Search

Colonoscopy is tool of choice for preventing Colorectal Cancer, by detecting and removing polyps before they become cancerous. However, colonoscopy is hampered by the fact that endoscopists routinely miss 22-28% of polyps. While some of these missed polyps appear in the endoscopist’s field of view, others are missed simply because of substandard coverage of the procedure, i.e. not all of the colon is seen. This paper attempts to rectify the problem of substandard coverage in colonoscopy through the introduction of the C2D2 (Colonoscopy Coverage Deficiency via Depth) algorithm which detects deficient coverage, and can thereby alert the endoscopist to revisit a given area. More specifically, C2D2 consists of two separate algorithms: the first performs depth estimation of the colon given an ordinary RGB video stream; while the second computes coverage given these depth estimates. Rather than compute coverage for the entire colon, our algorithm computes coverage locally, on a segment-by-segment basis; C2D2 can then indicate in real-time whether a particular area of the colon has suffered from deficient coverage, and if so the endoscopist can return to that area. Our coverage algorithm is the first such algorithm to be evaluated in a large-scale way; while our depth estimation technique is the first calibration-free unsupervised method applied to colonoscopies. The C2D2 algorithm achieves state of the art results in the detection of deficient coverage. On synthetic sequences with ground truth, it is 2.4 times more accurate than human experts; while on real sequences, C2D2 achieves a 93.0% agreement with experts. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for predicting online rotor angle stability in power system operation under significant contribution from wind generation. First, a novel algorithm is developed to extract a stability index (SI) that quantifies the margin of rotor angle stability of power systems reflecting the dynamics of wind power. An approach is proposed that takes advantage of the machine learning technique and the newly defined SI. In case of a contingency, the developed algorithm is employed in parallel to find SIs for all possible instability modes. The SIs are formed as a vector and then applied to a classifier algorithm for rotor angle stability prediction. Compared to other features used in state-of-the-art methods, SI vectors are highly recognizable and thus can lead to a more accurate and reliable prediction. The proposed approach is validated on two IEEE test systems with various wind power penetration levels and compared to existing methods, followed by a discussion of results. [ABSTRACT FROM AUTHOR]

In multi-user downlink small cell networks, cooperative resource allocation (RA) within a small cell cluster is a key technique to enhance network capacity. However, capacity-maximizing RA in frequency-selective fading channels requires global channel state information (CSI) of users within a small cell cluster, which makes it infeasible in practical networks with limited direct link capacity. To circumvent this global CSI assumption, most of the existing studies on RA have been based on several CSI assumptions such as local CSI and local CSI at the transmitters (CSIT). Nevertheless, cost functions with local CSI or local CSIT in the literature rely on heuristic formulations, because the sum-rate cannot be computed if without global CSI. In this paper, we propose a deep reinforcement learning-based RA algorithm to maximize the sum-rate for any given limited information on instantaneous CSI or sum-rate at the previous period. The proposed scheme is not restricted to certain CSI assumptions, but attempts to find the best RA for any given information such as quantized local CSI and quantized local CSIT; thus, it is applicable to any given direct link capacity. The proposed algorithm is self-adaptive in time-varying channels, since it is not divided into training and test phases. We modify the target neural network (TNN) scheme to enhance the sum-rate and the convergence speed. Numerical simulations confirm that: i) the proposed algorithm outperforms the conventional algorithms even under the same CSI assumption such as local CSI and local CSIT; ii) a flexible trade-off between the amount of CSI and the sum-rate is realizable in practical systems. [ABSTRACT FROM AUTHOR]

Trailer mass is one of the important trailer parameters that affects the stability of the tractor-trailer systems. In this paper, two different approaches are proposed to estimate trailer mass for arbitrary tractor-trailer configurations; dynamic system model-based and Machine Learning (ML) approaches. The stability of the dynamic system model-based estimation algorithm is analyzed, establishing the convergence of the estimation error to zero. In the proposed ML-based approach, a Deep Neural Network (DNN) is designed to estimate trailer mass. The inputs of the ML-based method have been selected based on the tractor-trailer dynamic model, and are considered to be normalized by the tractor mass, tire sizes, and geometry so that re-training of the network is not needed for different towing vehicles. The simulation and experimental results justify the accuracy of the trailer mass estimation in various cases and demonstrate that the trailer mass can be estimated with less than 10% error. [ABSTRACT FROM AUTHOR]

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities. [ABSTRACT FROM AUTHOR]

Confronted with considerable intermittence and variability of wind power, prediction intervals (PIs) serve as a crucial tool to assist power system decision-making under uncertainties. Conventional PIs rely on predetermining the lower and upper quantile proportions and therefore suffer from conservative interval width. This paper innovatively develops a chance constrained extreme learning machine (CCELM) model to generate quality nonparametric proportion-free PIs of wind power generation, which minimizes the expected interval width subject to the PI coverage probability constraint. Due to the independency on the preset PI bounds proportions, the proposed CCELM model merits high adaptivity and taps the latent potentialities for PI shortening. The convexity of extreme learning machine renders the sample average approximation counterpart of stochastic CCELM model equivalent to a parameter searching task in parametric optimization problem with polyhedral feasible region. A novel difference of convex functions optimization based bisection search (DCBS) algorithm is proposed to efficiently construct the CCELM model, which successfully realizes machine learning by means of solving linear programming problems sequentially. Comprehensive numerical experiments based on actual wind farm data demonstrate the significant effectiveness and efficiency of the developed CCELM model and DCBS algorithm. [ABSTRACT FROM AUTHOR]

