Whye Loon Tung

GenSoFNN: a generic self-organizing fuzzy neural network

Existing neural fuzzy (neuro-fuzzy) networks proposed in the literature can be broadly classified into two groups. The first group is essentially fuzzy systems with self-tuning capabilities and requires an initial rule base to be specified prior to training. The second group of neural fuzzy networks, on the other hand, is able to automatically formulate the fuzzy rules from the numerical training data. No initial rule base needs to be specified prior to training. A cluster analysis is first performed on the training data and the fuzzy rules are subsequently derived through the proper connections of these computed clusters. However, most existing neural fuzzy systems (whether they belong to the first or second group) encountered one or more of the following major problems. They are (1) inconsistent rule-base; (2) heuristically defined node operations; (3) susceptibility to noisy training data and the stability-plasticity dilemma; and (4) needs for prior knowledge such as the number of clusters to be computed. Hence, a novel neural fuzzy system that is immune to the above-mentioned deficiencies is proposed in this paper. This new neural fuzzy system is named the generic self-organizing fuzzy neural network (GenSoFNN). The GenSoFNN network has strong noise tolerance capability by employing a new clustering technique known as discrete incremental clustering (DIC). The fuzzy rule base of the GenSoFNN network is consistent and compact as GenSoFNN has built-in mechanisms to identify and prune redundant and/or obsolete rules. Extensive simulations were conducted using the proposed GenSoFNN network and its performance is encouraging when benchmarked against other neural and neural fuzzy systems.

FCMAC-Yager: A Novel Yager-Inference-Scheme-Based Fuzzy CMAC

The cerebellum is a brain region important for a number of motor and cognitive functions. It is able to generate error correction signals to drive learning and for the acquisition of memory skills. The cerebellar model articulation controller (CMAC) is a neural network inspired by the neurophysiologic theory of the cerebellum and is recognized for its localized generalization and rapid algorithmic computation capabilities. The main deficiencies in the basic CMAC structure are: 1) it is difficult to interpret the internal operations of the CMAC network and 2) the resolution (quantization) problem arising from the partitioning of the input training space. These limitations lead to the synthesis of a fuzzy quantization technique and the mapping of a fuzzy inference scheme onto the CMAC structure. The discrete incremental clustering (DIC) technique is employed to alleviate the quantization problem in the CMAC structure, resulting in the fuzzy CMAC (FCMAC) network. The Yager inference scheme (Yager), which possesses firm fuzzy logic foundation and maps closely to the logical implication operations in the classical (binary) logic framework, is subsequently mapped onto the FCMAC structure. This results in a novel fuzzy neural architecture known as the fuzzy cerebellar model articulation controller-Yager (FCMAC-Yager) system. The proposed FCMAC-Yager network exhibits learning and memory capabilities of the cerebellum through the CMAC structure while emulating the human way of reasoning through the Yager. The new FCMAC-Yager network employs a two-phase training algorithm consisting of structural learning based on the DIC technique and parameter learning using hebbian learning (associative long-term potentiation). The proposed FCMAC-Yager architecture is evaluated using an extensive suite of real-life applications such as highway traffic-trend modeling and prediction and performing as an early warning system for bank failure classification and medical diagnosis of breast cancer. The experimental results are encouraging

eFSM—A Novel Online Neural-Fuzzy Semantic Memory Model

Fuzzy rule-based systems (FRBSs) have been successfully applied to many areas. However, traditional fuzzy systems are often manually crafted, and their rule bases that represent the acquired knowledge are static and cannot be trained to improve the modeling performance. This subsequently leads to intensive research on the autonomous construction and tuning of a fuzzy system directly from the observed training data to address the knowledge acquisition bottleneck, resulting in well-established hybrids such as neural-fuzzy systems (NFSs) and genetic fuzzy systems (GFSs). However, the complex and dynamic nature of real-world problems demands that fuzzy rule-based systems and models be able to adapt their parameters and ultimately evolve their rule bases to address the nonstationary (time-varying) characteristics of their operating environments. Recently, considerable research efforts have been directed to the study of evolving Tagaki-Sugeno (T-S)-type NFSs based on the concept of incremental learning. In contrast, there are very few incremental learning Mamdani-type NFSs reported in the literature. Hence, this paper presents the evolving neural-fuzzy semantic memory (eFSM) model, a neural-fuzzy Mamdani architecture with a data-driven progressively adaptive structure (i.e., rule base) based on incremental learning. Issues related to the incremental learning of the eFSM rule base are carefully investigated, and a novel parameter learning approach is proposed for the tuning of the fuzzy set parameters in eFSM. The proposed eFSM model elicits highly interpretable semantic knowledge in the form of Mamdani-type if-then fuzzy rules from low-level numeric training data. These Mamdani fuzzy rules define the computing structure of eFSM and are incrementally learned with the arrival of each training data sample. New rules are constructed from the emergence of novel training data and obsolete fuzzy rules that no longer describe the recently observed data trends are pruned. This enables eFSM to maintain a current and compact set of Mamdani-type if-then fuzzy rules that collectively generalizes and describes the salient associative mappings between the inputs and outputs of the underlying process being modeled. The learning and modeling performances of the proposed eFSM are evaluated using several benchmark applications and the results are encouraging.

