Search

• We considered both the string and graph modal information in the drug and target. • We captured the positional information of string modal to extract more useful information in SMILES and target sequences. • We used multimodal fusion methods to balance and integrate the information from multiple modalities. • We conducted experiments based on two benchmark datasets Davis and KIBA, and FMDTA outperformed the state-of-the-art models. In the biomedical field, the efficacy of most drugs is demonstrated by their interactions with targets, meanwhile, accurate prediction of the strength of drug-target binding is extremely important for drug development efforts. Traditional bioassay-based drug-target binding affinity (DTA) prediction methods cannot meet the needs of drug R&D in the era of big data. Recent years we have witnessed significant success on deep learning-based models for drug-target binding affinity prediction task. However, these models only considered a single modality of drug and target information, and some valuable information was not fully utilized. In fact, the information of different modalities of drug and target can complement each other, and more valuable information can be obtained by fusing the information of different modalities. In this paper, we introduce a multimodal information fusion model for DTA prediction that is called FMDTA, which fully considers drug/target information in both string and graph modalities and balances the feature representations of different modalities by a contrastive learning approach. In addition, we exploited the alignment information of drug atoms and target residues to capture the positional information of string patterns, which can extract more useful feature information in SMILES and target sequences. Experimental results on two benchmark datasets show that FMDTA outperforms the state-of-the-art model, demonstrating the feasibility and excellent feature capture capability of FMDTA. The code of FMDTA and the data are available at: https://github.com/bestdoubleLin/FMDTA. [ABSTRACT FROM AUTHOR]

The number of Vehicle Equipment (VE) connected to the Internet is increasing, and these VEs generate tasks that contain large amounts of data. Processing these tasks requires a lot of computing resources. Therefore, it is a promising issue that offloading compute-intensive tasks from resource-limited vehicles to Vehicular Edge Computing (VEC) servers, which involves big data transmission, processing and computation. In a network, multiple providers provide VEC servers. When a vehicle generates a task, our goal is to make an intelligent decision on whether and when to offload this task to VEC servers to minimize the task completion time and total big data processing time. When each vehicle passes VEC servers, the vehicle can decide to offload its task to the VEC server in the current communication range, or continue to drive until it reaches the next server's communication range. This issue can be considered as an asset selling problem. It is a challenging issue to make a smart decision for the vehicle with a location view because the vehicle is not sure when the next VEC server will be available and how much about the available computing capacity of the next VEC server. Firstly, this paper formulates the problem as a Markov Decision Process (MDP), defines and analyzes the state set, action set, reward model, and state transition probability distribution. Then it uses Asynchronous Advantage Actor-Critic (A3C) algorithm to solve this MDP problem, builds the various elements of the A3C algorithm, uses Actor (the strategy function) to generate two actions of the vehicle: offloading and moving without offloading. Thirdly, it uses Critic (the value function) to evaluate Actor's behavior, and guide Actor's actions in subsequent stages. The Actor starts from the initial state in the state space until it enters the termination state, forming a complete decision-making process. It minimizes the completion time of task offloading through learning thereby reducing the delay of big data processing. Compared to the Immediately Offload (IO) scheme and Expect Offload (EO) scheme, the MIDP scheme proposed in this paper reduces the average task offloading delay to 29.93% and 29.99%, close to the EO scheme in terms of task completion rate and up to 66.6% improvement compared to the IO scheme. • A task offloading approach in Internet of Vehicles (IoV) is proposed. • An MDP-based Intelligent Big Data Processing (MIDP) Scheme is proposed. • Simulations demonstrate the better performances of MIDP scheme. [ABSTRACT FROM AUTHOR]

To explore contemporary college students' lack of learning motivation, this paper evaluates the students' comprehensive performance by quoting the fuzzy neural network system and adjusting the teaching plan according to the evaluation results to drive the students' learning enthusiasm and improve the student's performance. The University campus is unique for students. They need to learn professional knowledge and face the environment of entering society in the future, which is equivalent to a turning point in the undertaking. Learning here is relatively easy, lacks parental constraints, and their time is relatively free. After learning without motivation, people will also show a negative side. By adjusting teachers' teaching plans, this paper improves students' learning subjectivity, breaks the deadlock of teacher-student interaction in the past, changes students' learning atmosphere, and improves students' comprehensive quality. It also gives suggestions for the innovative teachers' teaching methods system, which will contribute to developing China's future education. [ABSTRACT FROM AUTHOR]

• LOF is an unsupervised anomaly detection algorithm that mines anomalies by calculating the local density of data points relative to their neighborhood. In this work LOF algorithm was implemented using the ECL (enterprise control language) programming language on the HPCC systems (high-performance computing cluster system) platform, an open-source distributed computing platform. • Improved LOF is a modified version of normal LOF, designed to handle datasets with duplicates. This work discusses the implementation of both normal LOF and improved LOF algorithms in HPCC systems for credit card fraud detection and localization data for person activity datasets. • Segmented k - d tree and unsegmented k - d tree are techniques proposed for neighbor search in a distributed system with worst-case time complexity of O((MinPts *| D |)*log(| D |)), where | D | represents the number of data points in the dataset and MinPts is the hyperparameter value. • LOF compared with other anomaly detection algorithms like COF, LoOP, and kNN across 6 benchmark datasets in the HPCC systems platform, demonstrating a favorable balance between execution time and precision in anomaly detection. • LOF implementation was compared across big-data frameworks like Spark, Hadoop, and HPCC systems revealing superior scalability and performance in HPCC systems, especially with larger datasets and higher MinPts values. Local Outlier Factor (LOF) is an unsupervised anomaly detection algorithm that finds anomalies by assessing the local density of a data point relative to its neighborhood. Anomaly detection is the process of finding anomalies in datasets. Anomalies in real-time datasets may indicate critical events like bank frauds, data compromise, network threats, etc. This paper deals with the implementation of the LOF algorithm in the HPCC Systems platform, which is an open-source distributed computing platform for big data analytics. Improved LOF is also proposed which efficiently detects anomalies in datasets rich in duplicates. The impact of varying hyperparameters on the performance of LOF is examined in HPCC Systems. This paper examines the performance of LOF with other algorithms like COF, LoOP, and kNN over several datasets in the HPCC Systems. Additionally, the efficacy of LOF is evaluated across big-data frameworks such as Spark, Hadoop, and HPCC Systems, by comparing their runtime performances. [ABSTRACT FROM AUTHOR]

Big data processing frameworks such as Spark usually provide a large number of performance-related configuration parameters, how to auto-tune these parameters for a better performance has been a hot issue in academia as well as industry for years. Through delicately tradeoff between exploration and exploitation, Bayesian Optimization (BO) is currently the most appealing algorithm to achieve configuration auto-tuning. However, considering the tuning cost constraint in practice, there are three critical limitations preventing conventional BO-based approaches from being directly applied into auto-tuning cluster-based big data frameworks. In this paper, we propose a cost-efficient configuration auto-tuning approach named TurBO for big data frameworks based on two enhancements of vanilla BO:1) To reduce the essential iteration times, TurBO integrates a well-designed adaptive pseudo point mechanism with BO; 2) To avoid the time-consuming practical evaluation of sub-optimal configurations as possible, TurBO leverages the proposed CASampling method to intelligently tackle with these sub-optimal configurations based on ensemble learning with historical tuning experiences. To evaluate the performance of TurBO, we conducted a series of experiments on a local Spark cluster with 9 different HiBench benchmark applications. Overall, compared with 3 representative BO-based baseline approaches OpenTuner, Bliss and ResTune, TurBO is able to speedup the tuning procedures respectively by 2.24×, 2.29× and 1.97× on average. Besides, TurBO can always achieve a positive cumulative performance gain under the simulated dynamic workload scenario, which means TurBO is indeed appropriate for workload changes of big data applications. • Analyze the limitations of vanilla Bayesian optimization considering tuning cost. • Implement a cost-efficient configuration auto-tuning approach named TurBO. • TurBO reduces iteration times via an adaptive pseudo point mechanism with BO. • TurBO reduces configuration evaluation cost via an ensemble learning-based method. • Experiments on a Spark cluster show the effectiveness and efficiency of TurBO. [ABSTRACT FROM AUTHOR]

