Search

A dynamically weighted directed network (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) concerned in this study. It consists of large-scale dynamic interactions among numerous nodes. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant DWDN High Dimensional and Incomplete (HDI). An HDI DWDN, in spite of its incompleteness, contains rich knowledge regarding involved nodes’ various behavior patterns. To extract such knowledge from an HDI DWDN, this paper proposes a novel Alternating direction method of multipliers (ADMM)-based Nonnegative Latent-factorization of Tensors (ANLT) model. It adopts three-fold ideas: a) building a data density-oriented augmented Lagrangian function for efficiently handling an HDI tensor's incompleteness and nonnegativity; b) splitting the optimization task in each iteration into an elaborately designed subtask series where each one is solved based on the previously solved ones following the ADMM principle to achieve fast convergence; and c) theoretically proving that its convergence is guaranteed with its efficient learning scheme. Experimental results on six DWDNs from real applications demonstrate that the proposed ANLT outperforms state-of-the-art models significantly in both computational efficiency and prediction accuracy for missing links of an HDI DWDN. Hence, this study proposes a novel and efficient approach to large-scale DWDN representation. [ABSTRACT FROM AUTHOR]

A dynamically weighted directed network (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) concerned in this study. It consists of large-scale dynamic interactions among numerous nodes. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant DWDN High Dimensional and Incomplete (HDI). An HDI DWDN, in spite of its incompleteness, contains rich knowledge regarding involved nodes’ various behavior patterns. To extract such knowledge from an HDI DWDN, this paper proposes a novel Alternating direction method of multipliers (ADMM)-based Nonnegative Latent-factorization of Tensors (ANLT) model. It adopts three-fold ideas: a) building a data density-oriented augmented Lagrangian function for efficiently handling an HDI tensor's incompleteness and nonnegativity; b) splitting the optimization task in each iteration into an elaborately designed subtask series where each one is solved based on the previously solved ones following the ADMM principle to achieve fast convergence; and c) theoretically proving that its convergence is guaranteed with its efficient learning scheme. Experimental results on six DWDNs from real applications demonstrate that the proposed ANLT outperforms state-of-the-art models significantly in both computational efficiency and prediction accuracy for missing links of an HDI DWDN. Hence, this study proposes a novel and efficient approach to large-scale DWDN representation. [ABSTRACT FROM AUTHOR]

While recent developments of neural network (NN) models have led to a series of record-breaking achievements in many applications, the lack of sufficiently good datasets remains a problem for some applications. For such a problem, we can however exploit a large number of unstructured text corpora as an external knowledge to complement the training data, and most prevailing neural network solutions employ word embedding methods for such purposes. In this paper, we propose LDA-Reg, a novel knowledge driven regularization framework based on Latent Dirichlet Allocation (LDA) as an alternative to the word embedding methods to adaptively utilize abundant external knowledge and to interpret the NN model. For the joint learning of the parameters, we propose EM-SGD, an effective update method which incorporates Expectation Maximization (EM) and Stochastic Gradient Descent (SGD) to update parameters iteratively. Moreover, we also devise a lazy update and sparse update method for the high-dimensional inputs and sparse inputs respectively. We validate the effectiveness of our regularization framework through an extensive experimental study over real world and standard benchmark datasets. The results show that our proposed framework not only achieves significant improvement over state-of-the-art word embedding methods but also learns interpretable and significant topics for various tasks. [ABSTRACT FROM AUTHOR]

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as “memory” for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a trained model is merely limited to either inference or better initialization towards a target task. In this paper, we go further and extract synthetic data by leveraging the learnt model parameters. We dub them Data Impressions, which act as proxy to the training data and can be used to realize a variety of tasks. These are useful in scenarios where only the pretrained models are available and the training data is not shared (e.g., due to privacy or sensitivity concerns). We show the applicability of data impressions in solving several computer vision tasks such as unsupervised domain adaptation, continual learning as well as knowledge distillation. We also study the adversarial robustness of lightweight models trained via knowledge distillation using these data impressions. Further, we demonstrate the efficacy of data impressions in generating data-free Universal Adversarial Perturbations (UAPs) with better fooling rates. Extensive experiments performed on benchmark datasets demonstrate competitive performance achieved using data impressions in absence of original training data. [ABSTRACT FROM AUTHOR]