Human mobility prediction techniques are instrumental for many important applications including service management and city planning. Previous work looks at the inherent patterns of a user's historical trajectories to predict his/her future location. Such method suffers when only a small number of historical locations are available, which is a main challenge for mobility prediction on sparse trajectory datasets. In this paper, we propose a multi-task learning based algorithm to predict users’ mobility by learning the mobility behaviors of different users at the same time and exploiting the similarities among them to overcome the sparse issue and improve the prediction performance. Specifically, we use a Bayesian mixture model to describe users’ spatio-temporal mobility patterns, where we introduce a novel von Mises distribution to model the temporal distribution of users’ mobility to better preserve its continuity across time. Then, we use the hierarchical Dirichlet process to perform joint prediction of all users’ mobility. This model allows us to leverage similar mobility patterns among users to improve the prediction performance for users with sparse trajectory data. We conduct extensive evaluations using data collected by a cellular network operator and mobile applications. Our evaluations show that our algorithms achieve prediction accuracy of 53.9% on average and 73.2% for users with high-quality mobility data, with the performance gap over 8.7% on average compared with the state-of-the-art algorithms, demonstrating the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Autoencoders are deep learning architectures that learn feature representation by minimizing the reconstruction error. Using an autoencoder as baseline, this paper presents a novel formulation for a class sparsity based supervised encoder, termed as CSSE. We postulate that features from the same class will have a common sparsity pattern/support in the latent space. Therefore, in the formulation of the autoencoder, a supervision penalty is introduced as a joint-sparsity promoting l2,1 -norm. The formulation of CSSE is derived for a single hidden layer and it is applied for multiple hidden layers using a greedy layer-by-layer learning approach. The proposed CSSE approach is applied for learning face representation and verification experiments are performed on the LFW and PaSC face databases. The experiments show that the proposed approach yields improved results compared to autoencoders and comparable results with state-of-the-art face recognition algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a self-tuning framework for the diagnosis of routine alarms in steam turbine generators utilizing a combination of inductive machine learning and knowledge-based heuristics. The techniques provide a novel basis for initializing and updating time series feature extraction parameters used in the automated decision support of vibration events due to operational transients. The data-driven nature of the algorithms allows for machine-specific characteristics of individual turbines to be learned and reasoned about. The paper provides a case study illustrating the routine alarm paradigm, and the applicability of systems using self-tuning techniques. The approaches discussed throughout are presented to provide useful diagnosis tools for the reliability and maintenance analysis of steam turbine generators. [ABSTRACT FROM PUBLISHER]

In a 2006 TPAMI paper, Wang proposed the Neighborhood Counting Measure [2], a similarity measure for the k-NN algorithm. In his paper, Wang mentioned the Minimum Risk Metric (MRM, [1]), an early distance measure based on the minimization of the risk of misclassification. Wang did not compare NCM to MRM because of its allegedly excessive computational load. In this comment paper, we complete the comparison that was missing in Wang's paper and, from our empirical evaluation, we show that MRM outperforms NCM and that its running time is not prohibitive as Wang suggested. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive tracking algorithm by learning hybrid object templates online in video. The templates consist of multiple types of features, each of which describes one specific appearance structure, such as flatness, texture, or edge/corner. Our proposed solution consists of three aspects. First, in order to make the features of different types comparable with each other, a unified statistical measure is defined to select the most informative features to construct the hybrid template. Second, we propose a simple yet powerful generative model for representing objects. This model is characterized by its simplicity since it could be efficiently learnt from the currently observed frames. Last, we present an iterative procedure to learn the object template from the currently observed frames, and to locate every feature of the object template within the observed frames. The former step is referred to as feature pursuit, and the latter step is referred to as feature alignment, both of which are performed over a batch of observations. We fuse the results of feature alignment to locate objects within frames. The proposed solution to object tracking is in essence robust against various challenges, including background clutters, low-resolution, scale changes, and severe occlusions. Extensive experiments are conducted over several publicly available databases and the results with comparisons show that our tracking algorithm clearly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, the problem of adaptive distributed learning in diffusion networks is considered. The algorithms are developed within the convex set theoretic framework. More specifically, they are based on computationally simple geometric projections onto closed convex sets. The paper suggests a novel combine-project-adapt protocol for cooperation among the nodes of the network; such a protocol fits naturally with the philosophy that underlies the projection-based rationale. Moreover, the possibility that some of the nodes may fail is also considered and it is addressed by employing robust statistics loss functions. Such loss functions can easily be accommodated in the adopted algorithmic framework; all that is required from a loss function is convexity. Under some mild assumptions, the proposed algorithms enjoy monotonicity, asymptotic optimality, asymptotic consensus, strong convergence and linear complexity with respect to the number of unknown parameters. Finally, experiments in the context of the system-identification task verify the validity of the proposed algorithmic schemes, which are compared to other recent algorithms that have been developed for adaptive distributed learning. [ABSTRACT FROM PUBLISHER]

This paper proposes a method for interactive surface recognition and surface categorization by a humanoid robot using a vibrotactile sensory modality. The robot was equipped with an artificial fingernail that had a built-in three-axis accelerometer. The robot interacted with 20 different surfaces by performing five different exploratory scratching behaviors on them. Surface-recognition models were learned by coupling frequency-domain analysis of the vibrations detected by the accelerometer with machine learning algorithms, such as support vector machine (SVM) and k-nearest neighbors (k -NN). The results show that by applying several different scratching behaviors on a test surface, the robot can recognize surfaces better than with any single behavior alone. The robot was also able to estimate a measure of similarity between any two surfaces, which was used to construct a grounded hierarchical surface categorization. [ABSTRACT FROM AUTHOR]

