Abstract: In the developing world, majority of people usually take para-transit services for their everyday commutes. However, their informal and demand-driven operation, like making arbitrary stops to pick up and drop off passengers, has been inefficient and poses challenges to efforts in integrating such services to more organized train and bus networks. In this study, we devised a methodology to design and optimize a road-based para-transit network using a genetic algorithm to optimize efficiency, robustness, and invulnerability. We first generated stops following certain geospatial distributions and connected them to build networks of routes. From them, we selected an initial population to be optimized and applied the genetic algorithm. Overall, our modified genetic algorithm with 20 evolutions optimized the 20% worst performing networks by 84% on average. For one network, we were able to significantly increase its fitness score by 223%. The highest fitness score the algorithm was able to produce through optimization was 0.532 from a score of 0.303.

Abstract: Networks furnish a mathematical framework to model and decipher the collective behavior of the complex real-world systems. Scrutiny of principal eigenvector (PEV) and the corresponding eigenvalue of the networks are known to provide an understanding of various local and global structural as well as the dynamical evolution of the networks. Recently scrutiny of eigenvector localization has received tremendous attention in network science due to its versatile applicability in many different areas which includes analyzing centrality measure, spectral partitioning, development of approximation algorithms and disease spreading phenomenon. Moreover, lower order eigenvectors have been studied to develop machine learning tools. They used inverse participation ratio (IPR) as well as another kind of measure for the eigenvector localization, called as statistical leverage score which has an impact on modern big data analysis. One key factor of our interest is to understand properties of networks which may help in spreading or restricting perturbation in networks captured by the PEV localization. For a network, an eigenvector is said to be localized when most of its components are near to zero, with few taking very high values. To study the structural and spectral properties of networks as PEV changes its state from the delocalized to a highly localized, we evolve an initial random network. We develop randomized algorithms considering the IPR as an objective function. We demonstrate that PEV localization is not a consequence of a single network property and rather requires collective impact of several structural features. The final optimized network possesses a special structure independent of the initial network. It reveals that optimized network consists of two graph components of different sizes which are connected to each other via a single node (in Fig. 1). Moreover, the optimized structure contains a special set of edges, rewiring any one of them leads to a complete delocalization of the PEV from a highly localized state (Fig. 2). This sensitivity of the PEV at the most localized state turns out to be related to the behavior of the largest and the second largest eigenvalue of the network. Precisely when the network becomes most localized, the second largest eigenvalue of the adjacency matrix become very close to the largest eigenvalue (Fig. 3). Furthermore, we identify an evolution regime where networks are as localized as the optimized one, but, are robust to single edge rewiring (in Fig. 2). Moreover, we use the Susceptible-Infected-Susceptible (SIS) disease spreading model and verify that the structure of the networks in the intermediate and optimized stages slows down the spreading process than the initial random structure (Fig. 4).

Abstract: Automated Planning has achieved a significant step forward in the last decade, and many advanced planning engines have been introduced. Nowadays, increases in computational power are mostly achieved through hardware parallelisation. In view of the increasing availability of multicore machines and of the intrinsic complexity of designing parallel algorithms, a natural exploitation of parallelism is to combine existing sequential planning engines into parallel portfolios. In this work, we introduce three techniques for an automatic configuration of static parallel portfolios of planning engines. The aim of generated portfolios is to provide a good tradeoff performance between coverage and runtime, on previously unseen problems. Our empirical results demonstrate that our techniques for configuring parallel portfolios combine strengths of planning engines, and fully exploit multicore machines.

