Predicting the direction of stock price changes is an important factor, as it contributes to the development of effective strategies for stock exchange transactions and attracts much interest in incorporating variables historical series into the mathematical models or computer algorithms in order to produce estimations of expected price fluctuations. The purpose of this study is to build a neural model for the financial market, allowing predictions of stocks closing prices future behavior negotiated in BM&FBOVESPA in the short term, using the economic and financial theory, combining technical analysis, fundamental analysis and analysis of time series, to predict price behavior, addressing the percentage of correct predictions of price series direction (POCID or Prediction of Change in Direction). The aim of this work is to understand the information available in the financial market and identify the variables that drive stock prices. The methodology presented may be adapted to other companies and their stock. Petrobras stock PETR4, traded in BM&FBOVESPA, was used as a case study. As part of this effort, configurations with different window sizes were designed, and the best performance was achieved with a window size of 3, which the POCID index of correct direction predictions was 93.62% for the test set and 87.50% for a validation set.

Applying Artificial Neural Networks to prediction of stock price and improvement of the directional prediction index – Case study of PETR4, Petrobras, Brazil

HELAD: A Novel Network Anomaly Detection Model Based on Heterogeneous Ensemble Learning

This above fig illustrates the flowchart of our proposed algorithm. The procedure consists of two main processes: the global HS-based search process and the local FFO-based search process. The FFO scheme is integrated into the modified HS as a local search strategy. Obviously, the HMs are updated two times in each iteration, one time is for the global HS search, while the other is for the local FFO search strategy. In this way, the exploration capability of the HS scheme and the exploitation ability of the FFO scheme are both considered in this algorithm. A harmony memory consideration rule is developed.Global-best pitch adjustment rule and parallel updating strategy are employed.The fruit fly optimization (FFO) scheme is integrated into the improved HS as a local search strategy. This study presents an effective hybrid algorithm based on harmony search (HHS) for solving multidimensional knapsack problems (MKPs). In the proposed HHS algorithm, a novel harmony improvisation mechanism is developed with the modified memory consideration rule and the global-best pitch adjustment scheme to enhance the global exploration. A parallel updating strategy is employed to enrich the harmony memory diversity. To well balance the exploration and the exploitation, the fruit fly optimization (FFO) scheme is integrated as a local search strategy. For solving MKPs, binary strings are used to represent solutions and two repair operators are applied to guarantee the feasibility of the solutions. The HHS is calibrated based on the Taguchi method of design-of-experiment. Extensive numerical investigations based on well-known benchmark instances are conducted. The comparative evaluations indicate the HHS is much more effective than the existing HS and FFO variants in solving MKPs.

An effective hybrid harmony search-based algorithm for solving multidimensional knapsack problems

A binary grey wolf optimizer for the multidimensional knapsack problem

Collaborative filtering is among the most preferred techniques when implementing recommender systems. Recently, great interest has turned toward parallel and distributed implementations of collaborative filtering algorithms. This work is a survey of parallel and distributed collaborative filtering implementations, aiming to not only provide a comprehensive presentation of the field's development but also offer future research directions by highlighting the issues that need to be developed further.

Parallel and Distributed Collaborative Filtering: A Survey

The rapid development of modern communication systems propels the demand of high performance and miniaturization of RF/microwave components. Power dividers and filters are indispensable circuit components in amplifiers and antenna feed-networks which occupy large footprint of circuit broads, particularly at low frequency. The purpose of this study is to initiate a new type of planar transmission line with unique dual signal-path characteristics and ultimately achieve circuit miniaturization. In this paper, a novel technique of consolidating microstrip lines (MLs) and coplanar waveguide (CPW) lines on a single dielectric substrate, designated as the composite microstrip/CPW line (CM/CPW line), is proposed. With reference to the average line length of ML and CPW, it warrants a physical length reduction of 48.3% and further achieves a reduction of 80.8% after zigzagging CM/CPW line. The proof-of-concept design example of a two-way Wilkinson power divider (WPD) has demonstrated the effectiveness of the miniaturization technique. The simulation, in combination with the experimental results, validates that a size reduction factor of 86.9% when compared to conventional one has been achieved while maintaining a fractional bandwidth of 57.7% for the WPD. 