This paper compares the performance of several boosting and bagging techniques in the context of learning from imbalanced and noisy binary-class data. Noise and class imbalance are two well-established data characteristics encountered in a wide range of data mining and machine learning initiatives. The learning algorithms studied in this paper, which include SMOTEBoost, RUSBoost, Exactly Balanced Bagging, and Roughly Balanced Bagging, combine boosting or bagging with data sampling to make them more effective when data are imbalanced. These techniques are evaluated in a comprehensive suite of experiments, for which nearly four million classification models were trained. All classifiers are assessed using seven different performance metrics, providing a complete perspective on the performance of these techniques, and results are tested for statistical significance via analysis-of-variance modeling. The experiments show that the bagging techniques generally outperform boosting, and hence in noisy data environments, bagging is the preferred method for handling class imbalance. [ABSTRACT FROM PUBLISHER]

This paper presents an innovative model of a program's internal behavior over a set of test inputs, called the probabilistic program dependence graph (PPDG), which facilitates probabilistic analysis and reasoning about uncertain program behavior, particularly that associated with faults. The PPDG construction augments the structural dependences represented by a program dependence graph with estimates of statistical dependences between node states, which are computed from the test set. The PPDG is based on the established framework of probabilistic graphical models, which are used widely in a variety of applications. This paper presents algorithms for constructing PPDGs and applying them to fault diagnosis. The paper also presents preliminary evidence indicating that a PPDG-based fault localization technique compares favorably with existing techniques. The paper also presents evidence indicating that PPDGs can be useful for fault comprehension. [ABSTRACT FROM AUTHOR]

This paper considers the NP-hard problem of object assignment with respect to multiple constraints: assigning a set of elements (or objects) into mutually exclusive classes (or groups), where the elements which are "similar" to each other are hopefully located in the same class. The literature reports solutions in which the similarity constraint consists of a single index that is inappropriate for the type of multiconstraint problems considered here and where the constraints could simultaneously be contradictory. Such a scenario is illustrated with the static mapping problem, which consists of distributing the processes of a parallel application onto a set of computing nodes. This is a classical and yet very important problem within the areas of parallel computing, grid computing, and cloud computing. We have developed four learning-automata (LA)-based algorithms to solve this problem: First, a fixed-structure stochastic automata algorithm is presented, where the processes try to form pairs to go onto the same node. This algorithm solves the problem, although it requires some centralized coordination. As it is desirable to avoid centralized control, we subsequently present three different variable-structure stochastic automata (VSSA) algorithms, which have superior partitioning properties in certain settings, although they forfeit some of the scalability features of the fixed-structure algorithm. All three VSSA algorithms model the processes as automata having first the hosting nodes as possible actions; second, the processes as possible actions; and, third, attempting to estimate the process communication digraph prior to probabilistically mapping the processes. This paper, which, we believe, comprehensively reports the pioneering LA solutions to this problem, unequivocally demonstrates that LA can play an important role in solving complex combinatorial and integer optimization problems. [ABSTRACT FROM AUTHOR]

This paper investigates potential improvement of non-parametric detection performance via addition of noise and evaluates the performance of noise modified nonparametric detectors. Detection performance comparisons are made between the original detectors and noise modified detectors. Conditions for improvability as well as the optimum additive noise distributions of the widely used sign detector, the Wilcoxon detector, and the dead-zone limiter detector are derived. Finally, a simple and fast learning algorithm to find the optimal noise distribution solely based on received data is presented. A near-optimal solution can be found quickly based on a relatively small dataset. [ABSTRACT FROM AUTHOR]

In this paper, we study a real-time monitoring system in which multiple source nodes are responsible for sending update packets to a common destination node in order to maintain the freshness of information at the destination. Since it may not always be feasible to replace or recharge batteries in all source nodes, we consider that the nodes are powered through wireless energy transfer (WET) by the destination. For this system setup, we investigate the optimal online sampling policy (referred to as the age-optimal policy) that jointly optimizes WET and scheduling of update packet transmissions with the objective of minimizing the long-term average weighted sum of Age of Information (AoI) values for different physical processes (observed by the source nodes) at the destination node, referred to as the sum-AoI. To solve this optimization problem, we first model this setup as an average cost Markov decision process (MDP) with finite state and action spaces. Due to the extreme curse of dimensionality in the state space of the formulated MDP, classical reinforcement learning algorithms are no longer applicable to our problem even for reasonable-scale settings. Motivated by this, we propose a deep reinforcement learning (DRL) algorithm that can learn the age-optimal policy in a computationally-efficient manner. We further characterize the structural properties of the age-optimal policy analytically, and demonstrate that it has a threshold-based structure with respect to the AoI values for different processes. We extend our analysis to characterize the structural properties of the policy that maximizes average throughput for our system setup, referred to as the throughput-optimal policy. Afterwards, we analytically demonstrate that the structures of the age-optimal and throughput-optimal policies are different. We also numerically demonstrate these structures as well as the impact of system design parameters on the optimal achievable average weighted sum-AoI. [ABSTRACT FROM AUTHOR]

In the current unmanned aircraft systems (UASs) for sensing services, unmanned aerial vehicles (UAVs) transmit their sensory data to terrestrial mobile devices over the unlicensed spectrum. However, the interference from surrounding terminals is uncontrollable due to the opportunistic channel access. In this paper, we consider a cellular Internet of UAVs to guarantee the Quality-of-Service (QoS), where the sensory data can be transmitted to the mobile devices either by UAV-to-Device (U2D) communications over cellular networks, or directly through the base station (BS). Since UAVs’ sensing and transmission may influence their trajectories, we study the trajectory design problem for UAVs in consideration of their sensing and transmission. This is a Markov decision problem (MDP) with a large state-action space, and thus, we utilize multi-agent deep reinforcement learning (DRL) to approximate the state-action space, and then propose a multi-UAV trajectory design algorithm to solve this problem. Simulation results show that our proposed algorithm can achieve a higher total utility than policy gradient algorithm and single-agent algorithm. [ABSTRACT FROM AUTHOR]