The construction of systems supporting spatial data has experienced great enthusiasm in the past, due to the richness of this type of data and their semantics, which can be used in the decision-making process in various fields. Thus, the problem of integrating spatial data into existing databases and information systems has been addressed by creating spatial extensions to relational tables or by creating spatial data warehouses, while arranging data structures and query languages by making them more spatially-aware. With the advent of Big Data, these conventional storage and spatial representation structures are becoming increasingly outdated, and required a new organization of spatial data. Approaches based on distributed storage and data lakes have been proposed, to integrate the complexity of spatial data, with operational and analytical systems which unfortunately quickly showed their limits. Recently the concept of lakehouse was introduced in order to integrate, among other things, the notion of reliability and ACID properties to the volume of data to be managed. This new data architecture is a combination of governed and reliable Data Warehouses and flexible, scalable and cost-effective Data Lakes. In this paper, we present how traditional approaches of spatial data management in the context of spatial big data have quickly shown their limits. We present a literature overview of these approaches, and how they led to the Data LakeHouse. We detail how the Lakehouse paradigm can be used and extended for managing spatial big data, by giving the different components and best practices for building a spatial data LakeHouse architecture optimized for the storage and computing over spatial big data. • Limitations of Data Warehouses and Data Lakes for Spatial Big Data. • Characteristics and Architecture of the Data LakeHouse. • Overview of Three Major Open Source LakeHouse Systems. • Challenges in Using Data LakeHouse for Spatial Big Data. • Optimized Data LakeHouse Architecture for Spatial Big Data. [ABSTRACT FROM AUTHOR]

This paper studies a flexible approach to analyze high-dimensional nonlinear time series of unconstrained dimension based on linear statistics calculated from spectral average statistics of bilinear forms and nonlinear transformations of lag-window (i.e. band-regularized) spectral density matrix estimators. That class of statistics includes, among others, smoothed periodograms, nonlinear statistics such as coherency, long-run-variance estimators and contrast statistics related to factorial effects as special cases. Especially, we introduce the class of nonlinear spectral averages of the spectral density matrix. Having in mind big data settings, we study a sampling design which includes a sparse sampling scheme. Gaussian approximations with optimal rate are derived for nonlinear time series of growing dimension for these frequency domain statistics and the underlying lag-window (cross-) spectral estimator under non-stationarity. For change-testing (self-standardized) CUSUM statistics are examined. Further, a specific wild bootstrap procedure is proposed to estimate critical values. Simulation studies and an application to SP500 financial returns are provided in a supplement to this paper. [ABSTRACT FROM AUTHOR]

The wide adoption of IoT technologies has accelerated the accumulation of big data. Recommender systems (RS) is one of the most effective methods to extract user interested items from the huge volume of big data. However, implementing a recommender system over the distributed error-prone IoT devices faces two challenges. On the one hand, the distributed IoT devices may randomly fail to deliver its local data due to hardware malfunction, which may cause unavailability of the recommender system. Moreover, collecting the raw data from the distributed IoT devices may cause data privacy leakage issue, since the privacy data of user-item interaction records may be abused by vicious parties. In view of these challenges, we propose a federated collaborative recommendation model based on microservice framework in this paper to implement privacy preserving distributed recommendation applications. Firstly, we utilize the federated learning framework to train the collaborative recommendation model, where the raw data on each distributed device is kept locally and only item related model parameters are exposed to train the federated recommendation model. Moreover, we adopt the microservice framework to encapsulate different functions of the federated recommender model. Each distributed device can participate in the federated training process via service registration and service discovery function of the microservice framework. Furthermore, we enhance the typical Neural Collaborative Filtering model with the proposed FedNeuMF model by fusing auxiliary user profiles and item attributes to improve the recommendation accuracy. Finally, we conduct a set of experiments on three real-world datasets to check the performance of our proposal. • A federated recommendation model is proposed based on the microservice framework. • Auxiliary information is adopted to enhance the typical neural CF model. • A set of experiments is conducted to verify the performance of the proposal. [ABSTRACT FROM AUTHOR]

Option pricing is one of the most active Financial Economics research fields. Black-Scholes-Merton option pricing theory states that risk-neutral density is lognormal. However, markets' pieces of evidence do not support that assumption. More realistic assumptions impose substantial computational burdens to calculate option pricing functions. Risk-neutral density is a pivotal element to price derivative assets, which can be estimated through nonparametric kernel methods. A significant computational challenge exists for determining optimal kernel bandwidths, addressed in this study through a parallel computing algorithm performed using Graphical Processing Units. The paper proposes a tailor-made Cross-Validation criterion function used to define optimal bandwidths. The selection of optimal bandwidths is crucial for nonparametric estimation and is also the most computationally intensive. We tested the developed algorithms through two data sets related to intraday data for VIX and S&P500 indexes. • An example of such big data environments is information associated with financial options contracts. • Second, we developed methods to estimate the risk-neutral density as a pivotal element for options pricing. • Third, we found that nonparametric methods should be adapted for estimating the second derivatives, which relate to the risk-neutral densities. • Fourth, the proposed adaptations imply significant computational burdens defining bandwidths for nonparametric estimators. • Fifth, we found that parallel computing procedures can reduce computational times, compatible with needed dynamic updating. [ABSTRACT FROM AUTHOR]

Processing high-throughput data-streams has become a major challenge in areas such as real-time event monitoring, complex dataflow processing, and big data analytics. While there has been tremendous progress in distributed stream processing systems in the past few years, the high-throughput and low-latency (a.k.a. high sustainable-throughput) requirement of modern applications is pushing the limits of traditional data processing infrastructures. This paper introduces a new distributed stream processing engine (DSPE), called Asynchronous Iterative Routing (or simply "AIR"), which implements a light-weight, dynamic sharding protocol. AIR expedites direct and asynchronous communication among all the worker nodes via a channel-like communication protocol on top of the Message Passing Interface (MPI), thereby completely avoiding the need for a dedicated driver node. The system adopts a new progress-tracking protocol, called hew-meld , which has been experimentally observed to show a low processing latency on our asynchronous master-less architecture when compared to the conventional low-watermark technique. The current version of AIR is also equipped with two fault tolerance and recovery strategies namely checkpointing & rollback and replication. With its unique design, AIR scales out particularly well to multi-core HPC architectures; specifically, we deployed it on clusters with up to 16 nodes and 448 cores (thus reaching a peak of 435.3 million events and 55.14 GB of data processed per second), which we found to significantly outperform existing DSPEs. • A new open source distributed stream processing engine (DSPE), called Asynchronous Iterative Routing (or simply "AIR"), which implements a light-weight, dynamic sharding protocol. • With its unique design, AIR scales out particularly well to multi-core HPC architectures. • Specifically, we deployed it on clusters with up to 16 nodes and 448 cores (thus reaching a peak of 435.3 million events and 55.14 GB of data processed per second), which we found to significantly outperform existing DSPEs. [ABSTRACT FROM AUTHOR]