Abstract: Spatial optimization (SO) is an important and prolific field of interdisciplinary research. Spatial optimization methods seek optimal allocation or arrangement of spatial units under constraints such as distance, adjacency, and contiguity. Evolutionary Algorithms (EA) are well-known heuristic approach for solving SO problems. However, as spatial granularity becomes finer and problem formulations comprise increasingly complex spatial relationships, EA solvers must be adapted with greater computational efficiency and algorithmic effectiveness. We present a solution that addresses the efficiency issue by leveraging massive computing power on supercomputers. The computational scalability challenge is tackled with a parallel EA library that eliminates the costly global synchronization in massively parallel computing environment. Our implementation scales to 131,072 processors on the Blue Waters supercomputer. We develop novel spatially explicit EA recombination operators that implement crossover and mutation using intelligently guided strategies in spatially constrained decision space, inspired by path relinking and ejection chain heuristics. Our high-performance EA framework is employed as a computational solution for the complex problem of political redistricting in the United States. It enables the creation of billions of feasible districting plans that adhere to U.S. Supreme Court mandates and further facilitates statistical analysis of gerrymandering.

Abstract: Several computational models have been developed in order to improve the outcome of Vein Graft Bypasses in response to arterial occlusions and they all share a common property: their accuracy relies on a winning choice of the coefficients’ value related to biological functions that drive them. Our goal is to optimize the retrieval of these unknown coefficients on the base of experimental data and accordingly, as biological experiments are noisy in terms of statistical analysis and the models are typically stochastic and complex, this work wants first to elucidate which experimental measurements might be sufficient to retrieve the targeted coefficients and second how many specimens would constitute a good dataset to guarantee a sufficient level of accuracy. Since experiments are often costly and time consuming, the planning stage is critical to the success of the operation and, on the base of this consideration, the present work shows how, thanks to an ad hoc use of a computational model of vascular adaptation, it is possible to estimate in advance the entity and the quantity of resources needed in order to efficiently repro-duce the experimental reality.

Abstract: Important progress in computational sciences has been made possible recently thanks to the increasing computing power of high performance systems. Following this trend, larger scientific studies, like brain tissue simulations, will continue to grow in the future. In addition to the challenges of conducting these experiments, we foresee an explosion of the amount of data generated and the consequent unfeasibility of analyzing and understanding the results with the current techniques. This paper proposes Neurolytics, a new data analysis framework, together with a new data layout. The implementation of Neurolytics is mainly focused on simulation neuroscience, although we believe that our design can be applied to other science domains. The framework relies on big data technologies, like Apache Spark, to enable fast, reliable and distributed analyses of brain simulation data in this case. Our experimental evaluation on a cluster of 100 nodes shows that Neurolytics gets up to 374x speed-up compared to a thread-parallel Python implementation and is on par with a highly optimized Spark code. This demonstrates the suitability of our proposal to help scientists structure and understand the results of their experiments in a fast and efficient way.

Abstract: Non-linear waves occur in various physical, chemical and biological media. One of the most important examples is electrical excitation waves in the myocardium, which initiate contraction of the heart. Abnormal wave propagation in the heart, such as the formation of spiral waves, causes dangerous arrhythmias, and thus methods of elimination of such waves are of great interest. One of the most promising methods is so-called low-voltage cardioversion and defibrillation, which is believed to be achieved by inducing the drift and disappearance of spiral waves using external high-frequency electrical stimulation of the heart. In this paper, we perform a computational analysis of the interaction of spiral waves and trains of high-frequency plane waves in 2D models of cardiac tissue. We investigate the effectiveness and safety of the treatment. We also identify the dependency of drift velocity on the period of plane waves. The simulations were carried out using a parallel computing system with OpenMP technology.

Abstract: Malaria remains a deadly disease that affected millions of people in 2016. Among the five Plasmodium (P.) parasites which contribute to malaria dis-eases in humans. P. falciparum is a lethal one which is responsible for the majority of the world-wide-malaria-related deaths. Since the banana-shaped stage V gametocytes play a crucial role in disease transmission, understand-ing the deformation of single stage V gametocytes may offer deeper insights into the development of the disease and provide possible targets for new treatment methods. In this study we used lattice Boltzmann-based simula-tions to investigate the effects of the stretching forces acting on infected red blood cells inside a slit-flow cytometer. The parameters that represent the cellular deformability of healthy and malaria infected red blood cells are chosen such that they mimic the deformability of these cells in a slit-flow cy-tometer. The simulation results show good agreement with experimental data and allow for studying the transportation of malaria infected red blood cell in blood circulation.