Convex formulations of low-rank matrix factorization problems have received considerable attention in machine learning. However, such formulations often require solving for a matrix of the size of the data matrix, making it challenging to apply them to large scale datasets. Moreover, in many applications the data can display structures beyond simply being low-rank, e.g., images and videos present complex spatio-temporal structures that are largely ignored by standard low-rank methods. In this paper we study a matrix factorization technique that is suitable for large datasets and captures additional structure in the factors by using a particular form of regularization that includes well-known regularizers such as total variation and the nuclear norm as particular cases. Although the resulting optimization problem is non-convex, we show that if the size of the factors is large enough, under certain conditions, any local minimizer for the factors yields a global minimizer. A few practical algorithms are also provided to solve the matrix factorization problem, and bounds on the distance from a given approximate solution of the optimization problem to the global optimum are derived. Examples in neural calcium imaging video segmentation and hyperspectral compressed recovery show the advantages of our approach on high-dimensional datasets. [ABSTRACT FROM AUTHOR]

Question answering (QA) and question generation (QG) are closely related tasks that could improve each other; however, the connection of these two tasks is not well explored in the literature. In this paper, we present two training algorithms for learning better QA and QG models through leveraging one another. The first algorithm extends Generative Adversarial Network (GAN), which selectively incorporates artificially generated instances as additional QA training data. The second algorithm is an extension of dual learning, which incorporates the probabilistic correlation of QA and QG as additional regularization in training objectives. To test the scalability of our algorithms, we conduct experiments on both document based and table based question answering tasks. Results show that both algorithms improve a QA model in terms of accuracy and QG model in terms of BLEU score. Moreover, we find that the performance of a QG model could be easily improved by a QA model via policy gradient, however, directly applying GAN that regards all the generated questions as negative instances could not improve the accuracy of the QA model. Our algorithm that selectively assigns labels to generated questions would bring a performance boost. [ABSTRACT FROM AUTHOR]

Recently, sparse representation-based classification (SRC) has been widely studied and has produced state-of-the-art results in various classification tasks. Learning useful and computationally convenient representations from complex redundant and highly variable visual data is crucial for the success of SRC. However, how to find the best feature representation to work with SRC remains an open question. In this paper, we present a novel discriminative projection learning approach with the objective of seeking a projection matrix such that the learned low-dimensional representation can fit SRC well and that it has well discriminant ability. More specifically, we formulate the learning algorithm as a bilevel optimization problem, where the optimization includes an $\ell _{1}$ -norm minimization problem in its constraints. Through the bilevel optimization model, the relationship between sparse representation and the desired feature projection can be explicitly exploited during the learning process. Therefore, SRC can achieve a better performance in the transformed subspace. The optimization model can be solved by using a stochastic gradient ascent algorithm, and the desired gradient is computed using implicit differentiation. Furthermore, our method can be easily extended to learn a dictionary. The extensive experimental results on a series of benchmark databases show that our method outperforms many state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

A series ac arc fault detection method based only on the voltage waveform measured at the power source is implemented. A relay de-energizes the arc fault after receiving an arc fault detected signal. Traditional arc fault detection methods use the current waveform, which may have false alarms with loads, such as electric hand drills (which intentionally generate small electric arcs) and dimmer switches because they show similar energy characteristics to an arc fault. However, in the proposed voltage-based method, a symmetric energy profile is observed, unique to the arc fault, which allows improved detection. This symmetry in the voltage waveform is exploited to derive threshold values from the sample energy that are eventually used to detect the ac arc fault. The approach avoids non-stationary signal analysis, machine learning, and advanced filtering techniques. The experimental results validate that the algorithm can successfully detect an arc fault and avoid common unwanted tripping events. Finally, devices, such as surge protectors will be able to integrate this detection algorithm without the addition of current sensors. [ABSTRACT FROM AUTHOR]

Surface defects of explosive cartridge in the automatic sorting process are of a small area, irregular shape, and random distribution, and all problematic characteristics that hinder surface defect detection. To address these issues, a new multidefect detection method has been proposed in this paper based on a combination of an improved visual attention model and image partitioning-weighted eigenvalue (IP-WEV). First, image preprocessing is carried out by a background estimation algorithm. Then, a new fusion operator based on defects discrimination is implemented in a visual attention model to integrate intensity, orientation, and edge conspicuity into a saliency graph, in which a saliency effect of defects is considered during the fusion process. Third, a saliency map is divided into image blocks based on the image variance. This allows for the extraction of image blocks including defects, the calculation of the weighted eigenvalue, and the determination of regions containing multidefect. The IP-WEV is used to make a decision for multidefect. The experimental results show this method’s detection accuracy as 98.2%, with a less computation time and quickly detection speed. Therefore, this method could be adopted for on-line detection systems for explosive cartridge surface defects. [ABSTRACT FROM AUTHOR]

Massive data broadcast by GPS-equipped vehicles provide unprecedented opportunities. One of the main tasks in order to optimize our transportation networks is to build data-driven real-time decision support systems. However, the dynamic environments where the networks operate disallow the traditional assumptions required to put in practice many off-the-shelf supervised learning algorithms, such as finite training sets or stationary distributions. In this paper, we propose BRIGHT: a drift-aware supervised learning framework to predict demand quantities. BRIGHT aims to provide accurate predictions for short-term horizons through a creative ensemble of time series analysis methods that handles distinct types of concept drift. By selecting neighborhoods dynamically, BRIGHT reduces the likelihood of overfitting. By ensuring diversity among the base learners, BRIGHT ensures a high reduction of variance while keeping bias stable. Experiments were conducted using three large-scale heterogeneous real-world transportation networks in Porto (Portugal), Shanghai (China), and Stockholm (Sweden), as well as with controlled experiments using synthetic data where multiple distinct drifts were artificially induced. The obtained results illustrate the advantages of BRIGHT in relation to state-of-the-art methods for this task. [ABSTRACT FROM AUTHOR]