Cloud service for data outsourcing has triggered security and privacy needs that can be satisfied by encrypting data prior to outsourcing to the cloud. Searchable Encryption that uses methods like homomorphic encryption is inefficient and impractical. In this paper, we have proposed a secure searchable encryption scheme using Hash based Indexing that consists of Elliptic curve based ElGamal additive homomorphic encryption. The use of indexing reduces computational load on the cloud server and users. The scheme obviates the need for generation and resource intensive processing on complex trapdoor system and binary query scheme. The security of this system relies on the Elliptic curve discrete logarithm problem assumption. Comparison analysis is performed and experimental results prove the suitability for the large data sets, while efficiently supporting the dynamic updates and effective ranking of precise files corresponding to the requested multi keywords. [ABSTRACT FROM AUTHOR]

With the advent of die stacking technology and big data applications, Processing-in-memory (PIM) is regaining attention as a promising technology for improving performance and energy efficiency. Although various PIM techniques have been proposed in recent studies for effectively offloading computation from the host, the thermal impacts of PIM offloading have not been fully explored. This paper investigates the thermal constraints of PIM and proposes techniques to enable thermal awareness for efficient PIM offloading. To understand the thermal effects of 3D-stacked designs, we measure the temperature of a real Hybrid Memory Cube (HMC) prototype and observe that compared to conventional DRAM, HMC reaches a significantly higher operating temperature, which causes thermal shutdowns with a passive cooling solution. Even with a commodity-server cooling solution, when in-memory processing is highly utilized, HMC fails to maintain the temperature of the memory dies within the normal operating range. In this paper, we propose a collection of software- and hardware-based techniques to enable thermal-aware PIM offloading by controlling the intensity of PIM offloading at runtime. Our evaluation results show that the proposed techniques achieve up to 1.4 × and 1.37 × speedups compared to non-offloading and naïve offloading scenarios. • We provide a thermal analysis to understand the thermal constraints of a real-world 3D memory. • Our thermal analysis shows that DRAM layers can exceed the normal operating temperature when PIM offloading is used. • We propose a collection of thermal-aware source throttling techniques that dynamically controls the intensity of PIM offloading. [ABSTRACT FROM AUTHOR]

Abstract Data Assimilation (DA) is an uncertainty quantification technique used to incorporate observed data into a prediction model in order to improve numerical forecasted results. Variational DA (VarDA) is based on the minimisation of a function which estimates the discrepancy between numerical results and observations. Operational forecasting requires real-time data assimilation. This mandates the choice of opportune methods to improve the efficiency of VarDA codes without loosing accuracy. Due to the scale of the forecasting area and the number of state variables used to describe the physical model, DA is a big data problem. In this paper, the Truncated Singular Value Decomposition (TSVD) is used to reduce the space dimension, alleviate the computational cost and reduce the errors. Nevertheless, a consequence is that important information is lost if the truncation parameter is not properly chosen. We provide an algorithm to compute the optimal truncation parameter and we prove that the optimal estimation reduces the ill-conditioning and removes the statistically less significant modes which could add noise to the estimate obtained from DA. In this paper, numerical issues faced in developing VarDA algorithm include the ill-conditioning of the background covariance matrix, the choice of a preconditioning and the choice of the regularisation parameter. We also show how the choice of the regularisation parameter impacts on the efficiency of the VarDA minimisation computed by the L-BFGS (Limited – Broyden Fletcher Goldfarb Shanno). Experimental results are provided for pollutant dispersion within an urban environment. Highlights • A Variational DA model is introduced for air flows prediction and pollution transport. • The optimal truncation parameter minimises condition number and Preconditioning Error. • The TSVD truncation parameter is independent from the knowledge of an exact solution. • The optimal truncation parameter does not require the whole spectrum of the matrix. [ABSTRACT FROM AUTHOR]

Abstract With the wide application of big data technology and the continuous innovation of the financial industry, the development of Internet finance has become irreversible. The new financial model has improved the efficiency of financial services and formed new ways of payment and transaction. The traditional credit information system has been unable to meet the needs of the development of the financial industry. The research methods adopted in this paper mainly include literature research, case analysis and comparative analysis. The development process, current situation and characteristics of China's personal credit system, as well as the development process and current situation of China's personal credit system under Internet finance are analyzed. It also points out the main problems faced by China's personal credit reporting system under the Internet finance. Then, aiming at the specific problems faced by China's personal credit reporting system under Internet finance, this paper makes case studies of representative market-oriented credit reporting institutions such as Beijing, Tianjin and Hebei, and uses convolutional neural network to analyze the specific practices of these individual credit reporting institutions and achieves results. At the same time, it compares how different credit agencies make up for the shortcomings of personal credit reporting system. Finally, it draws the conclusion of perfecting the personal credit system of our country under the Internet finance, points out the new problems that may be brought by the superposition of various solutions, and puts forward the countermeasures and suggestions of perfecting the personal credit system of our country under the Internet finance. [ABSTRACT FROM AUTHOR]

Synergetic control of environmental pollution and carbon emissions (SCEPCE) is essential to green development. The emergence of the digital economy has become a significant component in regional economic growth. Investigating the digital driving mode for SCEPCE in developing countries is crucial. This paper empirically analyzes the effect of establishing big data comprehensive experimental areas (BDCEAs) on air pollutants and carbon emissions using panel data of prefecture-level cities from 2009 to 2020 and the time-varying difference-in-differences method. The research found that (1) BDCEA inhibits pollution and carbon emissions, and the policy effect is sustainable. (2) The synergistic effect is significant, particularly in small and medium-sized cities and old industrial-base cities. The benefit of reducing pollution is only significant in the east. The effect of reducing CO 2 emissions is only significant in the west. (3) The pollution reduction effect of digital economic development has the characteristics of an increasing marginal effect, and the marginal effect of its carbon reduction effect is not apparent. (4) The technological innovation and energy efficiency improvement effects are effective mechanisms. This paper enriches the studies on the factors influencing SCEPCE, which will help to realize SCEPCE and the harmonious coexistence of humans and nature in developing countries. However, policy incentives and green development strategies must be fine-tuned to achieve global SCEPCE. • Digital economy realizes synergistic effect of pollution and carbon emission mitigation. • The findings have significant implications for governments. • The pollution reduction effect has the characteristics of an increasing marginal effect. • The technological innovation and energy eficiency improvement effects are effective mechanisms. [ABSTRACT FROM AUTHOR]

