Conference Paper

User Modelling for Interactive Optimization Using Neural Network

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

User modelling is one of the prominent research fields in information retrieval systems. In this paper, we model user's preferences and search criteria using an NN (Neural Network) to solve a multiobjective optimization problem specific to environmental planning systems. We argue that some NP hard problems cannot be solved alone either by a human or by a computer. Human participation in automated search is one way of combining human intuition with algorithmic search to solve such problems. However, even humans have some limitations for participation in that they cannot participate in search completely because of human fatigue. To overcome this, in our approach, an NN tries to model the user's rating criteria and preferences to help the user in rating large set of designs. Although training an NN with limited data is not always feasible, there are many situations where a simple modelling technique (e.g., linear/quadratic mapping) works better if the learning data set is small. In this paper we attempt to get more accuracy of the NN by generating data using other linear/non-linear techniques that fills the gap created by lack of sufficient training data. Also, we provided the architectural design of an HPC based framework we have proposed and compared the performance of the NN with fuzzy logic and other linear/non-linear user modelling techniques for the environmental resources optimization problem.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... For example, participatory approaches in which problem formulations are constructed in collaboration with stakeholders have been advanced in a series of studies by Babbar-Sebens and Minsker (2008, Babbar-Sebens and Mukhopadhyay (2009), Piemonti et al. (2013), as well as Castelletti and Soncini-Sessa (2006). In addition, Singh et al. (2009Singh et al. ( , 2010 and Singh et al. (2013) present interactive optimization approaches that incorporate qualitative information into the problem formulation using stakeholder rankings of interim solutions. Similar ideas have been developed in Castelletti et al. (2010bCastelletti et al. ( , 2011 and "Problem Structuring Methods" can also help to implement traditional operations research approaches with diverse sets of stakeholders (Rosenhead, 1996). ...
... Keijzer et al., 2001;Levine et al., 1999;Wall, 1996); portable java code and jar files (e.g. Cingolani, 2009;Hadka, 2012;Meffert, 2012;Singh et al., 2013;White, 2012); toolboxes and packages written for python, R, perl, MatLab/Octave, and other scripted languages (e.g. Izzo, 2012;Kelley, 1999;Matott et al., 2011;Merelo Guervos et al., 2010;Regis and Shoemaker, 2005;Theussl, 2013;Vrugt et al., 2003;Vrugt and Robinson, 2007;Vrugt et al., 2008;Zlatanov, 2001); and macros and extensions to spreadsheet packages (e.g. ...
Article
The development and application of evolutionary algorithms (EAs) and other metaheuristics for the optimisation of water resources systems has been an active research field for over two decades. Research to date has emphasized algorithmic improvements and individual applications in specific areas (e.g. model calibration, water distribution systems, groundwater management, river-basin planning and management, etc.). However, there has been limited synthesis between shared problem traits, common EA challenges, and needed advances across major applications. This paper clarifies the current status and future research directions for better solving key water resources problems using EAs. Advances in understanding fitness landscape properties and their effects on algorithm performance are critical. Future EA-based applications to real-world problems require a fundamental shift of focus towards improving problem formulations, understanding general theoretic frameworks for problem decompositions, major advances in EA computational efficiency, and most importantly aiding real decision-making in complex, uncertain application contexts.
Article
Full-text available
Land and water are the two most vital natural resources of the world and these resources must be conserved and maintained carefully for environmental protection and ecological balance. Estimation of sediment yield is prerequisite for conservation and management of water resources and for many hydrological applications. Therefore, this study was undertaken for a small agricultural watershed, Kapgari having a drainage area of 973 ha for prediction of daily sediment yield. Artificial neural network (ANN) models were developed, to predict sediment yield on a daily basis for the watershed. A total of four ANN models were developed using rainfall and temperature data for predicting sediment yield for Kapgari watershed and its three sub-watersheds. Due to smaller data set availability a10-fold cross validation method was used for selecting the best performing models and to avoid neural network over-fitting during the training process. As a result models considering both rainfall and temperature as inputs performed better than those considering rainfall alone as input. Training and testing results of selected models show that models were predicting the daily sediment yield satisfactorily. Therefore these models can be used for estimating the sediment yield on a daily basis for Kapgari watershed and its sub-watersheds. KEY WORDS: Agricultural watershed, Sediment yield, ANN, 10-fold cross validation, Rainfall, Temperature. INTRODUCTION The hydrological process, such as rainfall-sediment yield is extremely complex, non-linear, dynamic, and fragmented process due spatial variability of catchment characteristics, geomorphology, duration of the rainfall and involvement of other physical process. The involvement of many often interrelated physiographic and climatic factors makes the rainfall-sediment yield process not only very complex to understand but also extremely difficult to simulate (Zang & Govindaraju, 2003). Hydrological modeling is the best way for satisfactory prediction of sediment yield. The last two decades have seen increasing popularity of artificial neural network based models (ANNs) for simulation of hydrological process. The ANN is one of the intelligent techniques which is flexible and robust and requires less variety of data. Extensive review on application of ANNs in hydrologic simulation and forecasting has been presented in ASCE (2000 a, b), Maier & Dandy (2000) or Dawson & Wilby (2001). Various types of ANNs have been applied for rainfall-sediment simulation (Cigizoglu 2004; Agrawal et al. 2005; Sarangi & Bhattacharya (2005) and Rai & Mathur (2008).
