT CuNPs. Owing to the ultrahigh sensitivity of the ss-DNA to the hydroxyl radical, the proposed fluorescence immunoassay exhibited a favorable dynamic linear detection of AFB1 ranging from 0.46 pg mL-1 to 400 pg mL-1 with an good half maximal inhibitory concentration and limit of detection of 6.13 and 0.15 pg mL-1, respectively. The intra- and inter-assay showed that the average recoveries for AFB1 spiked corn samples ranged from 96.87% to 100.73% and 96.67% to 114.92%, respectively. The reliability of this method was further confirmed by adopting ultra-performance liquid chromatography coupled with the fluorescence detector method. In summary, this work offers a novel screening strategy with high sensitivity and robustness for the quantitative detection of mycotoxins or other pollutants for food safety and clinical diagnosis.

Daily transportation mode choice is largely habitual, but transitions between life events may disrupt travel habits and can shift choices between alternative transportation modes. Although much is known about general mode switches following life event transitions, less is understood about differences that may exist between subpopulations, especially from a long-term perspective. Understanding these differences will help planners and policymakers introduce more targeted policy interventions to promote sustainable transportation modes and inform longer-term predictions. Extending beyond existing literature, we use data collected from a retrospective survey to investigate the effects of life course events on mode use situated within different long-term life trajectory contexts. We apply a machine-learning method called joint social sequence clustering to define five distinct and interpretable cohorts based on trajectory patterns in family and career domains over their life courses. We use these patterns as an innovative contextual system to investigate (1) the heterogeneous effects of life events on travel mode use and (2) further differentiation between gender and generation groups in these life event effects. We find that events occurring relatively early in life are more strongly associated with changes in mode-use behavior, and that mode use can also be affected by the relative order of events. This timing and order effect can have lasting impacts on mode use aggregated over entire life cycles: members of our “Have-it-alls” cohort-who finish their education, start working, partner up, and have children early in life-ramp up car use at each event, resulting in the highest rate of car use occurring the earliest among all the cohorts. Women drive more when having children primarily when their family formation and career formation are intertwined early in life, and younger generations rely relatively more on car use during familial events when their careers have a later start.

Wi-Fi has become the wireless networking standard that allows short- to medium-range device to connect without wires. For the last 20 year, the Wi-Fi technology has so pervasive that most devices in use today are mobile and connect to the internet through Wi-Fi. Unlike wired network, a wireless network lacks a clear boundary, which leads to significant Wi-Fi network security concerns, especially because the current security measures are prone to several types of intrusion. To address this problem, machine learning and deep learning methods have been successfully developed to identify network attacks. However, collecting data to develop models is expensive and raises privacy concerns. The goal of this paper is to evaluate a federated learning approach that would alleviate such privacy concerns. This initial work on intrusion detection is performed in a simulated environment. Once proven feasible, this process would allow edge devices to collaboratively update global anomaly detection models, without sharing sensitive training data. On a set of tests with the AWID intrusion detection data set, we show that our federated approach is effective in terms of classification accuracy, computation cost, as well as communication cost.

Today, scientific experiments and simulations produce massive amounts of heterogeneous data that need to be stored and analyzed. Given that these large datasets are stored in many files, formats and locations, how can scientists find relevant data, duplicates or similarities? In this context, we concentrate on developing algorithms to compare similarity of time series for the purpose of search, classification and clustering. For example, generating accurate patterns from climate related time series is important not only for building models for weather forecasting and climate prediction, but also for modeling and predicting the cycle of carbon, water, and energy. We developed the methodology and ran an exploratory analysis of climatic and ecosystem variables from the FLUXNET2015 dataset. The proposed combination of similarity metrics, nonlinear dimension reduction, clustering methods and validity measures for time series data has never been applied to unlabeled datasets before, and provides a process that can be easily extended to other scientific time series data. The dimensionality reduction step provides a good way to identify the optimum number of clusters, detect outliers and assign initial labels to the time series data. We evaluated multiple similarity metrics, in terms of the internal cluster validity for driver as well as response variables. While the best metric often depends on a number of factor, the Euclidean distance seems to perform well for most variables and also in terms of computational expense.

Scientific workflows are increasingly transferring large amounts of data between high performance computing (HPC) systems. Even though these HPC systems are connected via high-speed dedicated networks and use dedicated data transfer nodes (DTNs), it is still difficult to predict the data transfer throughput because of variations in data transfer protocols, host configurations, performance of file systems, and overlapping workloads. In order to provide reliable performance prediction for better resource management and job scheduling, we need models for predicting data transfer throughput under real-world conditions. In this paper, we explore different machine learning approaches for building data-driven models to improve performance and prediction of large-scale data transfer throughput. In addition to the variables already collected by the network monitoring system, we also develop heuristics to derive additional metrics for improving the prediction accuracy. We use the prediction results to identify the importance of different network parameters in predicting the throughput for large-scale data transfers. Through extensive tests, we identify key network parameters, discover interesting variations among different HPC sites, and show that we can predict throughput with high accuracy. We also analyze our models and results to provide recommendations for improving the performance of big data transfers.