• We abstract a multipath parallel heterogeneous network node mapping model. • We propose a fast convergent network characteristics prediction algorithm. • We design a packet granularity scheduling scheme for multipath communication. • We apply the new results to some known network simulation models. Multipath parallel transmission has become an important research direction to improve big data transmission efficiency of connected vehicles. However, due to the heterogeneity and time-varying characteristics of parallel transmission paths, packets transmitted in parallel are usually out-of-order delivered to the destination, which greatly limits the throughput. To Lift the restriction of out-of-order delivery on the efficiency of big data transmission, this paper proposes a packet-granular real-time shortest delay scheduling scheme for multipath transmission based on path characteristics prediction. The scheme first clusters and models the heterogeneous network, which greatly reduces the complexity of the network. Subsequently, a prediction algorithm that can quickly converge to real-time delay is proposed. Then the details of the scheduling scheme are introduced by modules, and the bandwidth aggregation efficiency close to the theoretical upper limit is proved through simulation. Finally, we summarize the applicable scenarios and future work of the scheme. [ABSTRACT FROM AUTHOR]

[Display omitted] Calculating the magnetic interaction between magnetic particles that are positioned in close proximity to one another is a surprisingly challenging task. Exact solutions for this interaction exist either through numerical expansion of multipolar interactions or through solving Maxwell's equations with a finite element solver. These approaches can take hours for simple configurations of three particles. Meanwhile, across a range of scientific and engineering problems, machine learning approaches have been developed as fast computational platforms for solving complex systems of interest when large data sets are available. In this paper, we bring the touted benefits of recent advances in science-based machine learning algorithms to bear on the problem of modeling the magnetic interaction between three particles. We investigate this approach using diverse machine learning systems including physics informed neural networks. We find that once the training data has been collected and the model has been initiated, simulation times are reduced from hours to mere seconds while maintaining remarkable accuracy. Despite this promise, we also try to lay bare the current challenges of applying machine learning to these and more complex colloidal systems. [ABSTRACT FROM AUTHOR]

• We characterize the component connectivity of regular networks with some restrictions. • We establish the relationship between component connectivity and component diagnosability of a class of networks. • We apply the newly obtained results to some well-known networks. Enhancing the invulnerability of multiprocessor systems against malicious attacks has been regarded as one of the important issues in network science and big data era. Thus, in order to firmly characterize the robustness of systems, several variants of classic connectivity have been proposed so far. The component connectivity is a significant metric in evaluating the robustness and fault tolerability of interconnection network. For an interconnection network G and a positive integer h , the (h + 1) -component connectivity of G , denoted c κ h + 1 (G) , is the cardinality of a minimum vertex cut F such that G − F has at least h + 1 connected components. Based on component connectivity, component diagnosability has been proposed to measure the self-diagnosis capability of multiprocessor systems. In this paper, we suggest some characterizations of the (h + 1) -component connectivity of a class of regular networks under some restrictions. Furthermore, we establish the relationship between component connectivity and component diagnosability of one class of networks. As by-products, we present the (h + 1) -component diagnosability of the state-of-the-art compound networks based on hypercube, such as bicube network, generalized exchanged hypercube, hierarchical hypercube, half-hypercube, and so on. [ABSTRACT FROM AUTHOR]

• An encoding scheme named Pathed-Dewey Order for nodes in XML documents. • An XML-to-HBase mapping strategy based on Pathed-Dewey Order. • An algorithm to translate XPath into query operations on HBase tables. • Supports efficient storage and query of large collections of small XML documents. • A superior performance of XML2HBase over existing solutions in target use cases. Many big data applications such as smart transportation, healthcare, and e-commerce need to store and query large collections of small XML documents, which has become a fundamental problem. However, existing solutions are inadequate to deliver satisfactory query performance in such circumstances. In this paper, we propose a framework named XML2HBase to address this problem using HBase, a widely deployed NoSQL database. Within this framework, we design a novel encoding scheme called Pathed-Dewey Order and a two-layer mapping method to store XML documents in HBase tables. XML queries, which are represented as XPath expressions, are evaluated through their translation into queries over HBase tables. Based on an in-depth analysis of the characteristics of the proposed approach, we design and integrate four optimization strategies to reduce storage space and query response time. Extensive experiments on two well-known XML benchmarks demonstrate the superior performance of XML2HBase over three state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Stream Processing Systems (SPSs) dynamically process input events. Since the input is usually not a constant flow, presenting rate fluctuations, many works in the literature propose to dynamically replicate SPS operators, aiming at reducing the processing bottleneck induced by such fluctuations. However, these SPSs do not consider the problem of load balancing of the replicas or the cost involved in reconfiguring the system whenever the number of replicas changes. We present in this paper a predictive model which, based on input rate variation, execution time of operators, and queued events, dynamically defines the necessary current number of replicas of each operator. A predictor, composed of different models (i.e., mathematical and Machine Learning ones), predicts the input rate. We also propose a Storm-based SPS, named PA-SPS, which uses such a predictive model, not requiring reboot reconfiguration when the number of operators replica change. PA-SPS also implements a load balancer that distributes incoming events evenly among replicas of an operator. We have conducted experiments on Google Cloud Platform (GCP) for evaluation PA-SPS using real traffic traces of different applications and also compared it with Storm and other existing SPSs. • A prediction-based model for dynamically adapting SPS with highly variable traffic rate environments. • A new event grouping strategy that exploits operators' use. • The design and implementation of an elastic stream processing system based on Apache Storm with autonomic behaviour. • Performance evaluation of the proposed SPS through extensive experiments using real-world datasets on Google Cloud Platform. [ABSTRACT FROM AUTHOR]

Big data frameworks are widely deployed in supercomputers for analyzing large-scale datasets. Topological data processing is an emerging approach that focuses on analyzing the topological structures in high-dimensional scientific data. However, incorporating topological data processing into current big data frameworks presents three main challenges: (1) The frequent data exchange poses challenges to the traditional coarse-grained parallelism. (2) The spatial topology makes parallel programming harder using oversimplified MapReduce APIs. (3) The massive intermediate data and NUMA architecture hinder resource utilization and scalability on novel supercomputers and many-core processors. In this paper, we present Topo, a generic distributed framework that enhances topological data processing on many-core supercomputers. Topo relies on three concepts. (1) It employs fine-grained parallelism, with awareness of topological structures in datasets, to support interactions among collaborative workers before each shuffle phase. (2) It provides intuitive APIs for topological data operations. (3) It implements efficient collective I/O and NUMA-aware dynamic task scheduling to improve multi-threading and load balancing. We evaluate Topo's performance on the Tianhe-3 supercomputer, which utilizes state-of-the-art ARM many-core processors. Experimental results of execution time show that compared to popular frameworks, Topo achieves an average speedup of 5.3× and 6.3×, with a maximum speedup of 8.4× and 20×, on HPC workloads and big data benchmarks, respectively. Topo further reduces total execution time on processing skewed datasets by 41%. [ABSTRACT FROM AUTHOR]

Healthcare provides many services such as diagnosing, treatment, prevention of diseases, illnesses, injuries, and other physical and mental disorders. Large-scale distributed data processing applications in healthcare as a basic concept operates on large amounts of data. Therefore, big data application functions are the main part of healthcare operations, but there was not any comprehensive and systematic survey about studying and evaluating the important techniques in this field. Therefore, this paper aims at providing the comprehensive, detailed, and systematic study of the state-of-the-art mechanisms in the big data related to healthcare applications in five categories, including machine learning, cloud-based, heuristic-based, agent-based, and hybrid mechanisms. Also, this paper displayed a systematic literature review (SLR) of the big data applications in the healthcare literature up to the end of 2016. Initially, 205 papers were identified, but a paper selection process reduced the number of papers to 29 important studies. [ABSTRACT FROM AUTHOR]

