Yuki Todo

Financial time series prediction using a dendritic neuron model

As a complicated dynamic system, financial time series calls for an appropriate forecasting model. In this study, we propose a neuron model based on dendritic mechanisms and a phase space reconstruction (PSR) to analyze the Shanghai Stock Exchange Composite Index, Deutscher Aktienindex, N225, and DJI Average. The PSR allows us to reconstruct the financial time series, so we can prove that attractors exist for the systems constructed. Thus, the attractors obtained can be observed intuitively in a three-dimensional search space, thereby allowing us to analyze the characteristics of dynamic systems. In addition, using the reconstructed phase space, we confirmed the chaotic properties and the reciprocal to determine the limit of prediction through the maximum Lyapunov exponent. We also made short-term predictions based on the nonlinear approximating dendritic neuron model, where the experimental results showed that the proposed methodology which hybridizes PSR and the dendritic model performed better than traditional multi-layered perceptron, the Elman neural network, the single multiplicative neuron model and the neuro-fuzzy inference system in terms of prediction accuracy and training time. Hopefully, this hybrid technology is capable to advance the research for financial time series and provide an effective solution to risk management.

Unsupervised learnable neuron model with nonlinear interaction on dendrites

Recent researches have provided strong circumstantial support to dendrites playing a key and possibly essential role in computations. In this paper, we propose an unsupervised learnable neuron model by including the nonlinear interactions between excitation and inhibition on dendrites. The model neuron self-adjusts its synaptic parameters, so that the synapse to dendrite, according to a generalized delta-rule-like algorithm. The model is used to simulate directionally selective cells by the unsupervised learning algorithm. In the simulations, we initialize the interaction and dendrite of the neuron randomly and use the generalized delta-rule-like unsupervised learning algorithm to learn the two-dimensional multi-directional selectivity problem without an external teachers signals. Simulation results show that the directionally selective cells can be formed by unsupervised learning, acquiring the required number of dendritic branches, and if needed, enhanced and if not, eliminated. Further, the results show whether a synapse exists; if it exists, where and what type (excitatory or inhibitory) of synapse it is. This leads us to believe that the proposed neuron model may be considerably more powerful on computations than the McCulloch-Pitts model because theoretically a single neuron or a single layer of such neurons is capable of solving any complex problem. These may also lead to a completely new technique for analyzing the mechanisms and principles of neurons, dendrites, and synapses.

An approximate logic neuron model with a dendritic structure

An approximate logic neuron model (ALNM) based on the interaction of dendrites and the dendritic plasticity mechanism is proposed. The model consists of four layers: a synaptic layer, a dendritic layer, a membrane layer, and a soma body. ALNM has a neuronal-pruning function to form its unique dendritic topology for a particular task, through screening out useless synapses and unnecessary dendrites during training. In addition, corresponding to the mature dendritic morphology, the trained ALNM can be substituted by a logic circuit, using the logic NOT, AND and OR operations, which possesses powerful operation capacities and can be simply implemented in hardware. Since the ALNM is a feed-forward model, an error back-propagation algorithm is used to train it. To verify the effectiveness of the proposed model, we apply the model to the Iris, Glass and Cancer datasets. The results of the classification accuracy rate and convergence speed are analyzed, discussed, and compared with a standard back-propagation neural network. Simulation results show that ALNM can be used as an effective pattern classification method. It reduces the size of the dataset features by learning, without losing any essential information. The interaction between features can also be observed in the dendritic morphology. Simultaneously, the logic circuit can be used as a single classifier to deal with big data accurately and efficiently.

Incorporation of Solvent Effect into Multi-Objective Evolutionary Algorithm for Improved Protein Structure Prediction

The problem of predicting the three-dimensional (3-D) structure of a protein from its one-dimensional sequence has been called the “holy grail of molecular biology”, and it has become an important part of structural genomics projects. Despite the rapid developments in computer technology and computational intelligence, it remains challenging and fascinating. In this paper, to solve it we propose a multi-objective evolutionary algorithm. We decompose the protein energy function Chemistry at HARvard Macromolecular Mechanics force fields into bond and non-bond energies as the first and second objectives. Considering the effect of solvent, we innovatively adopt a solvent-accessible surface area as the third objective. We use 66 benchmark proteins to verify the proposed method and obtain better or competitive results in comparison with the existing methods. The results suggest the necessity to incorporate the effect of solvent into a multi-objective evolutionary algorithm to improve protein structure prediction in terms of accuracy and efficiency.

Discrete Chaotic Gravitational Search Algorithm for Unit Commitment Problem

This paper presents a discrete chaotic gravitational search algorithm (DCGSA) to solve the unit commitment (UC) problem. Gravitational search algorithm (GSA) has been applied to a wide scope of global optimization problems. However, GSA still suffers from the inherent disadvantages of trapping in local minima and the slow convergence rates. The UC problem is a discrete optimization problem and the original GSA and chaos which belong in the realm of continuous space cannot be applied directly. Thus in this paper a data discretization method is implemented after the population initialization to make the improved algorithm available for coping with discrete variables. Two chaotic systems, including logistic map and piece wise linear chaotic map, are used to generate chaotic sequences and to perform local search. The simulation was carried out on small-scale UC problem with six-unit system and ten-unit system. Simulation results show lower fuel cost than other methods such as quadratic model, selective pruning method and iterative linear algorithm, confirming the potential and effectiveness of the proposed DCGSA for the UC problem.

