Search

This note focuses on the optimization of neural architectures for stock index movement forecasting following a major market disruption or crisis. Given that such crises may introduce a shift in market dynamics, this study aims to investigate whether the training data from market dynamics prior to the crisis are compatible with the data during the crisis period. To this end, two distinct learning environments are designed to evaluate and reconcile the effects of possibly different market dynamics. These environments differ principally based on the role assigned to the pre-crisis data. In both environments, a set of non-dominated architectures are identified to satisfy the multi-criteria co-evolution problem, which simultaneously addresses the selection issues related to features and hidden layer topology. To test the hypothesis of pre-crisis data incompatibility, the day-ahead movement prediction of the NASDAQ index is considered during two recent and major market disruptions; the 2008 financial crisis and the COVID-19 pandemic. The results of a detailed comparative evaluation convincingly support the incompatibility hypothesis and highlight the need to select re-training windows carefully., Comment: 11 pages

In a multi objective setting, a portfolio manager's highly consequential decisions can benefit from assessing alternative forecasting models of stock index movement. The present investigation proposes a new approach to identify a set of nondominated neural network models for further selection by the decision maker. A new coevolution approach is proposed to simultaneously select the features and topology of neural networks (collectively referred to as neural architecture), where the features are viewed from a topological perspective as input neurons. Further, the coevolution is posed as a multicriteria problem to evolve sparse and efficacious neural architectures. The well known dominance and decomposition based multiobjective evolutionary algorithms are augmented with a nongeometric crossover operator to diversify and balance the search for neural architectures across conflicting criteria. Moreover, the coevolution is augmented to accommodate the data based implications of distinct market behaviors prior to and during the ongoing COVID 19 pandemic. A detailed comparative evaluation is carried out with the conventional sequential approach of feature selection followed by neural topology design, as well as a scalarized coevolution approach. The results on the NASDAQ index in pre and peri COVID time windows convincingly demonstrate that the proposed coevolution approach can evolve a set of nondominated neural forecasting models with better generalization capabilities., Comment: 22 pages

This study proposes a new framework to evolve efficacious yet parsimonious neural architectures for the movement prediction of stock market indices using technical indicators as inputs. In the light of a sparse signal-to-noise ratio under the Efficient Market hypothesis, developing machine learning methods to predict the movement of a financial market using technical indicators has shown to be a challenging problem. To this end, the neural architecture search is posed as a multi-criteria optimization problem to balance the efficacy with the complexity of architectures. In addition, the implications of different dominant trading tendencies which may be present in the pre-COVID and within-COVID time periods are investigated. An $\epsilon-$ constraint framework is proposed as a remedy to extract any concordant information underlying the possibly conflicting pre-COVID data. Further, a new search paradigm, Two-Dimensional Swarms (2DS) is proposed for the multi-criteria neural architecture search, which explicitly integrates sparsity as an additional search dimension in particle swarms. A detailed comparative evaluation of the proposed approach is carried out by considering genetic algorithm and several combinations of empirical neural design rules with a filter-based feature selection method (mRMR) as baseline approaches. The results of this study convincingly demonstrate that the proposed approach can evolve parsimonious networks with better generalization capabilities., Comment: 29 pages, 6 figures

The use of deep learning methods to extract vascular biometric patterns from the palm surface has been of interest among researchers in recent years. In many biometric recognition tasks, there is a limit in the number of training samples. This is because of limited vein biometric databases being available for research. This restricts the application of deep learning methods to design algorithms that can effectively identify or authenticate people for vein recognition. This paper proposes an architecture using Siamese neural network structure for few shot palm vein identification. The proposed network uses images from both the palms and consists of two sub-nets that share weights to identify a person. The architecture performance was tested on the HK PolyU multi spectral palm vein database with limited samples. The results suggest that the method is effective since it has 91.9% precision, 91.1% recall, 92.2% specificity, 91.5%, F1-Score, and 90.5% accuracy values., Comment: 5 pages IEEE

The present study proposes a new approach to automated screening of Clinically Significant Macular Edema (CSME) and addresses two major challenges associated with such screenings, i.e., exudate segmentation and imbalanced datasets. The proposed approach replaces the conventional exudate segmentation based feature extraction by combining a pre-trained deep neural network with meta-heuristic feature selection. A feature space over-sampling technique is being used to overcome the effects of skewed datasets and the screening is accomplished by a k-NN based classifier. The role of each data-processing step (e.g., class balancing, feature selection) and the effects of limiting the region-of-interest to fovea on the classification performance are critically analyzed. Finally, the selection and implication of operating point on Receiver Operating Characteristic curve are discussed. The results of this study convincingly demonstrate that by following these fundamental practices of machine learning, a basic k-NN based classifier could effectively accomplish the CSME screening.

The present study proposes a simple grey-box identification approach to model a real DC-DC buck converter operating in continuous conduction mode. The problem associated with the information void in the observed dynamical data, which is often obtained over a relatively narrow input range, is alleviated by exploiting the known static behavior of buck converter as a priori knowledge. A simple method is developed based on the concept of term clusters to determine the static response of the candidate models. The error in the static behavior is then directly embedded into the multi-objective framework for structure selection. In essence, the proposed approach casts grey-box identification problem into a multi-objective framework to balance bias-variance dilemma of model building while explicitly integrating a priori knowledge into the structure selection process. The results of the investigation, considering the case of practical buck converter, demonstrate that it is possible to identify parsimonious models which can capture both the dynamic and static behavior of the system over a wide input range.