Abstract: The paper presents early results on the development of a generalized approach for modeling and analysis of the interaction of multiple stakeholders in city environ-ment while providing services to citizens under the regulation of city authorities. The approach considers the interaction between main stakeholders (organizations of various kind, citizens, and city authorities) including information and finances exchange, activities taken and services or goods provided. The developed ap-proach is based on a combination of game-theoretic modeling and simulation of service providers interaction. Such combination enables consideration of con-fronting stakeholders as well as determined (e.g., scheduled) and stochastic varia-tion in characteristics of system’s elements. The goal of this approach develop-ment is supporting of analysis and optimization of city-level regulation through legislative, financial, and informational interaction with organizations and envi-ronment of a city. An example of ambulance dispatching during providing emer-gent care for acute coronary syndrome (ACS) patients is considered. The exam-ple is analyzed in a simplified linear case and in practical application to dispatch-ing ambulances providing service for ACS patients in Saint Petersburg.

Abstract: In soft complex grounds, earthquakes cause damages with large deformation such as landslides and subsidence. Use of elasto-plastic models as the constitutive equation of soils is suitable for evaluation of nonlinear wave propagation with large ground deformation. However, there is no example of elasto-plastic nonlinear wave propagation analysis method capable of simulating a large-scale soil deformation problem. In this study, we developed a scalable elasto-plastic nonlinear wave propagation analysis program based on three-dimensional nonlinear finite-element method. The program attains 86.2% strong scaling efficiency from 240 CPU cores to 3840 CPU cores of PRIMEHPC FX10 based Oakleaf-FX, with 8.85 TFLOPS (15.6% of peak) performance on 3840 CPU cores. We verified the elasto-plastic nonlinear wave propagation program through convergence analysis, and conducted an analysis with large deformation for an actual soft ground modeled using 47,813,250 degrees-of-freedom.

Abstract: We report on a two-scale approach for efficient matrix-free finite element simulations. The proposed method is based on surrogate element matrices constructed by low-order polynomial approximations, and applied to a Stokes-like PDE system with variable viscosity as a key component in mantle convection models. We set the basis for a rigorous performance analysis inspired by concept of parallel textbook multigrid efficiency and study the weak scaling behavior on SuperMUC, a peta-scale supercomputer system. For a real-world geodynamical model, we achieve a parallel efficiency of 95\% on up to 47\,250 compute cores. Our largest simulation uses a trillion ($\mathcal{O}(10^{12})$) degrees of freedom for a global mesh resolution of 1.7\,km.

Abstract: The computation of crustal deformation following a given fault slip is important for understanding earthquake generation processes and reduction of damage. In crustal deformation analysis, reflecting the complex geometry and material heterogeneity of the crust is important, and use of large-scale unstructured finite-element method is suitable. However, since the computation area is large, its computation cost has been a bottleneck. In this study, we develop a fast unstructured finite-element solver for GPU-based large-scale computers. By computing several times steps together, we reduce random access, together with the use of predictors suitable for viscoelastic analysis to reduce the total computational cost. The developed solver enabled 2.79 times speedup from the conventional solver. We show an application example of the developed method through a viscoelastic deformation analysis of the Eastern Mediterranean crust and mantle following a hypothetical M~9 earthquake in Greece by using a 2,403,562,056 degree-of-freedom finite-element model.

Abstract: Based on previous work on in-situ data transfer infrastructure and compiler-based software analysis, we have designed a virtual observation system for real-time computer simulations. This paper presents an event detection framework for a virtual observation system. By using signal processing and detection approaches to the memory-based data streams, this framework can be reconfigured to capture high-frequency events and low-frequency events. These approaches used in the framework can dramatically reduce the data transfer needed for in-situ data analysis (between distributed computing nodes or between the CPU/GPU nodes). In the paper, we also use a terrestrial ecosystem system simulation within the Earth System Model to demonstrate the practical values of this effort.