PMPSO: A near-optimal graph planarization algorithm using probability model based particle swarm optimization

Particle swarm optimization (PSO) has gained increasing attention in dealing with complex optimization problems. Nevertheless it still has some drawbacks, such as slow convergence and the tendency to become trapped in local minima. To overcome the local minimum problem of the PSO, a probability model inspired by the estimation distribution algorithm is incorporated into the PSO. The solutions generated by PSO are utilized to construct a probability vector which is thereafter utilized to guide the search to promising search space. The proposed probability model based particle swarm optimization (PMPSO) is used to solve the graph planarization problem (GPP) based on the single-row routing representation. Experimental results indicate that PSO that handles binary values for the problem can be applied on GPP, and the PMPSO is capable of obtaining competitive solutions when compared with other state-of-art algorithms.

AIMOES: Archive information assisted multi-objective evolutionary strategy for ab initio protein structure prediction

Abstract Despite half-century’s unremitting efforts, the prediction of protein structure from its amino acid sequence remains a grand challenge in computational biology and bioinformatics. Two key factors are crucial to solving the protein structure prediction (PSP) problem: an effective energy function and an efficient conformation search strategy. In this study, we model the PSP as a multi-objective optimization problem. A three-objective evolution algorithm called AIMOES is proposed. AIMOES adopts three physical energy terms: bond energy, non-bond energy, and solvent accessible surface area. In AIMOES, an evolution scheme which flexibly reuse past search experiences is incorporated to enhance the efficiency of conformation search. A decision maker based on the hierarchical clustering is carried out to select representative solutions. A set of benchmark proteins with 30–91 residues is tested to verify the performance of the proposed method. Experimental results show the effectiveness of AIMOES in terms of the root mean square deviation (RMSD) metric, the distribution diversity of the obtained Pareto front and the success rate of mutation operators. The superiority of AIMOES is demonstrated by the performance comparison with other five state-of-the-art PSP methods.

Single dendritic neuron with nonlinear computation capacity: A case study on XOR problem

Recently, a series of theoretical studies have conjectured that synaptic nonlinearities in a dendritic tree could make individual neurons act more powerfully in complex computational operations. Each of the neurons has quite distinct morphologies of synapses and dendrites to determine what signals a neuron receives and how these signals are integrated. However, there is no effective model that can captures the nonlinearities among excitatory and inhibitory inputs while predicting the morphology and its evolution of synapses and dendrites. In this paper, we propose a new single neuron model with synaptic nonlinearities in a dendritic tree. The computation on neuron has a neuron-pruning function that can reduce dimension by removing useless synapses and dendrites during learning, forming a precise synaptic and dendritic morphology. The nonlinear interactions in a dendrite tree are expressed using the Boolean logic AND (conjunction), OR (disjunction) and NOT (negation). An error back propagation algorithm is used to train the neuron model. Furthermore, we apply the new model to the Exclusive OR (XOR) problem and it can solve the problem perfectly with the help of inhibitory synapses which demonstrate synaptic nonlinear computation and the neurons ability to learn.

An artificial bee colony algorithm search guided by scale-free networks

Abstract Many optimization algorithms have adopted scale-free networks to improve the search ability. However, most methods have merely changed their population topologies into those of scale-free networks; their experimental results cannot verify that these algorithms have superior performance. In this paper, we propose a scale-free artificial bee colony algorithm (SFABC) in which the search is guided by a scale-free network. The mechanism enables the SFABC search to follow two rules. First, the bad food sources can learn more information from the good sources of their neighbors. Second, the information exchange among good food sources is relatively rare. To verify the effectiveness of SFABC, the algorithm is compared with the original artificial bee colony algorithm (ABC), several advanced ABC variants, and other metaheuristic algorithms on a wide range of benchmark functions. Experimental results and statistical analyses indicate that SFABC obtains a better balance between exploration and exploitation during the optimization process and that, in most cases, it can provide a competitive performance of the benchmark functions. We also verify that scale-free networks can not only improve the optimization performance of ABC but also enhance the search ability of other metaheuristic algorithms, such as differential evolution (DE) and the flower pollination algorithm (FPA).

A Novel Memetic Whale Optimization Algorithm for Optimization.

Whale optimization algorithm (WOA) is a newly proposed search optimization technique which mimics the encircling prey and bubble-net attacking mechanisms of the whale. It has proven to be very competitive in comparison with other state-of-the-art metaheuristics. Nevertheless, the performance of WOA is limited by its monotonous search dynamics, i.e., only the encircling mechanism drives the search which mainly focus the exploration in the landscape. Thus, WOA lacks of the capacity of jumping out the of local optima. To address this problem, this paper propose a memetic whale optimization algorithm (MWOA) by incorporating a chaotic local search into WOA to enhance its exploitation ability. It is expected that MWOA can well balance the global exploration and local exploitation during the search process, thus achieving a better search performance. Forty eight benchmark functions are used to verify the efficiency of MWOA. Experimental results suggest that MWOA can perform better than its competitors in terms of the convergence speed and the solution accuracy.