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness [ABSTRACT FROM AUTHOR]

An important cue for multi-pedestrian tracking in video is the consistent appearance of an individual for quite a while. In this paper, we address multi-pedestrian tracking by learning a robust appearance model from the paradigm of tracking by detection. To separate detections of different pedestrians while assembling detections of the same pedestrian, we take advantage of the cue of consistent appearance and exploit three types of evidence from the recent, past and near-future. Existing online approaches only exploit the detection-to-detection and sequence-to-detection metrics, which focus on the recent and past appearance patterns respectively, while the future pedestrian appearance is simply ignored. This drawback is remedied in this paper by further considering the sequence-to-sequence metric, which resorts to near-future appearance presentation. Adaptive combination weights are learned to fuse these three different metrics. Moreover, we propose a novel Focal Triplet Loss to make the model focus more on hard examples than the easy ones. We demonstrate that this can significantly enhance the discriminating power of the model compared with treating every sample equally. Effectiveness and efficiency of the proposed method is verified by conducting comprehensive ablation studies and comparing with many competitive (offline/online/near-online) counterparts on the MOT16 and MOT17 Challenges. [ABSTRACT FROM AUTHOR]

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate “weak” models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks. [ABSTRACT FROM AUTHOR]

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. Most of the traditional manifold-based methods on the OUDA problem focus on transforming each arriving target data to the source domain without sufficiently considering the temporal coherency and accumulative statistics among the arriving target data. In order to project the data from the source and the target domains to a common subspace and manipulate the projected data in real-time, our proposed framework institutes a novel method, called an Incremental Computation of Mean-Subspace (ICMS) technique, which computes an approximation of mean-target subspace on a Grassmann manifold and is proven to be a close approximate to the Karcher mean. Furthermore, the transformation matrix computed from the mean-target subspace is applied to the next target data in the recursive-feedback stage, aligning the target data closer to the source domain. The computation of transformation matrix and the prediction of next-target subspace leverage the performance of the recursive-feedback stage by considering the cumulative temporal dependency among the flow of the target subspace on the Grassmann manifold. The labels of the transformed target data are predicted by the pre-trained source classifier, then the classifier is updated by the transformed data and predicted labels. Extensive experiments on six datasets were conducted to investigate in depth the effect and contribution of each stage in our proposed framework and its performance over previous approaches in terms of classification accuracy and computational speed. In addition, the experiments on traditional manifold-based learning models and neural-network-based learning models demonstrated the applicability of our proposed framework for various types of learning models. [ABSTRACT FROM AUTHOR]

Many unsupervised domain adaptation (UDA) methods have been developed and have achieved promising results in various pattern recognition tasks. However, most existing methods assume that raw source data are available in the target domain when transferring knowledge from the source to the target domain. Due to the emerging regulations on data privacy, the availability of source data cannot be guaranteed when applying UDA methods in a new domain. The lack of source data makes UDA more challenging, and most existing methods are no longer applicable. To handle this issue, this paper analyzes the cross-domain representations in source-data-free unsupervised domain adaptation (SF-UDA). A new theorem is derived to bound the target-domain prediction error using the trained source model instead of the source data. On the basis of the proposed theorem, information bottleneck theory is introduced to minimize the generalization upper bound of the target-domain prediction error, thereby achieving domain adaptation. The minimization is implemented in a variational inference framework using a newly developed latent alignment variational autoencoder (LA-VAE). The experimental results show good performance of the proposed method in several cross-dataset classification tasks without using source data. Ablation studies and feature visualization also validate the effectiveness of our method in SF-UDA. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI)-powered autonomous vehicles (AVs) can integrate different machine learning (ML) techniques to build up a complex autonomous driving system. However, single AV intelligence is not enough to cope with ever-changing driving environments. The underlying reason is that, with current neural network design and training algorithms, it is challenging for the driving model to generalize to diverse driving environments all at once due to sample inefficiency and the curse of dimensionality. Powerful computing resources and massive amount of data can be used to train a good driving model offline. However, the driving model obtained offline might fail in corner case scenarios. In this paper, we propose an intelligence networking framework among AVs assisted by multi-access edge computing (MEC) with end-to-end learning for demonstration. In this framework, driving road is divided into segments and data is collected for each road segment separately. Assisted by MEC networks, a continuously updated driving model is produced in near real-time for each road segment when the environment changes. By dividing the road into segments, we aim to reduce the burden of generalization since a single model only needs to adapt to a specific road segment. Simulation results show that our solutions can produce updated driving model for each road segment to adapt to environmental changes better than the existing scheme. Upcoming AVs can then adapt to changing environments by downloading the updated driving model. [ABSTRACT FROM AUTHOR]