In recent years, the research of marine environmental monitoring system has been especially popular. The construction of Internet of things between devices occupies the main position in marine environment detection system. In order to protect and utilize marine resources, it is urgent to realize the collection and treatment of marine information. We have established the Internet of things system for large ocean data collected by sensors. We calculate the ocean data in terminal devices such as sensors. In the process of calculation and arrangement of data, this paper presents a new method for the calculation of data contours. The aim of this method is to quickly describe the contour of data. The distribution of contour lines can be calculated accurately in a short time. This paper introduces the principle and calculation process of the method. The simulation of big data calculation is carried out in practice. The simulation results are also analyzed. Finally, the advantages of this method are illustrated by comparison simulation. In the same set of data and conditions, the method achieves the improvement of computational efficiency and calculation accuracy. It has certain significance in practical application. [ABSTRACT FROM AUTHOR]

This paper is an extension of the previous work of Chui et al. (2015) [4] , not only from numeric data to include non-numeric data as in that paper, but also from undirected graphs to directed graphs (called digraphs, for simplicity). Besides theoretical development, this paper introduces effective mathematical tools in terms of certain data-dependent orthogonal systems for function representation and analysis directly on the digraphs. In addition, this paper also includes algorithmic development and discussion of various experimental results on such data-sets as CORA, Proposition, and Wiki-votes. [ABSTRACT FROM AUTHOR]

Existing knowledge distillation methods use large amount of bilingual data and focus on mining the corresponding knowledge distribution between the source language and the target language. However, for some languages, bilingual data is not abundant. In this paper, to make better use of both monolingual and limited bilingual data, we propose a new knowledge distillation method called Dual Knowledge Distillation (DKD). For monolingual data, we use a self-distillation strategy which combines self-training and knowledge distillation for the encoder to extract more consistent monolingual representation. For bilingual data, on top of the k Nearest Neighbor Knowledge Distillation (kNN-KD) method, a similar self-distillation strategy is adopted as a consistency regularization method to force the decoder to produce consistent output. Experiments on standard datasets, multi-domain translation datasets, and low-resource datasets show that DKD achieves consistent improvements over state-of-the-art baselines including kNN-KD. • Monolingual data can better help low-resource machine translation. • Dual Knowledge Distillation can better use bilingual and monolingual data. • Self-distillation can extract more consistent monolingual representation. • Consistency regularization can force the decoder to generate consistent output. [ABSTRACT FROM AUTHOR]

• A series of short, self-contained learning modules on bigdata and cloud computing were developed and dispersed over several core CS courses. • Modules are designed following established learning theories that adequately characterizes the embraced competency-based model. • Modules provide hands-on experiences using cloud analytics engines such as Hadoop and Spark on popular cloud platforms. • The GitHub repository of modules is available for broader adoption. • Student performance and survey results show reasonable success in attaining learning outcomes and enhanced interests. Big data and cloud computing collectively offer a paradigm shift in the way businesses are now acquiring, using, and managing information technology. This creates the need for every CS student to be equipped with foundational knowledge in this collective paradigm and possess some hands-on experience in deploying and managing big data applications in the cloud. This study argues that, for substantial coverage of big data and cloud computing concepts and skills, the relevant topics need to be integrated into multiple core courses across the CS curriculum rather than creating additional courses and performing a major overhaul of the curriculum. Our approach to including these topics is to develop autonomous competency-based learning modules for specific core courses in which their coverage might find an appropriate context. In this paper, four such modules are discussed, and our classroom experiences during these interventions are documented. Student performance data and survey results show reasonable success in attaining student learning outcomes, enhanced engagement, and interests. [ABSTRACT FROM AUTHOR]

In a proxy re-signature scheme, a semi-trusted proxy can convert Alice's (also called as delegatee's) signature into Bob's (also called as delegator's) signature on the same message. However, the proxy itself cannot produce any signatures on behalf of either Alice or Bob. There exists some unidirectional one-use and multi-use (a message can be re-signed a polynomial number of times) proxy re-signature schemes. In some scenarios of big data, it is required to design unidirectional infinite-use (a message can be re-signed infinite number of times) proxy re-signature schemes. In this paper, we propose the first unidirectional infinite-use proxy re-signature scheme and identity-based unidirectional infinite-use proxy re-signature scheme with private re-signature keys based on lattice and prove that they are secure in the random oracle model. [ABSTRACT FROM AUTHOR]

This paper describes a new visualization approach for the automatic generation of visual summaries dealing with cartographic visualization methods and modeling of real time data coming from sensors. Indeed the concept of chorems seems an interesting candidate to visualize real time geographic database summaries. Chorems have been defined by Roger Brunet as schematized visual representations of territories. However, the time information is not yet handled in existing chorematic map approaches, that is the issue been discussed in this paper in which geodata are coming regularly from sensors distributed along some territory. Our approach is based on spatial analysis by interpolating the values recorded at the same time, so we have a number of distributed observations on areas of study. To get a better visual overview of the entire sensor geodata at a given time, we use spatial statistics formulas on the fly, and so it is possible to extract important spatiotemporal patterns and detect trends over time as geographic rules. Then, those spatiotemporal patterns are visualized as animated chorems. An example is taken from meteorology. [ABSTRACT FROM AUTHOR]

In the paper, we suggest three tests on the validity of a factor model which can be applied for both, small-dimensional and large-dimensional data. The exact and asymptotic distributions of the resulting test statistics are derived under classical and high-dimensional asymptotic regimes. It is shown that the critical values of the proposed tests can be calibrated empirically by generating a sample from the inverse Wishart distribution with identity parameter matrix. The powers of the suggested tests are investigated by means of simulations. The results of the simulation study are consistent with the theoretical findings and provide general recommendations about the application of each of the three tests. Finally, the theoretical results are applied to two real data sets, which consist of returns on stocks from the DAX index and on stocks from the S&P 500 index. Our empirical results do not support the hypothesis that all linear dependencies between the returns can be entirely captured by the factors considered in the paper. [ABSTRACT FROM AUTHOR]

The term big data is currently a buzzword in social science, however its precise meaning is ambiguous. In this paper we focus on administrative data which is a distinctive form of big data. Exciting new opportunities for social science research will be afforded by new administrative data resources, but these are currently under appreciated by the research community. The central aim of this paper is to discuss the challenges associated with administrative data. We emphasise that it is critical for researchers to carefully consider how administrative data has been produced. We conclude that administrative datasets have the potential to contribute to the development of high-quality and impactful social science research, and should not be overlooked in the emerging field of big data. [ABSTRACT FROM AUTHOR]

Quantity and quality of grain are both closely related to national development and social stability. Grain is lost during storage due to mildew and insects. Detection of damaged grain kernels not only can reduce the loss of grain, but also protect human beings from diseases caused by damaged grain. Therefore, research on the automatic detection of damaged grain is of continued urgency. In this paper, we propose a framework combining spectrogram generative adversarial network and progressive neural architecture search (SPGAN-PNAS) to detect and classify mildew-damaged wheat kernels (MDK), insect-damaged wheat kernels (IDK) and undamaged wheat kernels (UDK). First, the spectrogram generative adversarial network (SPGAN) is designed to enlarge the data set. Second, we apply progressive neural architecture search (PNAS) to generate network structure to classify three types of wheat kernels. An F1 of 96.2% is obtained using the proposed method with 5-fold cross-validation. The results are superior to the classical neural networks for detection and classification of damaged wheat kernels. Experimental results show that the structure of SPGAN-PNAS is feasible and effective. • A novel framework SPGAN-PNAS was proposed for detection of damaged wheat kernels. • Neural architecture search applied to detection and classification of damaged wheat. • Good and rapid results for detection and classification of damaged wheat kernels. • Method particularly suitable for large data sets. [ABSTRACT FROM AUTHOR]

