The journey of graph kernels through two decades

In the real world all events are connected. There is a hidden network of dependencies that governs behavior of natural processes. Without much argument it can be said that, of all the known data-structures, graphs are naturally suitable to model such information. But to learn to use graph data structure is a tedious job as most operations on graphs are computationally expensive, so exploring fast machine learning techniques for graph data has been an active area of research and a family of algorithms called kernel based approaches has been famous among researchers of the machine learning domain. With the help of support vector machines, kernel based methods work very well for learning with Gaussian processes. In this survey we will explore various kernels that operate on graph representations. Starting from the basics of kernel based learning we will travel through the history of graph kernels from its first appearance to discussion of current state of the art techniques in practice.     

An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown

Dynamic control theory has long been used in solving optimal asset allocation problems, and a number of trading decision systems based on reinforcement learning methods have been applied in asset allocation and portfolio rebalancing. In this paper, we extend the existing work in recurrent reinforcement learning (RRL) and build an optimal variable weight portfolio allocation under a coherent downside risk measure, the expected maximum drawdown, E(MDD). In particular, we propose a recurrent reinforcement learning method, with a coherent risk adjusted performance objective function, the Calmar ratio, to obtain both buy and sell signals and asset allocation weights. Using a portfolio consisting of the most frequently traded exchange-traded funds, we show that the expected maximum drawdown risk based objective function yields superior return performance compared to previously proposed RRL objective functions (i.e. the Sharpe ratio and the Sterling ratio), and that variable weight RRL long/short portfolios outperform equal weight RRL long/short portfolios under different transaction cost scenarios. We further propose an adaptive E(MDD) risk based RRL portfolio rebalancing decision system with a transaction cost and market condition stop-loss retraining mechanism, and we show that the proposed portfolio trading system responds to transaction cost effects better and outperforms hedge fund benchmarks consistently.     

Convergence of parallel block SSOR multisplitting method for block H-matrix

In this paper we investigate block SSOR multisplittings. When the coefficient matrix is a block H-matrix or a (generalized) block strictly diagonally dominant matrix, the convergence of the parallel block SSOR multisplitting method for solving nonsingular linear systems is proved. Two numerical examples are given to illustrate the theoretical results.     

Ant Colony Optimization-based method for optic cup segmentation in retinal images

An accurate detection of the cup region in retinal images is necessary to obtain relevant measurements for glaucoma detection. In this work, we present an Ant Colony Optimization-based method for optic cup segmentation in retinal fundus images. The artificial agents will construct their solutions influenced by a heuristic that combines the intensity gradient of the optic disc area and the curvature of the vessels. On their own, the exploration capabilities of the agents are limited; however, by sharing the experience of the entire colony, they are capable of obtaining accurate cup segmentations, even in images with a weak or non-obvious pallor. This method has been tested with the RIM-ONE dataset, yielding an average overlapping error of 24.3% of the cup segmentation and an area under the curve (AUC) of 0.7957 using the cup to disc ratio for glaucoma assessment.     

An error correction framework for sequences resulting from known state-transition models in Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM), the set of techniques used for disaggregating total electricity consumption in a building into its constituent electrical loads, has recently received renewed interest in the research community, partly due to the roll-out of smart metering technology worldwide. Event-based NILM approaches (i.e., those that are based on first segmenting the power time-series and associating each segment with the operation of electrical appliances) are a commonly implemented solution but are prone to the propagation of errors through the data processing pipeline. Thus, during energy estimation (the final step in the process), many corrections need to be made to account for errors incurred during segmentation, feature extraction and classification (the other steps typically present in event-based approaches). A robust framework for energy estimation should use the labels from classification to (1) model the different state transitions that can occur in an appliance; (2) account for any misclassifications by correcting event labels that violate the extracted model; and (3) accurately estimate the energy consumed by that appliance over a period of time. In this paper, we address the second problem by proposing an error-correcting algorithm which looks at sequences generated by Finite State Machines (FSMs) and corrects for errors in the sequence; errors are defined as state transitions that violate the said FSM. We evaluate our framework on simulated data and find that it improves energy estimation errors. We further test it on data from 43 appliances collected from 19 houses and find that the framework significantly improves errors in energy estimates when compared to the case with no correction in 19 appliances, leaves 17 appliances unchanged, and has a slightly negative impact on 6 appliances.     