This paper introduces a fully automated greedy algorithm for the construction of parameterized behavioral models of electromagnetic structures, targeting at the same time uniform model stability and passivity. The proposed algorithm is able to determine a small set of parameter configurations for which an external solver provides on-the-fly the sampled scattering parameters of the structure over a predetermined frequency band. These samples are subjected to a multivariate rational/polynomial fitting process, which iteratively leads to a parameterized descriptor realization of the model. The main novel contribution in this paper is the adoption of a model-based approach for the adaptive augmentation of an initially small set of frequency responses, each corresponding to a randomly selected parameter configuration. In particular, the locations of the in-band passivity violations of intermediate macromodels constructed at each iteration are used as a proxy for the model-data error in those regions where input data are not available. This physics-based consistency check, which is enabled by recent developments in multivariate passivity characterization based on Skew-Hamiltonian–Hamiltonian (SHH) spectra, is combined with standard space exploration metrics to obtain a small-size and automatically determined distribution of points in the parameter space, leading to the construction of an accurate macromodel with a very limited number of external field solver runs. The embedded passivity check and enforcement process guarantees that either the final model is passive throughout the parameter space or the residual violations, if present, are negligible for practical purposes. Several examples validate the proposed approach for up to three concurrent parameters. [ABSTRACT FROM AUTHOR]

In skeleton-based action recognition, graph convolutional networks (GCNs) have achieved remarkable success. However, there are two shortcomings of current GCN-based methods. Firstly, the computation cost is pretty heavy, typically over 15 GFLOPs for one action sample. Some recent works even reach ~100 GFLOPs. Secondly, the receptive fields of both spatial graph and temporal graph are inflexible. Although recent works introduce incremental adaptive modules to enhance the expressiveness of spatial graph, their efficiency is still limited by regular GCN structures. In this paper, we propose a shift graph convolutional network (ShiftGCN) to overcome both shortcomings. ShiftGCN is composed of novel shift graph operations and lightweight point-wise convolutions, where the shift graph operations provide flexible receptive fields for both spatial graph and temporal graph. To further boost the efficiency, we introduce four techniques and build a more lightweight skeleton-based action recognition model named ShiftGCN++. ShiftGCN++ is an extremely computation-efficient model, which is designed for low-power and low-cost devices with very limited computing power. On three datasets for skeleton-based action recognition, ShiftGCN notably exceeds the state-of-the-art methods with over $10\times $ less FLOPs and $4\times $ practical speedup. ShiftGCN++ further boosts the efficiency of ShiftGCN, which achieves comparable performance with $6\times $ less FLOPs and $2\times $ practical speedup. [ABSTRACT FROM AUTHOR]

In this paper, characteristic model-based modeling and control approaches for complex dynamical networks based on sampled data are studied. It shows that the characteristic model, in which underline network topological structures are simplified, can provide a straightforward and implicit description for network dynamics. The induced parameter estimation method can further make the model adaptive and purely data-driven. Moreover, a control law based on this model is also proposed to govern the network dynamics. Finally, the theoretical results are verified through numerical simulations of modeling and stabilizing a dynamical network. [ABSTRACT FROM AUTHOR]