Abstract: This paper presents a hybrid algorithm employed to reduce the weight of an elec-tric motor, designed for electric vehicle (EV) propulsion. The approach uses a hybridization between Cuckoo Search and CMAES to generate an initial popula-tion. Then, the population is transferred to a new procedure which adaptively switches between two search strategies, i.e. one for exploration and one for ex-ploitation. Besides the electric motor optimization, the proposed algorithm per-formance is also evaluated using the 15 functions of the CEC 2015 competition benchmark. The results reveal that the proposed approach can show a very com-petitive performance when compared with different state-of-the-art algorithms.

Abstract: Nowadays, mobile cloud applications are growing progressively. It supports both compute and data intensive application integrates with the mobile device. Many attempts have been proposed to boost the application performance and to reduce the energy power of the mobile device by offloading computational components to the cloud server. However, current research only focused on mobile run time offloading cost. On the other hand, the cloud platform offloading cost has been ignored by the literature research. In this paper, we are studying the response time minimization problem of a real time applications (i.e., augmented reality, 3D gaming, mathematical tools) by considering offloading cost from both ends such as mobile run time and cloud run time with delay constraints (transmission cost and process cost). To minimize the total offloading cost, we have developed novel hybrid run time platform framework which will improve the offloading performance. However, the real time applications must be executed within a given deadline. To solve the above problem we have proposed the Latency Aware Task Assignment (LATA) algorithm which always executes real time application within a given deadline. Performance evaluation shows our proposed framework and algorithm are improving the response time and offloading cost as compared to baseline and conventional method.

Abstract: This work presents computations of electric current distributions inside an industrial submerged arc furnace. A 3D model has been developed in ANSYS Fluent that solves Maxwell’s equations based on scalar and vector potentials approach that are treated as transport equations. In this paper, the approach is described in detail and numerical simulations are performed on an industrial three-phase sub-merged arc furnace. The current distributions within electrodes due to skin and proximity effects are presented. The results show that the proposed method adequately models these phenomena

Abstract: Adaptive network-based fuzzy inference system (ANFIS), is a suitable technique for predicting the behavior of systems. In recent years, the capabilities of ANFIS in controlling nonlinear systems, has been studied by researchers. In this work, ability of ANFIS controller to stabilize the multi-link inverted pen-dulum-cart system is presented. The inverted pendulum on a cart system is a sys-tem with unstable and nonlinear behavior. Different types of inverted pendulum including single link inverted pendulum(SIP), double link inverted pendu-lum(DIP), triple link inverted pendulum(TIP) are subject of this paper. Training can be considered the most important and challenging part in design of ANFIS controller. To solve this problem, linear quadratic regulator(LQR) and linear model of inverted pendulum system are used, in a way that data including state variables are reduced to two variables, error and variation of error and are used for training of ANFIS. The most important section in designing of LQR is ap-propriate determination of Q and R matrices and consequently control gain matrix K so that it can meet the desired system characteristics such as settling time, over-shoot, …. The classic way for determination of these matrices, is trial and error approach that can be very time consuming and frustrating in some cases in addi-tion there is no guarantee to find the best possible solutions. To overcome this problem, Optimization algorithms have been used. Two Powerful optimization algorithms including genetic algorithm and particle swarm optimization algorithm are used and their results have been compared. In the end, the obtained results in MATLAB/SIMULINK environment show that the proposed ANFIS controller has an excellent ability to stabilize nonlinear multi-link inverted pendulum system in a very short time. The results associated with adding noise at the input of the system are provided in the final section of this paper which confirm that the pro-posed ANFIS controller is robust and effective.

Abstract: We consider a Cartesian decomposition of datasets, i.e. finding datasets such that their unordered Cartesian product yields the source set, and some natural generalization of this decomposition. In terms of relational databases, this means reversing the SQL CROSS JOIN and INNER JOIN operators (the last is equipped with a test verifying the equality of a table’s attribute to another table’s attribute). First we outline a polytime algorithm for computing the Cartesian decomposition. Then we describe a polytime algorithm for computing a generalized decomposition based on the Cartesian decomposition. Some applications and relating problems are discussed.