Luminescent and porous zinc complex with 2D → 3D parallel polycatenation based on a new rigid V-shaped pyridyl ligand

Entangled coordination polymers have attracted considerable interest due to their novel structures and potential applications. In this paper, one new 2D → 3D porous zinc coordination polymer {[Zn₂(DPDBT)₂(OBA)₂](H₂O)₃}_n (1) with parallel polycatenation was synthesized under solvothermal conditions based on 2,8-di(pyridin-4-yl)dibenzo[b,d]thiophene (DPDBT) ligand. In addition, complex 1 exhibits interesting solid-state photoluminescence and high thermal stability.     

GPU-based optimal control for RWM feedback in tokamaks

The design and implementation of a Graphics Processing Unit (GPU) based Resistive Wall Mode (RWM) controller to perform feedback control on the RWM using Linear Quadratic Gaussian (LQG) control is reported herein. The control algorithm is based on a simplified DIII-D VALEN model. By using NVIDIA’s GPUDirect RDMA framework, the digitizer and output module are able to write and read directly to and from GPU memory, eliminating memory transfers between host and GPU. The system and algorithm was able to reduce plasma response excited by externally applied fields by 32% during development experiments.     

Invariant texture classification using a spatial filter bank in multi-resolution analysis

This paper proposed a new method based on spatial filter banks and discrete wavelet transform (DWT) for invariant texture classification. The method used a multi-resolution analysis method like DWT and applied the proposed filter bank on different resolutions. Then, a simple fusion of features on different resolutions was used for invariant texture analysis. A comprehensive study was done to examine the effectiveness of the proposed method. Different datasets with different properties were used in this paper such as Brodatz, Outex, and KTH-TIPS for the evaluation. Local binary pattern (LBP) methods have been one of the powerful methods in recent years for invariant texture classification. A comparative study was performed with some state-of-the-art LBP methods. This comparison indicated promising results for the proposed approach as compared with the LBP methods.     

Enhanced energy storage performance of BNT-ST based ceramics under low electric field via domain engineering

Lead-free bulk ceramics for advanced pulse power capacitors possess low recoverable energy storage density (W_rec) under low electric field. Sodium bismuth titanate (Bi_0.5Na_0.5TiO₃, BNT)-based ferroelectrics have attracted great attention due to their large maximum polarization (P_m) and high power density. The BNT-ST: xAlN ceramics are designed and fabricated to get high W_rec and large P_m under low electric field simultaneously. An excellent large P_m (49.04 μC/cm²) and W_rec (2.07 J/cm³) under low electric field (160 kV/cm) are acquired in BNT-ST: 0.1 wt% AlN. The domain structure evolution and polarization switching are investigated systematically using piezoresponse force microscopy (PFM). The introduction of AlN promotes the formation of thermal conductive network and the crystallization of ceramics, thus improving thermal stability and increasing P_m significantly. The higher density of domain walls and the larger negative built-in voltage may be beneficial to increase breakdown field strength (E_b), while the more 180° domains induce by electric field and the better domain switching behavior contribute to a significant increase in P_m. The enhanced E_b and super high P_m are favorable for obtaining high W_rec under low electric field which will boost the application of BNT-based ferroelectrics in advanced pulse power capacitors.     

Swarm intelligence based approach for sinkhole attack detection in wireless sensor networks

Swarm intelligence, a nature inspired computing applies an algorithm situated within the context of agent based models that mimics the behavior of ants to detect sinkhole attacks in wireless sensor networks. An Ant Colony Optimization Attack Detection (ACO-AD) algorithm is proposed to identify the sinkhole attacks based on the nodeids defined in the ruleset. The nodes generating an alert on identifying a sinkhole attack are grouped together. A voting method is proposed to identify the intruder. An Ant Colony Optimization Boolean Expression Evolver Sign Generation (ABXES) algorithm is proposed to distribute the keys to the alerted nodes in the group for signing the suspect list to agree on the intruder. It is shown that the proposed method identifies the anomalous connections without generating false positives and minimizes the storage in the sensor nodes in comparison to LIDeA architecture for sinkhole attack detection. Experimental results demonstrating the Ant Colony Optimization approach of detecting a sinkhole attack are presented.