Financial volatility trading using a self-organising neural-fuzzy semantic network and option straddle-based approach

Abstract Financial volatility refers to the intensity of the fluctuations in the expected return on an investment or the pricing of a financial asset due to market uncertainties. Hence, volatility modeling and forecasting is imperative to financial market investors, as such projections allow the investors to adjust their trading strategies in anticipation of the impending financial market movements. Following this, financial volatility trading is the capitalization of the uncertainties of the financial markets to realize investment profits in times of rising, falling and side-way market conditions. In this paper, an intelligent straddle trading system (framework) that consists of a volatility projection module (VPM) and a trade decision module (TDM) is proposed for financial volatility trading via the buying and selling of option straddles to help a human trader capitalizes on the underlying uncertainties of the Hong Kong stock market. Three different measures, namely: (1) the historical volatility (HV), (2) implied volatility (IV) and (3) model-based volatility (MV) of the Hang Seng Index (HSI) are employed to quantify the implicit volatility of the Hong Kong stock market. The TDM of the proposed straddle trading system combines the respective volatility measures with the well-established moving-averages convergence/divergence (MACD) principle to recommend trading actions to a human trader dealing in HSI straddles. However, the inherent limitation of the MACD trading rule is that it generates time-delayed trading signals due to the use of moving averages, which are essentially lagging trend indicators. This drawback is intuitively addressed in the proposed straddle trading system by applying the VPM to compute future projections of the volatility measures of the HSI prior to the activation of the TDM. The VPM is realized by a self-organising neural-fuzzy semantic network named the evolving fuzzy semantic memory (eFSM) model. As compared to existing statistical and computational intelligence based modeling techniques currently employed for financial volatility modeling and forecasting, eFSM possesses several desirable attributes such as: (1) an evolvable knowledge base to continuously address the non-stationary characteristics of the Hong Kong stock market; (2) highly formalized human-like information computations; and (3) a transparent structure that can be interpreted via a set of linguistic IF–THEN semantic fuzzy rules. These qualities provide added credence to the computed HSI volatility projections. The volatility modeling and forecasting performances of the eFSM, when benchmarked to several established modeling techniques, as well as the observed trading returns of the proposed straddle trading system, are encouraging.

A mamdani-takagi-sugeno based linguistic neural-fuzzy inference system for improved interpretability-accuracy representation

Existing fuzzy and neural-fuzzy systems in the literature can be classified into three main categories, i.e. Mam-dani, Takagi-Sugeno (T-S) or Tsukamoto systems based on their implemented fuzzy rule structures. Furthermore, depending on the intended modeling objective, there are two main approaches to fuzzy and neural-fuzzy modeling; namely: linguistic fuzzy modeling (LFM) and precise fuzzy modeling (PFM). In general, Mamdani fuzzy models are more interpretive but less accurate than T-S fuzzy models, and improving the output accuracy of Mamdani fuzzy models usually implies using a larger rule-base with increased complexity and reduced interpretability. This paper presents a linguistic neural-fuzzy architecture that combines the explanatory trait of Mamdani-typed fuzzy models with the output accuracy of T-S fuzzy systems in a hybrid approach referred to as Mamdani-Tagaki-Sugneo (MTS) fuzzy modeling. The resultant network is named the MTS linguistic neural-fuzzy inference system (MTS-LiNFIS). The improved trade-off between the interpretability and accuracy demands of Mamdani-based fuzzy approximation is demonstrated through the evaluation of the learning and modeling performances of MTS-LiNFIS using a simple benchmark application.

A personalized approach to insulin regulation using brain-inspired neural sematic memory in diabetic glucose control

Diabetes mellitus is a chronic disease with a high incidence rate worldwide. In Type-1 diabetes, the failure to produce sufficient pancreatic insulin leads to an uncontrolled increase in blood glucose. Prolong elevated blood glucose level poses significant risks of acute and chronic medical complications. Human assisted insulin injection, either through a fixed regime under the close supervision of a physician or through compartmental model schedules, is fundamentally an open-loop control system. Currently, a large amount of research has been conducted to treat Type-1 diabetes using a closed-loop insulin delivery system. The objective of this work is to investigate the use of a brain-inspired neural fuzzy system as a controller to deliver insulin in a closed-loop system for the treatment of Type-1 diabetes. In this paper, the Pseudo-Outer Product based Fuzzy Neural Network using the Yager rule of inference (i.e. POP-Yager) is employed as an intelligent controller to dispense the appropriate amount of insulin in the presence of varying meal disturbances to achieve normoglycemia for a simulated Type-1 diabetic patient.