Abstract: Manifold learning is a main stream research track used for dimensionality reduction as a method to select features. Many variants have been proposed with good performance. In this paper, we present a novel graph-based supervised learning framework for image classification. It takes the advantage of graph embedding to improve the recognition accuracy. The proposed method is tested on four benchmark datasets of different types including scene, face and object. The experimental results demonstrate the effectiveness of the proposed algorithm by the comparison with other tested algorithms.

Abstract: Relation classification is one of the most important topics in Natural Language Processing (NLP) which could help mining structured facts from text and constructing knowledge graph. Although deep neural network models have achieved improved performance in this task, the state-of-the-art methods still suffer from the scarce training data and the overfitting problem. In order to solve this problem, we adopt the adversarial training framework to improve the robustness and generalization of the relation classifier. In this paper, we construct a bidirectional recurrent neural network as the relation classifier, and append word-level attention to the input sentence. Our model is an end-to-end framework without the use of any features derived from pre-trained NLP tools. In experiments, our model achieved higher F1-score and better robustness than comparative methods.

Abstract: Given a microblog post and a topic, it is an important task to judge the sentiment towards that topic: positive or negative, and has important theoretical and application value in the public opinion analysis, personalized recommendation, product comparison analysis, prevention of terrorist attacks, etc. Because of the short and irregular messages as well as containing multifarious features such as emoticons, and sentiment of a microblog post is closely related to its topic, most existing approaches cannot perfectly achieve cooperating analysis of topic and sentiment of messages, and even cannot know what factors actually determined the sentiment towards that topic. To address the issues, MB-LDA model and attention network are applied to Bi-RNN for topic-based microblog polarity classification. Our cascaded model has three distinctive characteristics: (i) a strong relationship between topic and its sentiment is considered; (ii) the factors that affect the topic’s sentiment are identified, and the degree of influence of each factor can be calculated; (iii) the synchronized detection of the topic and its sentiment in microblog is achieved. Extensive experiments show that our cascaded model outperforms state-of-the-art unsupervised approach JST and supervised approach SSA-ST significantly in terms of sentiment classification accuracy and F1-Measure.

Abstract: The existing pedestrian detection methods are still challenging under abrupt illumination, different human shape, and cluttered backgrounds. In this contribution, we suggest a novel method to handle the above detection failures. On account of the fact that the potential of features are different and a single feature cannot extract the comprehensive information and human appearance can be better acquired by combinations of efficacious features, we combine HOG, LBP, and Haar-like features. Thus, the proposed method contains the edge, texture information, and local shape information. It should be mentioned that there has not been a method based on combination of these three features yet. After feature combination, linear SVM classifier is used to detect pedestrian images from non-pedestrian. In experiments, INRIA dataset, Daimler dataset, and ETH dataset are adopted as the training and testing sets. Each dataset was recorded in various environments, resolution, and background occlusion. As a result, employing three various datasets can help not only further enrich our data but also scrutinize the robustness and precision of the proposed method in more depth. The substantial experimental result indicated that the proposed scheme outperformed the state of the art methods in terms of the accuracy with comparable computational time.

Abstract: Very large climate data repositories provide a consistent view of weather conditions over long time periods. In some applications and studies, given a current weather pattern (e.g. today's weather), it is useful to identify similar ones (weather analogues) in the past. Looking for simi-lar patterns in an archive using a brute force approach requires data to be retrieved from the ar-chive and the compared to the query, using a chosen similarity measure. Such operation would be very long and costly. In this work a wavelet-based fingerprinting scheme is proposed to in-dex all weather patterns from the archive. The scheme allows to answer queries by computing the fingerprint of the query pattern, then comparing them to the index of all fingerprints more ef-ficiently, in order to then retrieve only the corresponding selected data from the archive. The ex-perimental analysis is carried out on the ECMWF's ERA-Interim reanalyses data representing the global state of the atmosphere over seral decades. Results shows that 32 bits fingerprints are sufficient to represent metrological fields over a 1700 km×1700 km region and allow the quasi instantaneous retrieval of weather analogues.