The key approaches for machine learning, particu- larly learning in unknown probabilistic environments, are new representations and computation mechanisms. In this paper, a novel quantum reinforcement learning (QRL) method is proposed by combining quantum theory and reinforcement learning (RL). Inspired by the state superposition principle and quantum paral- lelism, a framework of a value-updating algorithm is introduced. The state (action) in traditional RL is identified as the eigen state (eigen action) in QRL. The state (action) set can be represented with a quantum superposition state, and the eigen state (eigen action) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement. The probability of the eigen action is determined by the probability amplitude, which is updated in parallel ac- cording to rewards. Some related characteristics of QRL such as convergence, optimality, and balancing between exploration and exploitation are also analyzed, which shows that this approach makes a good tradeoff between exploration and exploitation using the probability amplitude and can speedup learning through the quantum parallelism. To evaluate the performance and practi- cability of QRL, several simulated experiments are given, and the results demonstrate the effectiveness and superiority of the QRL algorithm for some complex problems. This paper is also an effective exploration on the application of quantum computation to artificial intelligence. [ABSTRACT FROM AUTHOR]

The goal of this paper is to derive a novel online algorithm for classification in reproducing kernel hilbert spaces (RKHS) by exploiting projection-based adaptive filtering tools. The paper brings powerful convex analytic and set theoretic estimation arguments in machine learning by revisiting the standard kernel-based classification as the problem of finding a point which belongs to a closed halfspace (a special closed convex set) in an RKHS. In this way, classification in an online setting, where data arrive sequentially, is viewed as the problem of finding a point (classifier) in the nonempty intersection of an infinite sequence of closed halfspaces in the RKHS. Convex analysis is also used to introduce sparsification arguments in the design by imposing an additional simple convex constraint on the norm of the classifier. An algorithmic solution to the resulting optimization problem, where new convex constraints are added every time instant, is given by the recently introduced adaptive projected subgradient method (APSM), which generalizes a number of well-known projection-based adaptive filtering algorithms such as the classical normalized least mean squares (NLMS) and the affine projection algorithm (APA). Under mild conditions, the generated sequence of estimates enjoys monotone approximation, strong convergence, asymptotic optimality, and a characterization of the limit point. Further, we show that the additional convex constraint on the norm of the classifier naturally leads to an online sparsification of the resulting kernel series expansion. We validate the proposed design by considering the adaptive equalization problem of a nonlinear channel, and by comparing it with classical as well as with recently developed stochastic gradient descent techniques. [ABSTRACT FROM PUBLISHER]

The combination of the famed kernel trick and the least-mean-square (LMS) algorithm provides an interesting sample-by-sample update for an adaptive filter in reproducing kernel Hubert spaces (RKHS), which is named in this paper the KLMS. Unlike the accepted view in kernel methods, this paper shows that in the finite training data case, the KLMS algorithm is well posed in RKHS without the addition of an extra regularization term to penalize solution norms as was suggested by Kivinen [Kivinen, Smola and Williamson, "Online Learning With Kernels," IEEE Transactions on Signal Processing, vol. 52, no. 8, pp. 2165-2176, Aug. 2004] and Smale [Smale and Yao, "Online Learning Algorithms," Foundations in computational Mathematics, vol. 6, no. 2, pp. 145-176, 20061. This result is the main contribution of the paper and enhances the present understanding of the LMS algorithm with a machine learning perspective. The effect of the KLMS step size is also studied from the viewpoint of regularization. Two experiments are presented to support our conclusion that with finite data the KLMS algorithm can be readily used in high dimensional spaces and particularly in RKHS to derive nonlinear, stable algorithms with comparable performance to batch, regularized solutions. [ABSTRACT FROM AUTHOR]

In many practical data mining applications such as text classification, unlabeled training examples are readily available, but labeled ones are fairly expensive to obtain. Therefore, semisupervised learning algorithms have aroused considerable interests from the data mining and machine learning fields. In recent years, graph-based semisupervised learning has been becoming one of the most active research areas in the semisupervised learning community. In this paper, a novel graph-based semisupervised learning approach is proposed based on a linear neighborhood model, which assumes that each data point can be linearly reconstructed from its neighborhood. Our algorithm, named Linear Neighborhood Propagation (LNP), can propagate the labels from the labeled points to the whole data set using these linear neighborhoods with sufficient smoothness. A theoretical analysis of the properties of LNP is presented in this paper. Furthermore, we also derive an easy way to extend LNP to out-of-sample data. Promising experimental results are presented for synthetic data, digit, and text classification tasks. [ABSTRACT FROM AUTHOR]

Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets. Consistent Weighted Sampling (CWS) generalizes the Min-Hash scheme to sketch weighted sets and has drawn increasing interest from the community. Due to its constant-time complexity independent of the values of the weights, Improved CWS (ICWS) is considered as the state-of-the-art CWS algorithm. In this paper, we revisit ICWS and analyze its underlying mechanism to show that there actually exists dependence between the two components of the hash-code produced by ICWS, which violates the condition of independence. To remedy the problem, we propose an Improved ICWS (I $^2$ 2 CWS) algorithm which not only shares the same theoretical computational complexity as ICWS but also abides by the required conditions of the CWS scheme. The experimental results on a number of synthetic data sets and real-world text data sets demonstrate that our I $^2$ 2 CWS algorithm can estimate the Jaccard similarity more accurately, and also competes with or outperforms the compared methods, including ICWS, in classification and top- $K$ K retrieval, after relieving the underlying dependence. [ABSTRACT FROM AUTHOR]