The join operations, including both equi and non-equi joins, are essential to the complex data analytics in the big data era. However, they are not inherently supported by existing DSPEs (Distributed Stream Processing Engines). The state-of-the-art join solutions on DSPEs rely on either complicated routing strategies or resource-inefficient processing structures, which are susceptible to dynamic workload, especially when the DSPEs face various join predicate operations and skewed data distribution. In this paper, we propose a new cost-effective stream join framework, named A-DSP (Adaptive Dimensional Space Processing), which enhances the adaptability of real-time join model and minimizes the resource used over the dynamic workloads. Our proposal includes: 1) a join model generation algorithm devised to adaptively switch between different join schemes so as to minimize the number of processing task required; 2) a load-balancing mechanism which maximizes the processing throughput; and 3) a lightweight algorithm designed for cutting down unnecessary migration cost. Extensive experiments are conducted to compare our proposal against state-of-the-art solutions on both benchmark and real-world workloads. The experimental results verify the effectiveness of our method, especially on reducing the operational cost under pay-as-you-go pricing scheme. [ABSTRACT FROM AUTHOR]

In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or social utility function which generates their comparison behaviors in experiments. However, in reality, annotators are subject to variations due to multi-criteria, abnormal, or a mixture of such behaviors. In this paper, we propose a parsimonious mixed-effects model, which takes into account both the fixed effect that the majority of annotators follows a common linear utility model, and the random effect that some annotators might deviate from the common significantly and exhibit strongly personalized preferences. The key algorithm in this paper establishes a dynamic path from the social utility to individual variations, with different levels of sparsity on personalization. The algorithm is based on the Linearized Bregman Iterations, which leads to easy parallel implementations to meet the need of large-scale data analysis. In this unified framework, three kinds of random utility models are presented, including the basic linear model with $L_2$ loss, Bradley-Terry model, and Thurstone-Mosteller model. The validity of these multi-level models are supported by experiments with both simulated and real-world datasets, which shows that the parsimonious multi-level models exhibit improvements in both interpretability and predictive precision compared with traditional HodgeRank. [ABSTRACT FROM AUTHOR]

In the past few years, kernel-based one-class extreme learning machine (ELM) receives quite a lot of attention by researchers for offline/batch learning due to its noniterative and fast learning capability. This paper extends this concept for adaptive online learning with regularized kernel-based one-class ELM classifiers for detection of outliers, and are collectively referred to as ORK-OCELM. Two frameworks, viz., boundary and reconstruction, are presented to detect the target class in ORK-OCELM. The kernel hyperplane-based baseline one-class ELM model considers whole data in a single chunk, however, the proposed one-class classifiers are adapted in an online fashion from the stream of training samples. The performance of ORK-OCELM is evaluated on a standard benchmark as well as synthetic datasets for both types of environments, i.e., stationary and nonstationary. While evaluating on stationary datasets, these classifiers are compared against batch learning-based one-class classifiers. Similarly, while evaluating on nonstationary datasets, the comparison is done with incremental learning-based online one-class classifiers. The results indicate that the proposed classifiers yield better or similar outcomes for both. In the nonstationary dataset evaluation, adaptability of the proposed classifiers in a changing environment is also demonstrated. It is further shown that the proposed classifiers have large stream data handling capability even under limited system memory. Moreover, the proposed classifiers gain significant time improvement compared to traditional online one-class classifiers (in all aspects of training and testing). A faster learning ability of the proposed classifiers makes them more suitable for real-time anomaly detection. [ABSTRACT FROM AUTHOR]

Deep Learning and Machine Learning models have recently been shown to be effective in many real world applications. While these models achieve increasingly better predictive performance, their structures have also become much more complex. A common and difficult problem for complex models is overfitting. Regularization is used to penalize the complexity of the model in order to avoid overfitting. However, in most learning frameworks, regularization function is usually set with some hyper-parameters where the best setting is difficult to find. In this paper, we propose an adaptive regularization method, as part of a large end-to-end healthcare data analytics software stack, which effectively addresses the above difficulty. First, we propose a general adaptive regularization method based on Gaussian Mixture (GM) to learn the best regularization function according to the observed parameters. Second, we develop an effective update algorithm which integrates Expectation Maximization (EM) with Stochastic Gradient Descent (SGD). Third, we design a lazy update and sparse update algorithm to reduce the computational cost by 4x and 20x, respectively. The overall regularization framework is fast, adaptive, and easy-to-use. We validate the effectiveness of our regularization method through an extensive experimental study over 14 standard benchmark datasets and three kinds of deep learning/machine learning models. The results illustrate that our proposed adaptive regularization method achieves significant improvement over state-of-the-art regularization methods. [ABSTRACT FROM AUTHOR]