Abstract: Assimilation of data into a fire-spread model is formulated as an optimization problem. The level set equation, which relates the fire arrival time and the rate of spread, is allowed to be satisfied only approximately, and we minimize a norm of the residual. Our previous methods based on modification of the fire arrival time either used an additive correction to the fire arrival time, or made a position correction. Unlike additive fire arrival time corrections, the new method respects the dependence of the fire rate of spread on diurnal changes of fuel moisture and on weather changes, and, unlike position corrections, it respects the dependence of the fire spread on fuels and terrain as well. The method is used to interpolate the fire arrival time between two perimeters by imposing the fire arrival time at the perimeters as constraints.

Abstract: Complex systems (e.g. volcanos, debris flows, climate) com- monly have many models advocated by different modelers and incorpo- rating different modeling assumptions. Limited and sparse data on the modeled phenomena does not permit a clean discrimination among mod- els for fitness of purpose and heuristic choices are usually made especially for critical predictions of behavior that has not been experienced. We advocate in recent work for characterizing models and the modeling as- sumptions they represent using a statistical approach over the full range of applicability of the models. Such a characterization may then be used to decide the appropriateness of a model for use and as needed weighted compositions of models for better predictive power. We use the example of dense granular representations of natural mass flows in volcanic debris avalanches to illustrate our approach.

Abstract: With the development of technology, the technology foresight becomes more and more important. Delphi method as the core method of technology foresight is increasingly questioned. This paper propose a new technology foresight method based on intelligent convergence in open network environment. We put a large number of scientific and technological innovation topics into the open network technology community. Through the supervision and guidance to stimulate the discussion of expert groups, a lot of interactive information can be generated. Based on the accurate topic delivery, effective topic monitoring, reasonable topic guiding, comprehensive topic recovering, and interactive data mining, we get the technology foresight result and further look for the expert or team engaged in relevant research.

Abstract: Detection of Cardiac Arrhythmia (CA) is performed using the clinical analysis of the electrocardiogram (ECG) of a patient to prevent cardiovascular diseases. Machine Learning Algorithms have been presented as promising tools in aid of CA diagnoses, with emphasis on those related to automatic classification. However, these algorithms suffer from two traditional problems related to classification: (1) excessive number of numerical attributes generated from the decomposition of an ECG; and (2) the number of patients diagnosed with CAs is much lower than those classified as “normal” leading to very unbalanced datasets. In this paper, we combine in a coordinate way several data mining techniques, such as clustering, feature selection, oversampling strategies and automatic classification algorithms to create more efficient classification models to identify the disease. In our evaluations, using a traditional dataset provided by the UCI, we were able to improve significantly the effectiveness of Random Forest classification algorithm achieving an accuracy of over 88%, a value higher than the best already reported in the literature.

Abstract: In the field of CT medical image reconstruction, there are two approaches you can take to reconstruct the images: the analytical methods, or the algebraic methods, which can be divided into iterative or direct. Although analytical methods are the most used for their low computational cost and good reconstruction quality, they do not allow reducing the number of views taken and thus the radiation absorbed by the patient. In this paper, we present two direct algebraic approaches for CT reconstruction: performing the Sparse QR (SPQR) factorization of the system matrix or carrying out a singular values decomposition (SVD). We compare the results obtained in terms of image quality and computational time cost and analyze the memory requirements for each case.

Abstract: In recent years interest in blood viscosity has increased significantly in different biomedical areas. Blood viscosity, a measure of the resistance of blood flow, related to its thickness and stickiness, is one of the main biophysical properties of blood. Many factors affect blood viscosity, both in physiological and in pathological conditions. The aim of this study is to estimate blood viscosity by using the regression equation of viscosity which is based on hematocrit and total plasma proteins. It can be used to perform several observations regards the main factors which can influence blood viscosity. The main contribution regards the correlation between viscosity values and other important biological parameters such as cholesterol. This correlation has been supported by performing statistical tests and it suggest that the viscosity could be the main risk factor in cardiovascular diseases. Moreover, it is the only biological measure being correlated with the other cardiovascular risk factors. Results obtained are compliant with values obtained by using the standard viscosity measurement through a viscometer.