The bi-directional flow of energy and information in the smart grid makes it possible to record and analyze the electricity consumption profiles of consumers. Because of the increasing rate of inflation over the past few years, people started looking for means to use electricity illegally, termed as electricity theft. Many data analytics techniques are proposed in the literature for electricity theft detection (ETD). These techniques help in the detection of suspected illegal consumers. However, the existing approaches have a low ETD rate either due to improper handling of the imbalanced class problem in a dataset or the selection of inappropriate classifier. In this paper, a robust big data analytics technique is proposed to resolve the aforementioned concerns. Firstly, adaptive synthesis (ADASYN) is applied to handle the imbalanced class problem of data. Secondly convolutional neural network (CNN) and long-short term memory (LSTM) integrated deep siamese network (DSN) are proposed to discriminate the features of both honest and fraudulent consumers. Specifically, the task of feature extraction from weekly energy consumption profiles is handed over to the CNN module while the LSTM module performs the sequence learning. Finally, the DSN contemplates on the shared features provided by the CNN-LSTM and applies final judgment. The data analytics is performed on different train–test ratios of the real-time smart meters' data. The simulation results validate the proposed model's effectiveness in terms of high area under the curve, F 1 -Score, precision and recall. • A robust big data analytic technique for electricity theft detection in smart grid is proposed. • We propose an adaptive synthesis to handle imbalanced class problem. • A deep siamese network with underpinned integrated networks of convolution neural network and long-short term memory is proposed to discriminate both features of fair and fraud consumers. • Simulation results validate the proposed model in terms of high area under the curve, low false positive rate and low false negative rate. [ABSTRACT FROM AUTHOR]

Linear algebra operations have been widely used in big data analytics and scientific computations. Many works have been done on optimizing linear algebra operations on GPUs with regular-shaped input. However, few works focus on fully utilizing GPU resources when the input is not regular-shaped. Current optimizations do not consider fully utilizing the memory bandwidth and computing power; therefore, they can only achieve sub-optimal performance. In this paper, we propose two efficient algorithms – TSM2R and TSM2L – for two classes of tall-and-skinny matrix–matrix multiplications on GPUs. Both of them focus on optimizing linear algebra operation with at least one of the input matrices tall-and-skinny. Specifically, TSM2R is designed for a large regular-shaped matrix multiplying a tall-and-skinny matrix, while TSM2L is designed for a tall-and-skinny matrix multiplying a small regular-shaped matrix. We implement our proposed algorithms and test on several modern NVIDIA GPU micro-architectures. Experiments show that, compared to the current state-of-the-art works, (1) TSM2R speeds up the computation by 1.6x on average and improves the memory bandwidth utilization and computing power utilization by 18.1% and 20.5% on average, respectively, when the regular-shaped matrix size is relatively large or medium; and (2) TSM2L speeds up the computation by 1.9x on average and improves the memory bandwidth utilization by up to 9.3% on average when the regular-shaped matrix size is relatively small. • Few works focus on optimizing GEMM on GPUs for the irregular-shaped input. • Current optimizations do not fully utilize the memory bandwidth and computing power. • We propose two efficient algorithms for two classes of tall-and-skinny GEMM on GPUs. • Our optimizations speedup GEMM by 1.1x ∼ 3.5x for various tall-and-skinny inputs. [ABSTRACT FROM AUTHOR]

The multispecies coalescent process models the genealogical relationships of genes sampled from several species, enabling useful predictions about phenomena such as the discordance between a gene tree and the species phylogeny due to incomplete lineage sorting. Conversely, knowledge of large collections of gene trees can inform us about several aspects of the species phylogeny, such as its topology and ancestral population sizes. A fundamental open problem in this context is how to efficiently compute the probability of a gene tree topology, given the species phylogeny. Although a number of algorithms for this task have been proposed, they either produce approximate results, or, when they are exact, they do not scale to large data sets. In this paper, we present some progress towards exact and efficient computation of the probability of a gene tree topology. We provide a new algorithm that, given a species tree and the number of genes sampled for each species, calculates the probability that the gene tree topology will be concordant with the species tree. Moreover, we provide an algorithm that computes the probability of any specific gene tree topology concordant with the species tree. Both algorithms run in polynomial time and have been implemented in Python. Experiments show that they are able to analyze data sets where thousands of genes are sampled in a matter of minutes to hours. [ABSTRACT FROM AUTHOR]

Clustering, which explores the visualization and distribution of data, has recently been studied widely. Although the existing clustering algorithms can well detect arbitrary shape clusters, most of them face the limitation that they cluster points on the basis of two physical metrics, distance and density, but ignore the orientation relationship of data distribution. Beside, they have a difficulty of selecting suitable parameters, which are important inputs of the clustering algorithms. In this paper, we firstly introduce a new physical metric, namely direction. Then, based on this new metric, we propose an adaptive direction-based clustering algorithm, namely ADC, which can automatically calculate appropriate parameters. Finally, we develop a parallel ADC algorithm based on multi-processors to improve the performance of the ADC algorithm. Compared with other clustering algorithms, experimental results demonstrate that the proposed algorithms are more general and can get much better clustering results. In addition, the parallel ADC algorithm has the best scalability over large data sets. • A new physical metric, direction, has been considered in the proposed clustering algorithm. • Adaptive strategies can obtain the parameter automatically. • A parallel algorithm PADC is proposed based on multi-core. • The experimental results demonstrate that the proposed PADC algorithm can efficiently process very large scale data sets with a good performance. [ABSTRACT FROM AUTHOR]

The exponential growth of scientific and business data has resulted in the evolution of the cloud computing environments and the MapReduce parallel programming model. The focus of cloud computing is increased utilization and power savings through consolidation while MapReduce enables large scale data analysis. Hadoop, an open source implementation of MapReduce has gained popularity in the last few years. In this paper, we evaluate Hadoop performance in both the traditional model of collocated data and compute services as well as consider the impact of separating out the services. The separation of data and compute services provides more flexibility in environments where data locality might not have a considerable impact such as virtualized environments and clusters with advanced networks. In this paper, we also conduct an energy efficiency evaluation of Hadoop on physical and virtual clusters in different configurations. Our extensive evaluation shows that: (1) coexisting virtual machines on servers decrease the disk throughput; (2) performance on physical clusters is significantly better than on virtual clusters; (3) performance degradation due to separation of the services depends on the data to compute ratio; (4) application completion progress correlates with the power consumption and power consumption is heavily application specific. Finally, we present a discussion on the implications of using cloud environments for big data analyses. [ABSTRACT FROM AUTHOR]

In this paper, we study the Nyström type subsampling for large-scale kernel methods to reduce the computational complexities of big data. We discuss the multi-penalty regularization scheme based on Nyström type subsampling which is motivated from well-studied manifold regularization schemes. We develop a theoretical analysis of the multi-penalty least-square regularization scheme under the general source condition in vector-valued function setting, therefore the results can also be applied to multi-task learning problems. We achieve the optimal minimax convergence rates of the multi-penalty regularization using the concept of effective dimension for the appropriate subsampling size. We discuss an aggregation approach based on the linear function strategy to combine various Nyström approximants. Finally, we demonstrate the performance of the multi-penalty regularization based on Nyström type subsampling on the Caltech-101 dataset for multi-class image classification and NSL-KDD benchmark dataset for intrusion detection problem. [ABSTRACT FROM AUTHOR]

