Discovering Interesting Patterns for Investment Decision Making with GLOWER ☹—A Genetic Learner Overlaid with Entropy Reduction

Prediction in financial domains is notoriously difficult for a number of reasons. First, theories tend to be weak or non-existent, which makes problem formulation open ended by forcing us to consider a large number of independent variables and thereby increasing the dimensionality of the search space. Second, the weak relationships among variables tend to be nonlinear, and may hold only in limited areas of the search space. Third, in financial practice, where analysts conduct extensive manual analysis of historically well performing indicators, a key is to find the hidden interactions among variables that perform well in combination. Unfortunately, these are exactly the patterns that the greedy search biases incorporated by many standard rule learning algorithms will miss. In this paper, we describe and evaluate several variations of a new genetic learning algorithm (GLOWER) on a variety of data sets. The design of GLOWER has been motivated by financial prediction problems, but incorporates successful ideas from tree induction and rule learning. We examine the performance of several GLOWER variants on two UCI data sets as well as on a standard financial prediction problem (S&P500 stock returns), using the results to identify one of the better variants for further comparisons. We introduce a new (to KDD) financial prediction problem (predicting positive and negative earnings surprises), and experiment with GLOWER, contrasting it with tree- and rule-induction approaches. Our results are encouraging, showing that GLOWER has the ability to uncover effective patterns for difficult problems that have weak structure and significant nonlinearities.     

A Software Fault Tree Approach to Requirements Analysis of an Intrusion Detection System

Requirements analysis for an intrusion detection system (IDS) involves deriving requirements for the IDS from analysis of the intrusion domain. When the IDS is, as here, a collection of mobile agents that detect, classify, and correlate system and network activities, the derived requirements include what activities the agent software should monitor, what intrusion characteristics the agents should correlate, where the IDS agents should be placed to feasibly detect the intrusions, and what countermeasures the software should initiate. This paper describes the use of software fault trees for requirements identification and analysis in an IDS. Intrusions are divided into seven stages (following Ruiu), and a fault subtree is developed to model each of the seven stages (reconnaissance, penetration, etc.). Two examples are provided. This approach was found to support requirements evolution (as new intrusions were identified), incremental development of the IDS, and prioritisation of countermeasures. Correspondence and offprint requests to: G. Helmer, Department of Computer Science, 226 Atanasoff Hall, Iowa State University, Ames, Iowa 50011, USA. Email: ghelmer@cs.iastate.edu     

Fuzzy Production Planning and its Application to Decision Making

This paper presents new methods for solving a production-planning problem. First the modified s-curve membership function as a methodology is constructed. Then fuzzy production planning problems with vagueness parameters alpha and fuzzy objective coefficients, fuzzy technical coefficients and fuzzy resource variables are outlined. The objective of this paper is to find a satisfactory solution for optimal profit in which vagueness is playing major factor in selecting the solution. Finally a practical application of decision-making in production planning is illustrated.     

Fuzzy optimization of units products in mix-product selection problem using fuzzy linear programming approach

In this paper, the modified S-curve membership function methodology is used in a real life industrial problem of mix product selection. This problem occurs in the production planning management where by a decision maker plays important role in making decision in an uncertain environment. As analysts, we try to find a good enough solution for the decision maker to make a final decision. An industrial application of fuzzy linear programming (FLP) through the S-curve membership function has been investigated using a set of real life data collected from a Chocolate Manufacturing Company. The problem of fuzzy product mix selection has been defined. The objective of this paper is to find an optimal units of products with higher level of satisfaction with vagueness as a key factor. Since there are several decisions that were to be taken, a table for optimal units of products respect to vagueness and degree of satisfaction has been defined to identify the solution with higher level of units of products and with a higher degree of satisfaction. The fuzzy outcome shows that higher units of products need not lead to higher degree of satisfaction. The findings of this work indicates that the optimal decision is depend on vagueness factor in the fuzzy system of mix product selection problem. Further more the high level of units of products obtained when the vagueness is low.     