In the upcoming Internet-of-Things (IoT) era, the communication is often featured by massive connection, sporadic transmission, and small-sized data packets, which poses new requirements on the delay expectation and resource allocation efficiency of the Random Access (RA) mechanisms of the IoT communication stack. A grant-free non-orthogonal random access (NORA) system is considered in this paper, which could simultaneously reduce the access delay and support more Machine Type Communication (MTC) devices with limited resources. In order to address the joint user activity detection (UAD) and channel estimation (CE) problem in the grant-free NORA system, we propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm. In the DNN-MP-BSBL algorithm, the iterative message passing process is transferred from a factor graph to a deep neural network (DNN). Weights are imposed on the messages in the DNN and trained to minimize the estimation error. It is shown that the trained weights could alleviate the convergence problem of the MP-BSBL algorithm, especially on crowded RA scenarios. Simulation results show that the proposed DNN-MP-BSBL algorithm could improve the UAD and CE accuracy with a smaller number of iterations, indicating its advantages for low-latency grant-free NORA systems. [ABSTRACT FROM AUTHOR]

In this paper, a general framework which enables to compare previously proposed block decoding approaches for the fast correlation attack is developed. All attacks are based on decoding using a set of parity check sums of an underlying linear code. The purpose of this paper is twofold: • to provide a simple close form estimate about the number of check sums of a particular structure necessary for the corresponding attack to succeed; • to illustrate how such estimates are useful in minimizing the computational complexity of each attack considered, and consequently, in establishing a unified framework for comparison. [ABSTRACT FROM AUTHOR]

Cooperation in learning (CL) can be realized in a multiagent system, if agents are capable of learning from both their own experiments and other agents' knowledge and expertise. Extra resources are exploited into higher efficiency and faster learning in CL as compared to that of individual learning (IL). In the real world, however, implementation of CL is not a straightforward task, in part due to possible differences in area of expertise (AOE). In this paper, reinforcement-learning homogenous agents are considered in an environment with multiple goals or tasks. As a result, they become expert in different domains with different amounts of expertness. Each agent uses a one-step Q-learning algorithm and is capable of exchanging its Q-table with those of its teammates. Two crucial questions are addressed in this paper: ‘How the AOE of an agent can be extracted?’ and ‘How agents can improve their performance in CL by knowing their AOEs?’ An algorithm is developed to extract the AOE based on state transitions as a gold standard from a behavioral point of view. Moreover, it is discussed that the AOE can be implicitly obtained through agents' expertness in the state level. Three new methods for CL through the combination of Q-tables are developed and examined for overall performance after CL. The performances of developed methods are compared with that of IL, strategy sharing (SS), and weighted SS (WSS). Obtained results show the superior performance of AOE-based methods as compared to that of existing CL methods, which do not use the notion of AOE. These results are very encouraging in support of the idea that ‘cooperation based on the AOE’ performs better than the general CL methods. [ABSTRACT FROM AUTHOR]

In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a priori for each unseen instance. In this paper, this problem is addressed in the way that a neural network algorithm named BP-MLL, i.e., Backpropagation for Multilabel Learning, is proposed. It is derived from the popular Backpropagation algorithm through employing a novel error function capturing the characteristics of multilabel learning, i.e., the labels belonging to an instance should be ranked higher than those not belonging to that instance. Applications to two real-world multilabel learning problems, i.e., functional genomics and text categorization, show that the performance of BP-MLL is superior to that of some well-established multilabel learning algorithms. [ABSTRACT FROM AUTHOR]

A shortcoming of univariate decision tree learners is that they do not learn intermediate concepts and select only one of the input features in the branching decision at each intermediate tree node. It has been empirically demonstrated that cascading other classification methods, which learn intermediate concepts, with decision tree learners can alleviate such representational bias of decision trees and potentially improve classification performance. However, a more complex model that fits training data belier may not necessarily perform better on unseen data, commonly referred to as the overfitting problem. To find the most appropriate degree of such cascade generalization, a decision forest (i.e., a set of decision trees with other classification models cascaded to different degrees) needs to be generated, from which the best decision tree can then be identified. In this paper, the authors pro- pose an efficient algorithm for generating such decision forests. The algorithm uses an extended decision tree data structure and constructs any node that is common to multiple decision trees only once. The authors have empirically evaluated the algorithm using 32 data sets for classification problems from the University of California, Irvine (UCI) machine learning repository and report on results demonstrating the efficiency of the algorithm in this paper. [ABSTRACT FROM AUTHOR]

This paper presents a kernel-based feature selection method for the classification of hyperspectral images. The proposed method aims at selecting a subset of the original features that are both 1) relevant (discriminant) for the considered classification problem, i.e., preserve the functional relationship between input and output variables, and 2) invariant (stable) across different domains, i.e., minimize the data-set shift between the source and the target domains. Domains can be associated with hyperspectral images collected either on different geographical areas or on the same area at different times. We propose a novel measure of data-set shift for evaluating the domain stability, which computes the distance of the conditional distributions between the source and target domains in a reproducing kernel Hilbert space. Such a measure is defined on the basis of the kernel embeddings of the conditional distributions resulting in a nonparametric approach that does not require estimating the distribution of the classes. The adopted search strategy is based on a multiobjective optimization algorithm, which optimizes the two terms of the criterion function for the estimation of the Pareto-optimal solutions. This results in an effective approach of performing feature selection in a transfer learning setting. The experimental results obtained on two hyperspectral images show the effectiveness of the proposed method in selecting features with high generalization capabilities. [ABSTRACT FROM AUTHOR]