Semi-supervised learning models for multiview data are important in image classification tasks, since heterogeneous features are easy to obtain and semi-supervised schemes are economical and effective. To model the view importance, conventional graph-based multiview learning models learn a linear combination of views while assuming a priori weights distribution. In this paper, we present a novel structural regularized semi-supervised model for multiview data, termed Adaptive MUltiview SEmi-supervised model (AMUSE). Our new model learns weights from a priori graph structure, which is more reasonable than weight regularization. Theoretical analysis reveals the significant difference between AMUSE and the prior arts. An efficient optimization algorithm is provided to solve the new model. Experimental results on six real-world data sets demonstrate the effectiveness of the structural regularized weights learning scheme. [ABSTRACT FROM AUTHOR]

A microscopic fuel consumption model with respect to comprehensive fuel consumption key impact factors that can reflect dynamic engine operations and various real-world driving conditions is essential for fuel efficient model-based vehicle and powertrain control (MB-VPC). Existing microscopic fuel consumption models are mostly steady state models with limited vehicle parameters as dynamic variables. Data-driven solutions can make the model comprehensive by introducing broad impact factors. However, without the required accessible online computational capability and fast model adaptation mechanisms, those data-driven solutions cannot quickly adapt to unseen driving conditions and engine condition changes based on real-world vehicle data to support MB-VPC. In this paper, a connected vehicle-based data mining (CV-DM) framework is proposed to achieve online adaptive dynamic fuel consumption modeling through knowledge sharing over CVs and the CV remote data center. Based on the CV-DM framework, CV-supported Distributed Meta-regression (CV-DMR) algorithms are developed to realize a fast few-shot adaptation with limited training data. Extensive proof-of-concept experiments are conducted with steady-state and transient vehicle engine data. Compared to the baseline physical model and the existing non-adaptive grey-box model, prediction accuracy is improved by 47%–85% and 38%–80% respectively with only limited training data needed for the subject vehicle. Accordingly, a fuel savings of up to 9.4% can be achieved owing to the improvement of prediction accuracy. [ABSTRACT FROM AUTHOR]

Current deep supervised learning methods typically require large amounts of labeled data for training. Since there is a significant cost associated with clinical data acquisition and labeling, medical datasets used for training these models are relatively small in size. In this paper, we aim to alleviate this limitation by proposing a variational generative model along with an effective data augmentation approach that utilizes the generative model to synthesize data. In our approach, the model learns the probability distribution of image data conditioned on a latent variable and the corresponding labels. The trained model can then be used to synthesize new images for data augmentation. We demonstrate the effectiveness of the approach on two independent clinical datasets consisting of ultrasound images of the spine and magnetic resonance images of the brain. For the spine dataset, a baseline and a residual model achieve an accuracy of 85% and 92%, respectively, using our method compared to 78% and 83% using a conventional training approach for image classification task. For the brain dataset, a baseline and a U-net network achieve an accuracy of 84% and 88%, respectively, in Dice coefficient in tumor segmentation compared to 80% and 83% for the convention training approach. [ABSTRACT FROM AUTHOR]

Energy imbalance market (EIM) provides an opportunity that allows larger shares of variable renewable energy sources in the grid. Under highly volatile weather conditions, an accurate forecasting of photovoltaic (PV) power is necessary for grid stability and market operation. Most of existing forecasting methods strongly rely on the accuracy of measurements, and the adaptability of these methods to complex weather conditions is rarely discussed. In this paper, a weather classification multivariate adaptive regression spline (MARS) forecasting model is introduced for complex weather conditions in all seasons. It can be updated incrementally and its high computational efficiency satisfies EIM operations. A data set that consists of the historical power and meteorological parameters produced by a small-scale PV platform is classified and used to train MARS models with forecast horizons ranging from 15 min to 24 h in different seasons. The tests and analyses results indicate higher accuracy, adaptability, and efficiency of the novel model. [ABSTRACT FROM AUTHOR]