Miniaturization of microwave planar circuits using composite microstrip/coplanar-waveguide transmission lines

Multidimensional knapsack problem (MKP) is known to be a NP-hard problem, more specifically a NP-complete problem, which cannot be resolved in polynomial time up to now. MKP can be applicable in many management, industry and engineering fields, such as cargo loading, capital budgeting and resource allocation, etc. In this article, using a combinational permutation constructed by the convex combinatorial value $$M_j=(1-\lambda ) u_j+ \lambda x^\mathrm{LP}_j$$ M j = ( 1 - ? ) u j + ? x j LP of both the pseudo-utility ratios of MKP and the optimal solution $$x^\mathrm{LP}$$ x LP of relaxed LP, we present a new hybrid combinatorial genetic algorithm (HCGA) to address multidimensional knapsack problems. Comparing to Chu's GA (J Heuristics 4:63---86, 1998), empirical results show that our new heuristic algorithm HCGA obtains better solutions over 270 standard test problem instances.

A new hybrid combinatorial genetic algorithm for multidimensional knapsack problems

Forecasting volatility is an important issue in financial econometric analysis. This paper aims to seek a computationally feasible approach for predicting large scale conditional volatility and covariance of financial time series. In the case of multi-variant time series, the volatility is represented by a Conditional Covariance Matrix (CCM). Traditional models for predicting CCM such as GARCH models are incapable of dealing with high-dimensional cases as there are O(N 2) parameters to be estimated in the case of N-variant asset return, and it is difficult to accelerate the computation of estimating these parameters by utilizing modern multi-core architecture. These GARCH models also have difficulties in modeling non-linear properties. The widely used Restricted Boltzmann Machine (RBM) is an energy-based stochastic recurrent neural network and its extended model, Conditional RBM (CRBM), has shown its capability in modeling high-dimensional time series. In this paper, we first propose a CRBM-based approach to forecast CCM and show how to capture the long memory properties in volatility, and then we implement the proposed model on GPU by using CUDA and CUBLAS. Experiment results indicate that the proposed CRBM-based model obtains better forecasting accuracy for low-dimensional volatility and it also shows great potential in modeling for large-scale cases compared with traditional GARCH models.

Forecasting large scale conditional volatility and covariance using neural network on GPU

Communication plays a critical role in the design and performance of multi-core systems-on-chip (SoCs). Networks-on-chip (NoCs) have been proposed as a promising solution to complex on-chip communication problems. As regular NoC topologies are infeasible to satisfy the performance demand for application-specific NoC, customized topology synthesis is therefore desirable. However, NoC topology synthesis problem is an NP-hard problem. In this paper, we propose a suboptimal genetic-algorithm based technique to synthesize application-specific NoC topology with system-level floorplan awareness. The method minimizes the power consumption and router resources while satisfying latency and bandwidth performance constraints. We have evaluated the proposed technique by running a number of representative benchmark applications and the results indicate that our method generates approximate optimal topologies effectively and efficiently for all benchmarks under consideration.

Floorplan-aware application-specific network-on-chip topology synthesis using genetic algorithm technique

Collaborative Filtering (CF) is an important technique for recommendation systems which model and analyzes the preferences of customers for giving reasonable advices. Recently, many applications based on Restricted Boltzmann Machine (RBM) have been developed for a large variety of learning problems. RBM-based model for Collaborative Filtering (RBM-CF) is able to deal with large scale data sets and obtains good recommendation performance. However, the computation of RBM becomes problematic when using large number of hidden features to improve the recommendation accuracy. Although RBM has great potential for parallelism, it is still a challenge to develop a parallel implementation of RBM-CF on GPU, since the data sets for CF are always large and sparse. In this paper, we propose a parallel implementation of RBM-CF on GPU using CUDA. We first present how to transform the computation of RBM-CF into matrix-based operation on GPU, and three CUDA kernels for sparse matrix-matrix multiplication to further improve the computational efficiency of RBM-CF for modeling large scale and sparse data sets. Experimental results show that significant speedups are achieved by our parallel implementation on GPU.

Guoming Lai

Papers

Miniaturization of microwave planar circuits using composite microstrip/coplanar-waveguide transmission lines

A new hybrid combinatorial genetic algorithm for multidimensional knapsack problems

Forecasting large scale conditional volatility and covariance using neural network on GPU

Floorplan-aware application-specific network-on-chip topology synthesis using genetic algorithm technique

GPU-accelerated restricted boltzmann machine for collaborative filtering