Influence of support on surface basicity and catalytic activity in oxidative coupling of methane of Li–MgO deposited on different commercial catalyst carriers

Deposition of Li–MgO catalyst on commonly used supports (containing SiO₂, Al₂O₃, SiC, ZrO₂, HfO₂, etc.) causes a drastic reduction in the catalytic activity/selectivity for the oxidative methane coupling reaction and also in both the total and strong surface basicity. The decrease in the catalytic activity/selectivity and basicity is attributed to strong chemical interactions between the catalyst and support which occur during the high temperature (750°C) calcination/pretreatment of the catalyst. The chemical interactions result in catalytically less active binary and ternary metal oxides containing Li and/or Mg, thus deactivating the Li–MgO catalyst by consuming its active components. © 1998 SCI     

Surface Properties of CaO (or BaO)–La2O3–MgO Catalysts and Their Performance in Oxidative Coupling of Methane

CaO–La₂O₃–MgO and BaO–La₂O₃–MgO catalysts with different compositions have been studied for their bulk and surface properties (viz. crystal phases, surface area, acidity/acid strength distribution, basicity/base strength distribution, etc.) and catalytic activity/selectivity in the oxidative coupling of methane (OCM) at different processing conditions (reaction temperature, 700–850°C; CH₄/O₂ ratio in feed, 3·0, 4·0 and 8·0 and GHSV, 102000 and 204000 cm³ g⁻¹ h⁻¹). The surface acidity and strong basicity of La₂O₃–MgO are found to be increased due to the addition of a third component (CaO or BaO), depending upon its concentration in the catalyst. The addition of CaO or BaO to La₂O₃–MgO OCM catalyst causes a significant improvement in its performance. Both the CaO- and BaO-containing catalysts show a high activity and selectivity at 800°C, whereas, the activity and selectivity of BaO-containing catalysts at 700°C is lower than that of CaO-containing catalysts. © 1997 SCI.     

Hybrid neuro-swarm optimization approach for design of distributed generation power systems

The global energy sector faces major challenges in providing sufficient energy to the worlds ever-increasing energy demand. Options to produce greener, cost effective, and reliable source of alternative energy need to be explored and exploited. One of the major advances in the development of this sort of power source was done by integrating (or hybridizing) multiple different alternative energy sources (e.g., wind turbine generators, photovoltaic cell panels, and fuel-fired generators, equipped with storage batteries) to form a distributed generation (DG) power system. However, even with DG power systems, cost effectiveness, reliability, and pollutant emissions are still major issues that need to be resolved. The model development and optimization of the DG power system were carried out successfully in the previous work using particle swarm optimization (PSO). The goal was to minimize cost, maximize reliability, and minimize emissions (multi-objective function) subject to the requirements of the power balance and design constraints. In this work, the optimization was performed further using Hopfield neural networks (HNN), PSO, and HNN-PSO techniques. Comparative studies and analysis were then carried out on the optimized results.     

Ferroelectric lead iron-chromium-nickel niobate films

Abstract

The fabrication of ferroelectric films of modified lead iron niobate by a multiple magnetron sputtering technique with a subsequent rapid thermal annealing at 800°C for 5 seconds is reported. Since the magnetic properties of pure iron preclude its use in magnetron sputtering, a non-magnetic stainless steel was used as one of the target materials resulting in a ferroelectric of composition Pb[(Fe_0.7Cr_0.2Ni_0.1)_0.5Nb_0.5]O₃. The reaction sequence involved in the formation of the ferroelectric perovskite phase has been identified. The films exhibit unsaturated ferroelectric hysteresis loops with a remanent polarization of 15 μC/cm² and a coercive field of 100 kV/cm. The room temperature dielectric constant and dielectric loss at 1 kHz were 640 and 0.1, respectively. The dielectric constant showed a dielectric anomaly as a function of temperature in the form of a broad maximum around 90°C confirming the ferro-para electric phase transition. The films were highly insulating with a room temperature conductivity of ≈1 X^?12 Ω^?1 cm^?1, and an activation energy of 0.8 eV.     

Integrating Equation of Gradually Varied Flow

This paper presents an improvement in the direct method originally proposed by Chow for integrating the equation of gradually varied flow in prismatic channels. The hydraulic parameters assumed to be constants at all depths by Chow are introduced in the integration as variable parameters. The differential equation of gradually varied flow is integrated, considering the effect of variable parameters. The results obtained by this improved method compare well with the results of the numerical method. The advantage of this method over the existing method is that acceptable accuracy is obtained in only one step for a wide range of cases.