OLAP models can be categorized with two types: MOLAP (multidimensional OLAP) and ROLAP (relational OLAP). In particular, MOLAP is efficient in multidimensional computing at the cost of cube maintenance, while ROLAP reduces the data storage size at the cost of expensive multidimensional join operations. In this paper, we propose a novel Fusion OLAP model to fuse the multidimensional computing model and relational storage model together to make the best aspects of both MOLAP and ROLAP worlds. This is achieved by mapping the relation tables into virtual multidimensional model and binding the multidimensional operations into a set of vector indexes to enable multidimensional computing on relation tables. The Fusion OLAP model can be integrated into the state-of-the-art in-memory databases with additional surrogate key indexes and vector indexes. We compared the Fusion OLAP implementations with three leading analytical in-memory databases. Our comprehensive experimental results show that Fusion OLAP implementation can achieve up to 35, 365, and 169 percent performance improvements based on the Hyper, Vectorwise, and MonetDB databases, respectively, for the Star Schema Benchmark (SSB) with scale factor 100. [ABSTRACT FROM AUTHOR]

The prediction of combined sewer overflow (CSO) operation in urban environments presents a challenging task for water utilities. The operation of CSOs (most often in heavy rainfall conditions) prevents houses and businesses from flooding. However, sometimes, CSOs do not operate as they should, potentially bringing environmental pollution risks. Therefore, CSOs should be appropriately managed by water utilities, highlighting the need for adapted decision support systems. This paper proposes an automated CSO predictive model construction methodology using field monitoring data, as a substitute for the commonly established hydrological-hydraulic modeling approach for time-series prediction of CSO statuses. It is a systematic methodology factoring in all monitored field variables to construct time-series dependencies for CSO statuses. The model construction process is largely automated with little human intervention, and the pertinent variables together with their associated time lags for every CSO are holistically and automatically generated. A fast least absolute shrinkage and selection operator solution generating scheme is proposed to expedite the model construction process, where matrix inversions are effectively eliminated. The whole algorithm works in a stepwise manner, invoking either an incremental or decremental movement for including or excluding one model regressor into, or from, the predictive model at every step. The computational complexity is thereby analyzed with the pseudo code provided. Actual experimental results from both single-step ahead (i.e., 15 min) and multistep ahead predictions are finally produced and analyzed on a U.K. pilot area with various types of monitoring data made available, demonstrating the efficiency and effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Safe and reliable operation of systems relies on the use of online condition monitoring and diagnostic systems that aim to take immediate actions upon the occurrence of a fault. Model-based solutions are often not practical in nonstationary environments. Thus, the evolving data stream requires the data-driven model to be adaptive. In this paper, we propose a framework for the fault detection and classification that is accomplished on the data stream with both the gradual and abrupt drifts. The framework is only provided with prior information about the possible faults at the initial step; however, despite this, the framework can still detect the novel faults without receiving any update. Furthermore, an efficient fault classification algorithm is presented to maximize the efficiency of the proposed framework. Finally, the proposed framework is applied for diagnosing bearing defects in the induction motors to demonstrate its feasibility for industrial applications. [ABSTRACT FROM AUTHOR]

A social approach can be exploited for the Internet of Things (IoT) to manage a large number of connected objects. These objects operate as autonomous agents to request and provide information and services to users. Establishing trustworthy relationships among the objects greatly improves the effectiveness of node interaction in the social IoT and helps nodes overcome perceptions of uncertainty and risk. However, there are limitations in the existing trust models. In this paper, a comprehensive model of trust is proposed that is tailored to the social IoT. The model includes ingredients such as trustor, trustee, goal, trustworthiness evaluation, decision, action, result, and context. Building on this trust model, we clarify the concepts of trust in the social IoT in five aspects such as: 1) mutuality of trustor and trustee; 2) inferential transfer of trust; 3) transitivity of trust; 4) trustworthiness update; and 5) trustworthiness affected by dynamic environment. With network connectivities that are from real-world social networks, a series of simulations are conducted to evaluate the performance of the social IoT operated with the proposed trust model. An experimental IoT network is used to further validate the proposed trust model. [ABSTRACT FROM PUBLISHER]