Graph classification aims to learn models to classify structure data. To date, all existing graph classification methods are designed to target one single learning task and require a large number of labeled samples for learning good classification models. In reality, each real-world task may only have a limited number of labeled samples, yet multiple similar learning tasks can provide useful knowledge to benefit all tasks as a whole. In this paper, we formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. The niche of MTG stems from the fact that with a limited number of training samples, subgraph features selected for one single graph classification task tend to overfit the training data. By using additional tasks as evaluation sets, MTG can jointly regularize multiple tasks to explore high quality subgraph features for graph classification. To achieve this goal, we formulate an objective function which combines multiple graph classification tasks to evaluate the informativeness score of a subgraph feature. An iterative subgraph feature exploration and multi-task learning process is further proposed to incrementally select subgraph features for graph classification. Experiments on real-world multi-task graph classification datasets demonstrate significant performance gain. [ABSTRACT FROM PUBLISHER]

In this paper, we introduce a novel approach to automatically detect salient regions in an image. Our approach consists of global and local features, which complement each other to compute a saliency map. The first key idea of our work is to create a saliency map of an image by using a linear combination of colors in a high-dimensional color space. This is based on an observation that salient regions often have distinctive colors compared with backgrounds in human perception, however, human perception is complicated and highly nonlinear. By mapping the low-dimensional red, green, and blue color to a feature vector in a high-dimensional color space, we show that we can composite an accurate saliency map by finding the optimal linear combination of color coefficients in the high-dimensional color space. To further improve the performance of our saliency estimation, our second key idea is to utilize relative location and color contrast between superpixels as features and to resolve the saliency estimation from a trimap via a learning-based algorithm. The additional local features and learning-based algorithm complement the global estimation from the high-dimensional color transform-based algorithm. The experimental results on three benchmark datasets show that our approach is effective in comparison with the previous state-of-the-art saliency estimation methods. [ABSTRACT FROM PUBLISHER]

In this paper, a novel framework for designing and implementing a coordinated wide-area controller architecture for improved power system dynamic stability is presented and tested. The algorithm is an optimal wide-area system-centric controller and observer based on a hybrid reinforcement learning and temporal difference framework. It allows the system to deal with major concerns of wide-area monitoring problem: delays in signal transmission, the uncertainty of the communication network, and data traffic. The main advantage of this design is its ability to learn from the past using eligibility traces and predict the optimal trajectory of cost function through temporal difference method. The control algorithm is evolved from adaptive critic design (ACD) and performed online at a finite horizon through backward and forward view. The ACD controller's training and testing are implemented on the Innovative Integration Picolo card integrated to TMS320C28335 processor. Results on a real experimental test bed using a real power system feeder shows that this architecture provides better stability compared with conventional schemes. [ABSTRACT FROM AUTHOR]

Rare class problems are common in real-world applications across a wide range of domains. Standard classification algorithms are known to perform poorly in these cases, since they focus on overall classification accuracy. In addition, we have seen a significant increase of data in recent years, resulting in many large scale rare class problems. In this paper, we focus on nonlinear kernel based classification methods expressed as a regularized loss minimization problem. We address the challenges associated with both rare class problems and large scale learning, by 1) optimizing area under curve of the receiver of operator characteristic in the training process, instead of classification accuracy and 2) using a rare class kernel representation to achieve an efficient time and space algorithm. We call the algorithm RankRC. We provide justifications for the rare class representation and experimentally illustrate the effectiveness of RankRC in test performance, computational complexity, and model robustness. [ABSTRACT FROM PUBLISHER]

Accurate tree-cover estimates are useful in deriving above-ground biomass density estimates from very high resolution (VHR) satellite imagery data. Numerous algorithms have been designed to perform tree-cover delineation in high-to-coarse-resolution satellite imagery, but most of them do not scale to terabytes of data, typical in these VHR data sets. In this paper, we present an automated probabilistic framework for the segmentation and classification of 1-m VHR data as obtained from the National Agriculture Imagery Program (NAIP) for deriving tree-cover estimates for the whole of Continental United States, using a high-performance computing architecture. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on conditional random field, which helps in capturing the higher order contextual dependence relations between neighboring pixels. Once the final probability maps are generated, the framework is updated and retrained by incorporating expert knowledge through the relabeling of misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates (FPRs). The tree-cover maps were generated for the state of California, which covers a total of 11 095 NAIP tiles and spans a total geographical area of 163 696 sq. miles. Our framework produced correct detection rates of around 88% for fragmented forests and 74% for urban tree-cover areas, with FPRs lower than 2% for both regions. Comparative studies with the National Land-Cover Data algorithm and the LiDAR high-resolution canopy height model showed the effectiveness of our algorithm for generating accurate high-resolution tree-cover maps. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel sparse signal recovery algorithm called the trainable iterative soft thresholding algorithm (TISTA). The proposed algorithm consists of two estimation units: a linear estimation unit and a minimum mean squared error (MMSE) estimator based shrinkage unit. The error variance required in the MMSE shrinkage unit is precisely estimated from a tentative estimate of the original signal. The remarkable feature of the proposed scheme is that TISTA includes adjustable variables that control step size and the error variance for the MMSE shrinkage function. The variables are adjusted by standard deep learning techniques. The number of trainable variables of TISTA is nearly equal to the number of iteration rounds and is much smaller than that of known learnable sparse signal recovery algorithms. This feature leads to highly stable and fast training processes of TISTA. Computer experiments show that TISTA is applicable to various classes of sensing matrices, such as Gaussian matrices, binary matrices, and matrices with large condition numbers. Numerical results also demonstrate that, in many cases, TISTA provides significantly faster convergence than approximate message passing (AMP) and the learned iterative shrinkage thresholding algorithm and also outperforms orthogonal AMP in the NMSE performance. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this paper, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network’s predictions. Our approach can analyze a variety of CNN-based models trained for computer vision applications, such as object recognition and caption generation. Unlike the existing methods, we achieve this via unraveling the forward pass operation. The proposed method exploits feature dependencies across the layer hierarchy and uncovers the discriminative image locations that guide the network’s predictions. We name these locations CNN fixations, loosely analogous to human eye fixations. Our approach is a generic method that requires no architectural changes, additional training, or gradient computation, and computes the important image locations (CNN fixations). We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks, and data modalities. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection (MSD). Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD. In our framework, we first learn domain-invariant objectness knowledge from the existing fully labeled categories. The knowledge is modeled based on invariant features that are robust to the distribution discrepancy between the existing categories and new categories; therefore the resulting knowledge would generalize well to new categories and could assist detection models to reject distractors (e.g., object parts) in weakly labeled images of new categories. Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors in weakly labeled images. Our robust objectness transfer approach outperforms the existing MSD methods, and achieves state-of-the-art results on the challenging ILSVRC2013 detection dataset and the PASCAL VOC datasets. [ABSTRACT FROM AUTHOR]