With the advent of the Big data, the scalability of the machine learning algorithms has become more crucial than ever before. Furthermore, Feature selection as an essential preprocessing technique can improve the performance of the learning algorithms in confront with large-scale dataset by removing the irrelevant and redundant features. Owing to the lack of scalability, most of the classical feature selection algorithms are not so proper to deal with the voluminous data in the Big Data era. QPFS is a traditional feature weighting algorithm that has been used in lots of feature selection applications. By inspiring the classical QPFS, in this paper, a scalable algorithm called DQPFS is proposed based on the novel Apache Spark cluster computing model. The experimental study is performed on three big datasets that have a large number of instances and features at the same time. Then some assessment criteria such as accuracy, execution time, speed-up and scale-out are figured. Moreover, to study more deeply, the results of the proposed algorithm are compared with the classical version QPFS and the DiRelief, a distributed feature selection algorithm proposed recently. The empirical results illustrate that proposed method has (a) better scale-out than DiRelief, (b) significantly lower execution time than DiRelief, (c) lower execution time than QPFS, (d) better accuracy of the Naïve Bayes classifier in two of three datasets than DiRelief. • Proposing a distributed and scalable feature selection for Big Data, DQPFS. • An experimental study in three big datasets over a real cluster of computers. • Comparing the DQPFS algorithm with a similar distributed algorithm, DiRelief. • The proposed method has better Execution time and Speed-up than DiRelief Algorithm. [ABSTRACT FROM AUTHOR]

Micro-core architectures combine many low memory, low power computing cores together in a single package. These are attractive for use as accelerators but due to limited on-chip memory and multiple levels of memory hierarchy, the way in which programmers offload kernels needs to be carefully considered. In this paper we use Python as a vehicle for exploring the semantics and abstractions of higher level programming languages to support the offloading of computational kernels to these devices. By moving to a pass by reference model, along with leveraging memory kinds, we demonstrate the ability to easily and efficiently take advantage of multiple levels in the memory hierarchy, even ones that are not directly accessible to the micro-cores. Using a machine learning benchmark, we perform experiments on both Epiphany-III and MicroBlaze based micro-cores, demonstrating the ability to compute with data sets of arbitrarily large size. To provide context of our results, we explore the performance and power efficiency of these technologies, demonstrating that whilst these two micro-core technologies are competitive within their own embedded class of hardware, there is still a way to go to reach HPC class GPUs. • Pass by reference model is mandatory for micro-cores to support arbitrary large data • Memory kinds abstract low level details of the memory hierarchy • The use of memory kinds supports simple experimentation around data residency options • Our approach enables neural networks of arbitrary size on these accelerators • Against embedded technologies we demonstrate micro-cores are competitive [ABSTRACT FROM AUTHOR]

Cloud computing empowers enterprises to efficiently manage big data and discovery of useful information which are the most fundamental challenges for big data enabled applications. The cloud offered unlimited resources that can store, manage and analyze massive and heterogeneous data to improve the quality assurance of application services. Nevertheless, cloud computing is exposed to enormous external and internal privacy breaches and leakage threats. In this paper, we introduce a privacy-preserving distributed analytics framework for big data in cloud. Fully Homomorphic Encryption (FHE) is used as an emerging and powerful cryptosystem that can carry out analysis tasks on encrypted data. The developed distributed approach has the scalability to partition both data and analysis computations into subset cloud computing nodes that can be run independently. This rapidly accelerates the performance of encrypted data processing while preserving a high level of analysis accuracy. Our experimental evaluation demonstrates the efficiency of the proposed framework, in terms of both analysis performance and accuracy, for building a secure analytics cloud-enabled application. • A privacy-preserving distributed analytics framework for big data in the cloud is proposed. • Fully Homomorphic Encryption (FHE) is adapted to protect the privacy of outsourced data while it is stored and processed in cloud computing. • Distributed analytics approach is proposed which can be applied to several distributed-based applications. • The distributed approach improves the scalability of analytic tasks in a way that ensures a high level of analysis accuracy while reducing the performance overhead of encrypted computations. [ABSTRACT FROM AUTHOR]

In this paper, we present a comprehensive survey of privacy-preserving big data analytics. We introduce well-designed taxonomies which offer both systematic views and a detailed classification of this challenging research field. We give insights into recent studies on existing active topics in the field. Furthermore, we identify open future research directions for privacy-preserving big data analytics. This survey can serve as a good reference source for the development of modern privacy-preserving techniques to address various privacy-related scenarios to be encountered in practice. • A comprehensive survey of privacy-preserving big data analytics. • Well-designed taxonomies with both systematic views and detailed classification. • Insights into recent works on existing active privacy topics in social networks. • Open future research directions for privacy-preserving big data analytics. • A good reference source to address various privacy-related scenarios. [ABSTRACT FROM AUTHOR]

With the emerging of the Internet of Things (IoT) technology, we can analyze and real-time monitoring the power consumption data of buildings or equipment. However, over time, many power data will accumulate to even the terabyte level. Traditional data processing techniques will not handle. It is a challenge to monitor and process the data in a reasonable time. In this paper, we construct an efficient and real-time power monitoring platform, based on open source techniques. The power-data of buildings or equipment is provided through smart meters equipped inside campus buildings. The technologies of data collected and stored on the server side were handled by the Hadoop ecosystem and the data process to Hive data warehouse is executed by the Spark. On the particulars of system evaluation, we make some experiments to compare with the performance of record query, use three different technologies separately: Apache Hive, Apache Spark, and Impala had been evaluated regarding query-response performance. Moreover, for the performance estimation on the data ETL processing and SQL functions. The relevant experiments have been conducted on the same three software modules as well. • Real-time power monitoring platform based on the smart meter. • Data collection and storage method using the Hadoop subsystem and Hive data warehouse with Spark. • Query-response efficiency testing of Apache Hive, Apache Spark, and Impala. • Performance testing on the statistical query function and data ETL processing of Apache Hive, Apache Spark, and Impala. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) recordings have been rarely included in large-scale studies. This is arguably not due to a lack of information that lies in EEG recordings but mainly on account of methodological issues. In many cases, particularly in clinical, pediatric and aging populations, the EEG has a high degree of artifact contamination and the quality of EEG recordings often substantially differs between subjects. Although there exists a variety of standardized preprocessing methods to clean EEG from artifacts, currently there is no method to objectively quantify the quality of preprocessed EEG. This makes the commonly accepted procedure of excluding subjects from analyses due to exceeding contamination of artifacts highly subjective. As a consequence, P-hacking is fostered, the replicability of results is decreased, and it is difficult to pool data from different study sites. In addition, in large-scale studies, data are collected over years or even decades, requiring software that controls and manages the preprocessing of ongoing and dynamically growing studies. To address these challenges, we developed Automagic, an open-source MATLAB toolbox that acts as a wrapper to run currently available preprocessing methods and offers objective standardized quality assessment for growing studies. The software is compatible with the Brain Imaging Data Structure (BIDS) standard and hence facilitates data sharing. In the present paper we outline the functionality of Automagic and examine the effect of applying combinations of methods on a sample of resting and task-based EEG data. This examination suggests that applying a pipeline of algorithms to detect artifactual channels in combination with Multiple Artifact Rejection Algorithm (MARA), an independent component analysis (ICA)-based artifact correction method, is sufficient to reduce a large extent of artifacts. • Automagic is a new EEG preprocessing toolbox for large and growing studies. • Automagic is open source and wraps a selection of available preprocessing tools. • Automagic is BIDS compatible and offers standardized quality metrics. • Bad channel detection and MARA sufficiently reduces artifacts from resting EEG. [ABSTRACT FROM AUTHOR]