Most of existing models for facial behavior analysis rely on generic classifiers, which fail to generalize well to previously unseen data. This is because of inherent differences in source (training) and target (test) data, mainly caused by variation in subjects’ facial morphology, camera views, and so on. All of these account for different contexts in which target and source data are recorded, and thus, may adversely affect the performance of the models learned solely from source data. In this paper, we exploit the notion of domain adaptation and propose a data efficient approach to adapt already learned classifiers to new unseen contexts. Specifically, we build upon the probabilistic framework of Gaussian processes (GPs), and introduce domain-specific GP experts (e.g., for each subject). The model adaptation is facilitated in a probabilistic fashion, by conditioning the target expert on the predictions from multiple source experts. We further exploit the predictive variance of each expert to define an optimal weighting during inference. We evaluate the proposed model on three publicly available data sets for multi-class (MultiPIE) and multi-label (DISFA, FERA2015) facial expression analysis by performing adaptation of two contextual factors: “where” (view) and “who” (subject). In our experiments, the proposed approach consistently outperforms: 1) both source and target classifiers, while using a small number of target examples during the adaptation and 2) related state-of-the-art approaches for supervised domain adaptation. [ABSTRACT FROM PUBLISHER]

Knowledge-based neural network modeling techniques using space-mapping concept have been demonstrated in the existing literature as efficient methods to overcome the accuracy limitations of empirical/equivalent circuit models when matching new electromagnetic data. For different modeling problems, the mapping structures can be different. In this paper, we propose a unified automated model generation algorithm that uses \boldsymbol l\mathbf {1} optimization to automatically determine the type and the topology of the mapping structure in a knowledge-based neural network model. By encompassing various types of mappings of the knowledge-based neural network model in the existing literature, we present a new unified model structure and derive new sensitivity formulas for the training of the unified model. The proposed \boldsymbol l\mathbf {1} formulation of modeling can force some weights of the mapping neural networks to zeros while leaving other weights as nonzeros. We utilize this feature to allow \boldsymbol l\mathbf {1} optimization to automatically determine which mapping is necessary and which mapping is unnecessary. Using the proposed \boldsymbol l\mathbf {1} optimization method, the mapping structure can be determined to address different needs of different modeling problems. The structure of the final knowledge-based model can be flexible combinations of some or all of linear mapping, nonlinear mapping, input mapping, frequency mapping, and output mapping. In this way, the proposed algorithm is more systematic and can further speed up the knowledge-based modeling process than existing knowledge-based modeling algorithms. The proposed method is illustrated by three microwave filter modeling examples. [ABSTRACT FROM PUBLISHER]

We investigate uncertainty quantification under a sparse Bayesian model of medical image registration. Bayesian modelling has proven powerful to automate the tuning of registration hyperparameters, such as the trade-off between the data and regularization functionals. Sparsity-inducing priors have recently been used to render the parametrization itself adaptive and data-driven. The sparse prior on transformation parameters effectively favors the use of coarse basis functions to capture the global trends in the visible motion while finer, highly localized bases are introduced only in the presence of coherent image information and motion. In earlier work, approximate inference under the sparse Bayesian model was tackled in an efficient Variational Bayes (VB) framework. In this paper we are interested in the theoretical and empirical quality of uncertainty estimates derived under this approximate scheme vs. under the exact model. We implement an (asymptotically) exact inference scheme based on reversible jump Markov Chain Monte Carlo (MCMC) sampling to characterize the posterior distribution of the transformation and compare the predictions of the VB and MCMC based methods. The true posterior distribution under the sparse Bayesian model is found to be meaningful: orders of magnitude for the estimated uncertainty are quantitatively reasonable, the uncertainty is higher in textureless regions and lower in the direction of strong intensity gradients. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the despeckling of synthetic aperture radar (SAR) images by variational methods which introduce nonlocal regularization functionals. To achieve this goal, two models are investigated from different aspects. The first model is derived for the logarithmically transformed (homomorphic) domain of the SAR data, and the other is derived for the original (nonhomomorphic) domain. The statistical properties of the speckle and the log-transformed speckle are analyzed, and the similarity measurements between pixels in the homomorphic domain and nonhomomorphic domain are then derived for constructing the corresponding nonlocal regularization functionals. Meanwhile, in the proposed models, we develop a strategy to adaptively choose the regularization parameters based on both the local heterogeneity information and the noise level of the images, aiming at getting a better balance between the goodness of fit of the original data and the amount of smoothing. A quasi-Newton iteration method is employed to quickly minimize the proposed adaptive nonlocal functionals. Experiments conducted on both simulated images and real SAR images confirm the good performances of the proposed methods, both in reducing speckle and preserving image quality. [ABSTRACT FROM AUTHOR]