Abstract: This paper presents improvements in financial time series prediction using a Deep Neural Network (DNN) in conjunction with a Discrete Wavelet Transform (DWT). When comparing our model to other three alternatives, including ARIMA and other deep learning topologies, ours has a better performance. All of the experiments were conducted on High Frequency Data (HFD). Given the fact that DWT decomposes signals in terms of frequency and time, we expect this transformation will make a better representation of the streaking behavior of high frequency data. The input information consists of 27 variables: The last 3 one-minute pseudo-log-returns and last 3 one-minute compressed tick-by-tick wavelet vectors. Each vector is a product of compressing the tick-by-tick transactions inside a particular minute using a DWT with length 8. Furthermore, the DNN predicts the next one-minute pseudo-log-return that can be transformed into the next predicted one-minute average price. For testing purposes, we use tick-by-tick data of 19 companies in the Dow Jones Industrial Average Index (DJIA), from January 2015 to July 2017. The proposed DNN's Directional Accuracy (DA) presents a remarkable forecasting performance ranging from 64% to 72%.

Abstract: As far as we know, Inverse Extreme Learning Machine (IELM) is the first work extending ELM to LLP problem. Due to basing on extreme learning machine (ELM), it obtains the fast speed and achieves competitive classification accuracy with the existing LLP methods. Kernel extreme learning machine (KELM) generalizes basic ELM to the kernel-based framework. It not only solves the problem that the number of hidden layer nodes in basic ELM depends on manual setting, but also presents better generalization ability and stability than basic ELM. However, there is no research based on KELM for LLP. In this paper, we apply KELM and propose the novel method LLP-KELM for LLP. The classification accuracy is greatly improved compared with IELM. Lots of numerical experiments validate the effectiveness of our method.

Abstract: Recurrent neural networks are a type of deep learning units that are well studied to extract features from sequential samples. They have been extensively applied in forecasting univariate financial time series, however their application to high frequency multivariate sequences has been merely considered. This paper solves a classification problem in which recurrent units are extended to deep architecture to extract features from multi-variance market data in 1-minutes frequency and extreme market are subsequently predicted for trading signals. Our results demonstrate the abilities of deep recurrent architecture to capture the relationship between the historical behavior and future movement of high frequency samples. The deep RNN is compared with other models, including SVM, random forest, logistic regression, using CSI300 1-minutes data over the test period. The result demonstrate that the capability of deep RNN to generate trading signal based on extreme movement prediction support more efficient market decision making and enhance the profitability.

Abstract: Multi-view Multi-task (MVMT) Learning, a novel learning paradigm, can be used in extensive applications such as pattern recognition and natural language processing. Therefore, researchers come up with several methods from different perspectives including graph model, regularization techniques and feature learning. SVMs have been acknowledged as powerful tools in machine learning. However, there is no SVMbased method for MVMT learning. In order to build up an excellent MVMT learner, we extend PSVM-2V model, an excellent SVM-based learner for MVL, to the multi-task framework. Through experiments we demonstrate the effectiveness of the proposed method.

Abstract: Based on the media news of Alibaba and improvement of L&M dictionary, this study transforms unstructured text into structured news sentiment through dictionary matching. By employing data of Alibaba’s opening price, closing price, maximum price, minimum price and volume in Thomson Reuters database, we build a fifth-order VAR model with lags. The AR test indicates the stability of VAR model. In a further step, the results of Granger causality tests, impulse response function and variance decomposition show that VAR model is successful to forecast variables dopen, dmax and dmin. What’s more, news sentiment contributes to the prediction of all these three variables. At last, MAPE reveals dopen, dmax and dmin can be used in the out sample forecast. We take dopen sequence for example, document how to predict the movement and rise of opening price by using the value and slope of dopen.