Big data sensing system (BDSS) plays an important role in the Internet of Things, in which how to reduce power consumption is one crucial problem. Currently, low energy adaptive clustering hierarchy (LEACH) protocol is one well-known algorithm used in BDSS with low energy cost. In this paper, a new variant of bat algorithm combined with centroid strategy is introduced. Three different centroid strategies with six different designs are introduced. In addition, the velocity inertia-free update equation is also provided. The optimization performance is verified by CEC2013 benchmarks in those designs against standard BA. Simulation results prove that the bat algorithm with weighted harmonic centroid (WHCBA) strategy is superior to other algorithms. By integrating WHCBA into LEACH protocol, we develop a two-stage cluster-head node selection strategy and can save more energy compared to the standard LEACH protocol. • Modified bat algorithm with centroid strategy is designed. • Six different centroid strategies are designed and compared. • Velocity inertia-free update equation is designed. • Bat algorithm with weighted harmonic centroid strategy is used to optimize the performance of LEACH protocol, and compared with other four algorithms. [ABSTRACT FROM AUTHOR]

Nowadays, the success of Internet of Things (IoT) applications depends on the intelligence of tools and techniques that can monitor, manage, and verify the correct operations of smart ecosystems including sensors and big data analytics tools, typically deployed in Cloud and Edge computing datacenters. In this paper, we propose a framework for the monitoring and management of IoT system that integrates the AllJoyn functionalities, useful to interconnect IoT devices, MongoDB, to implement Big Data storage, and Storm, to run real-time data analytics. We implemented the proposed framework and we tested its main functionalities in a smart home application scenario. In our experimentation, we investigated three different data patterns, i.e., regular, event-based, and automated, in order to evaluate performance of our framework in terms of response time under different operational conditions. Experimental results show that the latency of the monitoring and service strongly depends on the type of management application running in the system, whereas it is lightly affected by the data patterns. • Monitoring of IoT device requires the analysis of big data. • We propose a piece framework integrating AllJoyn with MongoDB and Storm. • Different data patterns were designed to manage several smart home scenarios. • Simulation experiments prove the feasibility of the proposed system. [ABSTRACT FROM AUTHOR]

The ongoing myelination of white-matter fiber bundles plays a significant role in brain development. However, reliable and consistent identification of these bundles from infant brain MRIs is often challenging due to inherently low diffusion anisotropy, as well as motion and other artifacts. In this paper we introduce a new tool for automated probabilistic tractography specifically designed for newborn infants. Our tool incorporates prior information about the anatomical neighborhood of white-matter pathways from a training data set. In our experiments, we evaluate this tool on data from both full-term and prematurely born infants and demonstrate that it can reconstruct known white-matter tracts in both groups robustly, even in the presence of differences between the training set and study subjects. Additionally, we evaluate it on a publicly available large data set of healthy term infants (UNC Early Brain Development Program). This paves the way for performing a host of sophisticated analyses in newborns that we have previously implemented for the adult brain, such as pointwise analysis along tracts and longitudinal analysis, in both health and disease. • Tool successfully reconstructs 14 WM pathways in both full- and pre-term subjects. • The accuracy of the reconstruction depends on the test but not on the training data. • No significant effect of segmentation/registration on our pathway reconstruction. • Training set may combine data from different studies (or different from test data). • Diffusion values extracted with manual and automated methods are closely associated. [ABSTRACT FROM AUTHOR]

Surrogate modeling and uncertainty quantification tasks for PDE systems are most often considered as supervised learning problems where input and output data pairs are used for training. The construction of such emulators is by definition a small data problem which poses challenges to deep learning approaches that have been developed to operate in the big data regime. Even in cases where such models have been shown to have good predictive capability in high dimensions, they fail to address constraints in the data implied by the PDE model. This paper provides a methodology that incorporates the governing equations of the physical model in the loss/likelihood functions. The resulting physics-constrained, deep learning models are trained without any labeled data (e.g. employing only input data) and provide comparable predictive responses with data-driven models while obeying the constraints of the problem at hand. This work employs a convolutional encoder-decoder neural network approach as well as a conditional flow-based generative model for the solution of PDEs, surrogate model construction, and uncertainty quantification tasks. The methodology is posed as a minimization problem of the reverse Kullback-Leibler (KL) divergence between the model predictive density and the reference conditional density, where the later is defined as the Boltzmann-Gibbs distribution at a given inverse temperature with the underlying potential relating to the PDE system of interest. The generalization capability of these models to out-of-distribution input is considered. Quantification and interpretation of the predictive uncertainty is provided for a number of problems. • Physics-constrained surrogates achieve comparable accuracy with data-driven ones without labeled data and generalize better. • Flow-based conditional generative model trained with reverse KL-divergence without labels captures the predictive uncertainty. • The developed models are used to solve PDEs, as surrogate models and for uncertainty propagation and calibration tasks. • Convolutional neural nets capture multiscale features of PDE solution fields much more effectively than fully-connected ones. [ABSTRACT FROM AUTHOR]

This paper studies the approximation of generalized ridge functions, namely of functions which are constant along some submanifolds of R N. We introduce the notion of linear-sleeve functions, whose function values only depend on the distance to some unknown linear subspace L. We propose two effective algorithms to approximate linear-sleeve functions f (x) = g (dist (x , L) 2) , when both the linear subspace L ⊂ R N and the function g ∈ C s [ 0 , 1 ] are unknown. We will prove error bounds for both algorithms and provide an extensive numerical comparison of both. We further propose an approach of how to apply these algorithms to capture general sleeve functions, which are constant along some lower dimensional submanifolds. [ABSTRACT FROM AUTHOR]

Chemotherapeutic response of cancer cells to a given compound is one of the most fundamental information one requires to design anti-cancer drugs. Recently, considerable amount of drug-induced gene expression data has become publicly available, in addition to cytotoxicity databases. These large sets of data provided an opportunity to apply machine learning methods to predict drug activity. However, due to the complexity of cancer drug mechanisms, none of the existing methods is perfect. In this paper, we propose a novel ensemble learning method to predict drug response. In addition, we attempt to use the drug screen data together with two novel signatures produced from the drug-induced gene expression profiles of cancer cell lines. Finally, we evaluate predictions by in vitro experiments in addition to the tests on data sets. The predictions of the methods, the signatures and the software are available from http://mtan.etu.edu.tr/drug-response-prediction/. • We proposed novel signatures to represent cell line sensitivity and drug activity. • We designed an ensemble learning method to predict anti cancer drug response based on stacked generalization. • The performance was evaluated using both in silico and in vitro methods. • We integrated drug induced gene expression data with large scale cell viability screens. [ABSTRACT FROM AUTHOR]