The demands of increasingly large scientific application workflows lead to the need for more powerful supercomputers. As the scale of supercomputing systems have grown, the prediction of fault tolerance has become an increasingly critical area of study, since the prediction of system failures can improve performance by saving checkpoints in advance. We propose a real-time failure detection algorithm that adopts an event-based prediction model. The prediction model is a convolutional neural network that utilizes both traditional event attributes and additional spatio-temporal features. We present a case study using our proposed method with six years of reliability, availability, and serviceability event logs recorded by Mira, a Blue Gene/Q supercomputer at Argonne National Laboratory. In the case study, we have shown that our failure prediction model is not limited to predict the occurrence of failures in general. It is capable of accurately detecting specific types of critical failures such as coolant and power problems within reasonable lead time ranges. Our case study shows that the proposed method can achieve a F 1 score of 0.56 for general failures, 0.97 for coolant failures, and 0.86 for power failures.

Prediction of daily transportation mode use (car, public transit, or active travel) is a important task in transportation research. Unlike statistical models that impose a predetermined model structure, machine learning models are learned from the data, making them more flexible with higher prediction accuracy. However, prediction of mid-to long-term habitual modes still largely relies on traditional statistical analysis using small samples of cross-sectional data. Low interpretability of “black-box” machine learning models limits their usefulness for generating behavior insights needed for designing appropriate interventions. This paper, leveraging a set of unique longitudinal life course data, is the first use case to demonstrate machine learning methods applied for both predicting and interpreting regularly used travel modes. We combine sequence clustering and tree-based machine learning methods coupled with TreeExplainer to predict and interpret habitual travel modes using mid-to long-term predictors. Five life course clusters are derived to provide evaluation and interpretation contexts. This allows us to improve upon a recently developed TreeExplainer method to better distinguish predictor importance locally and globally; and predictor interactions across subpopulations within distinctive life history contexts. Our results demonstrate a promising step toward interpretable machine learning applications to mid-to long-term prediction of travel modes for transportation planning.

Author(s): Yildiz, B; Wu, K; Byna, S; Shoshani, A | Abstract: Many scientific applications produce very large amounts of data as advances in hardware fuel computing and experimental facilities. Managing and analyzing massive quantities of scientific data is challenging as data are often stored in specific formatted files, such as HDF5 and NetCDF, which do not offer appropriate search capabilities. In this research, we investigated a special class of search capability, called membership query, to identify whether queried elements of a set are members of an attribute. Attributes that naturally have classification values appear frequently in scientific domains such as category and object type as well as in daily life such as zip code and occupation. Because classification attribute values are discrete and require random data access, performing a membership query on a large scientific data set creates challenges. We applied bitmap indexing and parallelization to membership queries to overcome these challenges. Bitmap indexing provides high performance not only for low cardinality attributes but also for high cardinality attributes, such as floating-point variables, electric charge, or momentum in a particle physics data set, due to compression algorithms such as Word-Aligned Hybrid. We conducted experiments, in a highly parallelized environment, on data obtained from a particle accelerator model and a synthetic data set.

In this work, we study the use of decision tree-based models to predict the transfer rates in different parts of the data pipeline that sends experiment data from Linac Coherent Light Source (LCLS) at SLAC National Accelerator Laboratory (SLAC) to National Energy Research Scientific Computing Center (NERSC). The system monitoring the data pipeline collects a number of characteristics such as the file size, source file system, start time and so on, all of which are known at the start of the file transfer. However, these static variables do not capture the dynamic information such as current state of the networking system. In this work, we explore a number of different ways to capture the state of the network and other dynamic information. We find that in addition to using static features, using these dynamic features can improve the transfer performance predictions by up to 10-15%. We additionally study a couple of different well-known decision-tree based models and find that Gradient-Tree Boosting algorithm performs better overall.

Sensors typically record their measurements using more precision than the accuracy of the sensing techniques. Thus, experimental and observational data often contain noise that appears random and cannot be easily compressed. This noise increases storage requirement as well as computation time for analyses. In this work, we describe a line of research to develop data reduction techniques that preserve the key features while reducing the storage requirement. Our core observation is that the noise in such cases could be characterized by a small number of patterns based on statistical similarity. In earlier tests, this approach was shown to reduce the storage requirement by over 100-fold for one-dimensional sequences. In this work, we explore a set of different similarity measures for multidimensional sequences. During our tests with standard quality measures such as Peak Signal to Noise Ratio (PSNR), we observe that the new compression methods reduce the storage requirements over 100- fold while maintaining relatively low errors in PSNR. Thus, we believe that this is an effective strategy to construct data reduction techniques.