This paper proposes artificial neural network and fuzzy system-based extreme learning machines (ELM) for offline and online modeling of U-tube steam generators (UTSG). Water level of UTSG systems is predicted in a one-step-ahead fashion using nonlinear autoregressive with exogenous input (NARX) topology. Modeling data are generated using a well-known and widely accepted dynamic model reported in the literature. Model performances are analyzed with different number of neurons for the neural network and with different number of rules for the fuzzy system. UTSG models are built at different reactor power levels as well as full range that corresponds to all reactor operating powers. A quantitative comparison of the models are made using the root-mean-squared error (RMSE) and the minimum-descriptive-length (MDL) criteria. Furthermore, conventional back propagation learning-based neural and fuzzy models are also designed for comparing ELMs to classical artificial models. The advantages and disadvantages of the designed models are discussed. [ABSTRACT FROM AUTHOR]

The past decade witnessed the tremendous growth of online services and applications. Together with the increase of cloud computing, more and more computation are hosted by Internet data centers (IDCs). Today’s IDCs are achieving significant advances in communication and computation capabilities. However, along with the increasing demand from IDC clients, power consumption for powering up and cooling these IDCs has been skyrocketing. Most existing works optimize the power consumption of either servers or Computer Room Air Conditioners (CRACs), and overlook the correlation between the power consumption of these two types of equipment. In this paper, we propose an adaptive power control method which leverages the correlation between the power consumption of servers and CRACs. To capture the workload uncertainties and thermal dynamics, we exploit Recursive-Least Square based Model Predictive Control (MPC) to solve the power control problem. Performance evaluations shows the effective power peak reduction using our approach. [ABSTRACT FROM AUTHOR]

We have recently presented a novel unsupervised, non-Gaussian, and contextual clustering algorithm for segmentation of polarimetric synthetic aperture radar (PolSAR) images. This represents one of the most advanced PolSAR unsupervised statistical segmentation algorithms and uses the doubly flexible two-parameter U-distribution model for the PolSAR statistics and includes a Markov random field (MRF) approach for contextual smoothing. A goodness-of-fit testing stage adds a statistically rigorous approach to determine the significant number of classes. The fully automatic algorithm was demonstrated with good results for both simulated and real data sets. This paper discusses a rethinking of the overall strategy and leads to some simplifications. The primary issue was that the MRF optimization depends on the number of classes and did not behave well under the split-and-merge environment. We explain the reasons behind a separation of the cluster evaluation from the contextual smoothing and a modified rationale for the adaptive number of classes. Both aspects have simplified the overall algorithm while maintaining good visual results. [ABSTRACT FROM PUBLISHER]

Kernel principal component analysis and the reconstruction error is an effective anomaly detection technique for non-linear data sets. In an environment where a phenomenon is generating data that is non-stationary, anomaly detection requires a recomputation of the kernel eigenspace in order to represent the current data distribution. Recomputation is a computationally complex operation and reducing computational complexity is therefore a key challenge. In this paper, we propose an algorithm that is able to accurately remove data from a kernel eigenspace without performing a batch recomputation. Coupled with a kernel eigenspace update, we demonstrate that our technique is able to remove and add data to a kernel eigenspace more accurately than existing techniques. An adaptive version determines an appropriately sized sliding window of data and when a model update is necessary. Experimental evaluations on both synthetic and real-world data sets demonstrate the superior performance of the proposed approach in comparison to alternative incremental KPCA approaches and alternative anomaly detection techniques. [ABSTRACT FROM PUBLISHER]