GenSo-OPATS: a brain-inspired dynamically evolving option pricing model and arbitrage trading system

Obtaining the theoretical fair value of an option based on the factors affecting its price is a process called option pricing and commonly known approaches are the Black-Scholes formula and the binomial pricing model. However, these parametric models are generally dependent on the assumptions of continuous-time finance theory and presumed complex and rigid statistical formulations. Nonparametric and computational methods of option pricing, on the other hand, are able to accurately model the pricing formula from historical data but suffer from poor interpretability due to their opaque architectures. Generally, there is no guarantee that the prices derived from these model-free approaches conform to rational pricing. This paper proposes a novel brain-inspired nonparametric model for pricing American-style option on currency futures based on a dynamically evolving semantic memory model named GenSoFNN-TVR(S). Logical reasoning rules governing the pricing decisions can be extracted from the proposed model. Subsequently, the GenSoFNN-TVR(S) based option pricing model is implemented in a mis-priced option arbitrage trading system named GenSo-OPATS, and simulation results demonstrated an encouraging rate of return on investment.

A Hippocampal-inspired Self-Organising Learning Memory Model with Analogical Reasoning for Decision Support

Decision-making is innately human-centered; and a decision support system seeks to provide a systematic and consistent way to information processing by integrating the domain knowledge with a rational reasoning capability to support the human decision process. Traditionally, decision support systems are based on data-mining solutions, statistical models and conventional AI techniques. These systems have several deficiencies such as lacking in ability to explain the computed decisions (black-box nature) and are not dynamically adaptive to handle the emergence of new information. This paper presents a brain-inspired learning memory model with analogical reasoning as a tool to facilitate human decisionmaking. The proposed model is named GenSoFNN-AR and constitutes a neurocognitive approach to the science of knowledge discovery to support the human decision process. The GenSoFNN-AR model is subsequently evaluated with a bank failure classification and analysis problem using a set of historical financial records. The results are encouraging.

A novelty detection machine and its application to bank failure prediction

Novelty detection has been well-studied for many years and has found a wide range of applications, but correctly identifying the outliers is still a hard problem because of the diverse variation and the small quantity of such outliers. We address the problem using several distinct characteristics of the outliers and the normal patterns. First, normal patterns are usually grouped together, forming clusters in the high density regions of the data space. Second, outliers are characteristically very different from the normal patterns, and hence tend to be located far away from the normal patterns in the data space. Third, the number of outliers is generally very small in a given dataset. Based on these observations, we can envisage that the appropriate decision boundary segregating the outliers and the normal patterns usually lies in some low density regions of the data space. This is referred to as cluster assumption. The resultant optimization problem to learn the decision function can be solved using the mixed integer programming approach. Following that, we present a cutting plane algorithm together with a multiple kernel learning technique to solve the convex relaxation of the optimization problem. Specifically, we make use of the scarcity of the outliers to find a violating solution to the cutting plane algorithm. Experimental results with several benchmark datasets show that our proposed novelty detection method outperforms existing hyperplane and density estimation-based novelty detection techniques. We subsequently apply our method to the prediction of banking failures to identify potential bank failures or high risk banks through the traits of financial distress.

Brain-inspired evolving neuro-fuzzy system for financial forecasting and trading of the s&p500 index

An interday financial trading system with a predictive model empowered by a novel brain-inspired evolving Mamdani-Takagi-Sugeno Neural-Fuzzy Inference System (eMTSFIS) is proposed in this paper. The eMTSFIS predictive model possesses synaptic mechanisms and information processing capabilities of the human hippocampus, resulting in a more robust and adaptive forecasting model as compared to existing econometric and neural-fuzzy techniques. The trading strategy of the proposed system is based on the moving-averages-convergence/divergence (MACD) principle to generate buy-sell trading signals. By introducing forecasting capabilities to the computation of the MACD trend signals, the lagging nature of the MACD trading rule is addressed. Experimental results based on the S&P500 Index confirmed that eMTSFIS is able to provide highly accurate predictions and the resultant system is able to identify timely trading opportunities while avoiding unnecessary trading transactions. These attributes enable the eMTSFIS-based trading system to yield higher multiplicative returns for an investor.