The present study proposes a multi-objective framework for structure selection of nonlinear systems which are represented by polynomial NARX models. This framework integrates the key components of Multi-Criteria Decision Making (MCDM) which include preference handling, Multi-Objective Evolutionary Algorithms (MOEAs) and a posteriori selection. To this end, three well-known MOEAs such as NSGA-II, SPEA-II and MOEA/D are thoroughly investigated to determine if there exists any significant difference in their search performance. The sensitivity of all these MOEAs to various qualitative and quantitative parameters, such as the choice of recombination mechanism, crossover and mutation probabilities, is also studied. These issues are critically analyzed considering seven discrete-time and a continuous-time benchmark nonlinear system as well as a practical case study of non-linear wave-force modeling. The results of this investigation demonstrate that MOEAs can be tailored to determine the correct structure of nonlinear systems. Further, it has been established through frequency domain analysis that it is possible to identify multiple valid discrete-time models for continuous-time systems. A rigorous statistical analysis of MOEAs via performance sweet spots in the parameter space convincingly demonstrates that these algorithms are robust over a wide range of control parameters.

A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the information about the subset cardinality (i.e., the number of features) as an additional learning dimension to effectively guide the search process. The efficacy of this approach has been demonstrated considering fourteen distinct classes of PQ events which conform to the IEEE Standard 1159. The search performance of the 2D learning approach has been compared to the other six well-known feature selection wrappers by considering two induction algorithms: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). Further, the robustness of the selected/reduced feature subsets has been investigated considering seven different levels of noise. The results of this investigation convincingly demonstrate that the proposed 2D learning can identify significantly better and robust feature subsets for PQ events.

The present study proposes a new Orthogonal Floating Search framework for structure selection of nonlinear systems by adapting the existing floating search algorithms for feature selection. The proposed framework integrates the concept of orthogonal space and consequent Error-Reduction-Ratio (ERR) metric with the existing floating search algorithms. On the basis of this framework, three well-known feature selection algorithms have been adapted which include the classical Sequential Forward Floating Search (SFFS), Improved sequential Forward Floating Search (IFFS) and Oscillating Search (OS). This framework retains the simplicity of classical Orthogonal Forward Regression with ERR (OFR-ERR) and eliminates the nesting effect associated with OFR-ERR. The performance of the proposed framework has been demonstrated considering several benchmark non-linear systems. The results show that most of the existing feature selection methods can easily be tailored to identify the correct system structure of nonlinear systems.

The present study applies a novel two-dimensional learning framework (2D-UPSO) based on particle swarms for structure selection of polynomial nonlinear auto-regressive with exogenous inputs (NARX) models. This learning approach explicitly incorporates the information about the cardinality (i.e., the number of terms) into the structure selection process. Initially, the effectiveness of the proposed approach was compared against the classical genetic algorithm (GA) based approach and it was demonstrated that the 2D-UPSO is superior. Further, since the performance of any meta-heuristic search algorithm is critically dependent on the choice of the fitness function, the efficacy of the proposed approach was investigated using two distinct information theoretic criteria such as Akaike and Bayesian information criterion. The robustness of this approach against various levels of measurement noise is also studied. Simulation results on various nonlinear systems demonstrate that the proposed algorithm could accurately determine the structure of the polynomial NARX model even under the influence of measurement noise.

The present study proposes a new structure selection approach for non-linear system identification based on Two-Dimensional particle swarms (2D-UPSO). The 2D learning framework essentially extends the learning dimension of the conventional particle swarms and explicitly incorporates the information about the cardinality, i.e., number of terms, into the search process. This property of the 2D-UPSO has been exploited to determine the correct structure of the non-linear systems. The efficacy of the proposed approach is demonstrated by considering several simulated benchmark nonlinear systems in discrete and in continuous domain. In addition, the proposed approach is applied to identify a parsimonious structure from practical non-linear wave-force data. The results of the comparative investigation with Genetic Algorithm (GA), Binary Particle Swarm Optimization (BPSO) and the classical Orthogonal Forward Regression (OFR) methods illustrate that the proposed 2D-UPSO could successfully detect the correct structure of the non-linear systems.

This paper proposes a new generalized two dimensional learning approach for particle swarm based feature selection. The core idea of the proposed approach is to include the information about the subset cardinality into the learning framework by extending the dimension of the velocity. The 2D-learning framework retains all the key features of the original PSO, despite the extra learning dimension. Most of the popular variants of PSO can easily be adapted into this 2D learning framework for feature selection problems. The efficacy of the proposed learning approach has been evaluated considering several benchmark data and two induction algorithms: Naive-Bayes and k-Nearest Neighbor. The results of the comparative investigation including the time-complexity analysis with GA, ACO and five other PSO variants illustrate that the proposed 2D learning approach gives feature subset with relatively smaller cardinality and better classification performance with shorter run times.