In this paper, four iterative algorithms for learning analysis operators are presented. They are built upon the same optimization principle underlying both Analysis K-SVD and Analysis SimCO. The forward and sequential analysis operator learning (AOL) algorithms are based on projected gradient descent with optimally chosen step size. The implicit AOL algorithm is inspired by the implicit Euler scheme for solving ordinary differential equations and does not require to choose a step size. The fourth algorithm, singular value AOL, uses a similar strategy as Analysis K-SVD while avoiding its high computational cost. All algorithms are proven to decrease or preserve the target function in each step and a characterization of their stationary points is provided. Further they are tested on synthetic and image data, compared to Analysis SimCO and found to give better recovery rates and faster decay of the objective function, respectively. In a final denoising experiment the presented algorithms are again shown to perform similar to or better than the state-of-the-art algorithm ASimCO. [ABSTRACT FROM AUTHOR]

Electron and light microscopy imaging can now deliver high-quality image stacks of neural structures. However, the amount of human annotation effort required to analyze them remains a major bottleneck. While machine learning algorithms can be used to help automate this process, they require training data, which is time-consuming to obtain manually, especially in image stacks. Furthermore, due to changing experimental conditions, successive stacks often exhibit differences that are severe enough to make it difficult to use a classifier trained for a specific one on another. This means that this tedious annotation process has to be repeated for each new stack. In this paper, we present a domain adaptation algorithm that addresses this issue by effectively leveraging labeled examples across different acquisitions and significantly reducing the annotation requirements. Our approach can handle complex, nonlinear image feature transformations and scales to large microscopy datasets that often involve high-dimensional feature spaces and large 3D data volumes. We evaluate our approach on four challenging electron and light microscopy applications that exhibit very different image modalities and where annotation is very costly. Across all applications we achieve a significant improvement over the state-of-the-art machine learning methods and demonstrate our ability to greatly reduce human annotation effort. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) recognition is an important tool for online monitoring of gas insulated switchgear (GIS) and diagnosing existing defects. At present, there are two different types of data patterns used for analysis and evaluation of PD signals: phase resolved partial discharge (PRPD) mode and time resolved partial discharge (TRPD) mode. Using different types of data patterns separately can lead to inconsistent or even conflicted recognition results, but the two types of data patterns having complementary information between each other can be used together for data fusion. Dempster-Shafer (DS) evidence theory is introduced to address the problem of evidence conflict and low fusion efficiency. First, two sub-networks for PD recognition are established and compared employing the back propagation neural network (BPNN) learning algorithm under the two modes respectively. Secondly, to minimize (with possible elimination of) the possibility of misclassification, a new fusion decision-making system for PD recognition is proposed on the basis of fusing the results from the sub-networks. Finally, extensive field experiments on two artificial defects are conducted in order to evaluate the performance of the proposed method in this paper. The classification results reveal that the proposed method significantly outperforms the ways of using only single type of data patterns. The method proposed in this paper reduces the uncertainty and effectively improves the credibility of diagnosis. [ABSTRACT FROM AUTHOR]

In this work and the supporting Parts II and III of this paper, also in the current issue, we provide a rather detailed analysis of the stability and performance of asynchronous strategies for solving distributed optimization and adaptation problems over networks. We examine asynchronous networks that are subject to fairly general sources of uncertainties, such as changing topologies, random link failures, random data arrival times, and agents turning on and off randomly. Under this model, agents in the network may stop updating their solutions or may stop sending or receiving information in a random manner and without coordination with other agents. We establish in Part I conditions on the first and second-order moments of the relevant parameter distributions to ensure mean-square stable behavior. We derive in Part II expressions that reveal how the various parameters of the asynchronous behavior influence network performance. We compare in Part III the performance of asynchronous networks to the performance of both centralized solutions and synchronous networks. One notable conclusion is that the mean-square-error performance of asynchronous networks shows a degradation only in the order of O(\nu), where \nu is a small step-size parameter, while the convergence rate remains largely unaltered. The results provide a solid justification for the remarkable resilience of cooperative networks in the face of random failures at multiple levels: agents, links, data arrivals, and topology. [ABSTRACT FROM PUBLISHER]