Fog computing has the potential to be an energy-efficient alternative to cloud computing for guaranteeing latency requirements of Latency-critical (LC) IoT services. However, even in fog computing low energy-efficiency of homogeneous multi-core server processors can be a major contributor to energy wastage. Recent studies have shown that Heterogeneous Multi-core Processors (HMPs) can improve energy efficiency of servers by adapting to dynamic load changes of LC-services. However, proposed approaches optimize energy only at a single server level. In our work, we demonstrate that optimization at the cluster-level across many HMP-servers can offer much greater energy savings through optimal work distribution across the HMP-servers while still guaranteeing the Service Level Objectives (SLO) of LC-services. In this paper, we present Greeniac, a cluster-level task manager that employs Reinforcement Learning to identify optimal configurations at the server- A nd cluster-levels for different workloads. We develop a server-level service scheduler and a cluster-level load balancing module to assign services and distribute tasks across HMP servers based on the learned configurations. In addition to meeting the required SLO targets, Greeniac achieves up to 28% energy saving compared to best-case cluster scheduling techniques with local HMP-aware scheduling on a 4-server fog cluster, with potentially larger savings in a larger cluster.

In this paper, a highly sensitive plasmonic enzyme-linked immunosorbent assay (pELISA) was developed for the naked-eye detection of fumonisin B1 (FB1). Glucose oxidase (GOx) was used as an alternative to horseradish peroxidase as the carrier of the competing antigen. GOx catalyzed the oxidation of glucose to produce hydrogen peroxide, which acted as a reducing agent to reduce Au3+ to Au on the surface of gold seeds (5 nm), This reaction led to a color change in the solution from colorless to purple, which was observable to the naked eye. Various parameters that could influence the detection performance of pELISA were investigated. The developed method exhibited a considerably high sensitivity for FB1 qualitative naked-eye detection, with a visible cut-off limit of 1.25 ng/mL. Moreover, the proposed pELISA showed a good linear range of 0.31&ndash, 10 ng/mL with a half maximal inhibitory concentration (IC50) of 1.86 ng/mL, which was approximately 13-fold lower than that of a horseradish peroxidase- (HRP)-based conventional ELISA. Meanwhile, the proposed method was highly specific and accurate. In summary, the new pELISA exhibited acceptable accuracy and precision for sensitive naked-eye detection of FB1 in maize samples and can be applied for the detection of other chemical contaminants.

Data from large-scale experiments and extreme-scale computing is expensive to produce and may be used for critical applications. However, it is not the mere existence of data that is important, but our ability to make use of it. Experience has shown that when metadata is better organized and more complete, the underlying data becomes more useful. Traditionally, capturing the steps of scientific workflows and metadata was the role of the lab notebook, but the digital era has resulted instead in the fragmentation of data, processing, and annotation. This paper presents the Metadata, Provenance, and Ontology (MPO) System, the software that can automate the documentation of scientific workflows and associated information. Based on recorded metadata, it provides explicit information about the relationships among the elements of workflows in notebook form augmented with directed acyclic graphs. A set of web-based graphical navigation tools and Application Programming Interface (API) have been created for searching and browsing, as well as programmatically accessing the workflows and data. We describe the MPO concepts and its software architecture. We also report the current status of the software as well as the initial deployment experience.

Self-assembled iron oxide nanocomposites are good magnetic nano-adsorbents that can be prepared using simple methods. Four types of organic acid-functionalised (oleic acid, undecenoic acid, caprylic acid or hexanoic acid) magnetic nanoparticles (MNPs) were synthesised through a one-pot chemisorption method for the removal of tetracycline (TC) from aqueous solution. The undecenoic acid-coated MNPs (UA-MNPs) exhibited the highest adsorption efficiency and can be easily retrieved with a low-gradient magnetic separator (0.4 Tesla) at pH 5.0 aqueous solution. The TC adsorption process on the UA-MNPs followed the Langmuir isotherm and the maximum adsorption capacities increased from 86.96 mg g(-1) to 222.2 mg g(-1) with the increase in temperature from 288 K to 318 K. The kinetics of adsorption fits pseudo-second-order model perfectly with a rate constant, 5.946 g mg(-1) min(-1) at 298 K. The positive values of the enthalpy (AH) and the negative value of the free energy (AG) indicated an endothermic and spontaneous adsorption process of TC on the UA-MNPs. Moreover, the UA-MNPs possessed excellent ability to adsorb the other three major types of TC antibiotics, including chlortetracycline, oxytetracycline and doxycycline.