Article
Full-text available
This paper proposes a neural network (NN)-embedded genetic algorithm (GA) approach for solving inverse water quality modeling problems to overcome the computational bottleneck of inverse modeling by replacing a water quality model with an efficient NN functional evaluator. An existing one-step, NN-embedded GA approach is found incapable of solving an inverse water quality modeling problem because it tends to fail in guiding the global search process to converge toward the near optima. As a remedy, an adaptive NN-GA approach is proposed to achieve a gradual convergence toward the near optima through an iterative network learning method. The proposed approach is applied to a full-scale, numerical example, and the result shows that the adaptive NN-GA approach is capable of obtaining near-optimal solutions for the inverse problem of a complicated water quality model.
Article
Full-text available
Adaptive Hypermedia systems are becoming more important in our everyday activities and users are expecting more intelligent services from them. The key element of a generic adaptive hypermedia system is the user model. Traditional machine learning techniques used to create user models are usually too rigid to capture the inherent uncertainty of human behavior. In this context, soft computing techniques can be used to handle and process human uncertainty and to simulate human decision-making. This paper examines how soft computing techniques, including fuzzy logic, neural networks, genetic algorithms, fuzzy clustering and neuro-fuzzy systems, have been used, alone or in combination with other machine learning techniques, for user modeling from 1999 to 2004. For each technique, its main applications, limitations and future directions for user modeling are presented. The paper also presents guidelines that show which soft computing techniques should be used according to the task implemented by the application.
Article
Full-text available
The limitations of traditional knowledge representation methods for modeling complex human behaviour led to the investigation of statistical models. Predictive statistical models enable the anticipation of certain aspects of human behaviour, such as goals, actions and preferences. In this paper, we motivate the development of these models in the context of the user modeling enterprise. We then review the two main approaches to predictive statistical modeling, content-based and collaborative, and discuss the main techniques used to develop predictive statistical models. We also consider the evaluation requirements of these models in the user modeling context, and propose topics for future research.
Article
Full-text available
New methods are needed for accessing very large information services. This paper proposes the use of a user model neural network to allow better access to a news service. The network is constructed on the basis of articles read, and articles marked as rejected. It adapts overtime to better represent the user's interests andrank the articles supplied by the news service. Using an augmented keyword search we can also search for articles using keywords in conjunction with the user model neural network. Trials of the system in a USENET news environment show promising results for the use of this approach in information retrieval. 1 A Personal News Service Based.. 1. Introduction In this paper we introduce an approach to a personal news service based on the use of a user model neural network. The approach makes careful use of computation to enhance access to a large information store. As far as possible we share the computational cost of processing amongst a large group of users, leading...
Conference Paper
Learning Automata (LA) and Genetic Algorithms (GA) have been used for a long time to solve problems in different domains. However, there is criticism that LA has slow rate of convergence and both LA and GA have the problem of getting stuck in local optima. In this paper we tried to solve the multi-objective problems using LA in batch mode to make the learning faster and more accurate. We used Decentralized pursuit learning automaton as LA and NSGA2 as GA. Problems where evaluation of fitness function is a bottleneck like SWAT, evaluation of individuals in parallel can give considerable speed-up. In the multi-objective LA, different weight pairs and individual designs can be evaluated independently. So we created their parallel versions to make them practically faster in learning and computations and extended the parallelization concept with the batch mode learning.
Article
In most practical situations involving reliability optimization, there are several mutually conflicting goals such as maximizing the system reliability and minimizing the cost, weight and volume. This paper develops an effective multiobjective optimization method, the Intelligent Interactive Multiobjective Optimization Method (IIMOM). In IIMOM, the general concept of the model parameter vector is proposed. From a practical point of view, a designer's preference structure model is built using Artificial Neural Networks (ANNs) with the model parameter vector as the input and the preference information articulated by the designer over representative samples from the Pareto frontier as the desired output. Then with the ANN model of the designer's preference structure as the objective, an optimization problem is solved to search for improved solutions and guide the interactive optimization process intelligently. IIMOM is applied to the reliability optimization problem of a multi-stage mixed system with five different value functions simulating the designer in the solution evaluation process. The results illustrate that IIMOM is effective in capturing different kinds of preference structures of the designer, and it provides a complete and effective solution for medium-and small-scale multiobjective optimization problems.
Conference Paper
A neural network approach to user modeling is proposed in the context of information retrieval. User level of expertise and the inquiry interests underlying the goals are considered as two major factors affecting information provision. A prototype system, UM-net, is presented for modeling user domain experiences and the inquiry interests and tailoring the descriptions about software packages provided to a user
Article
This paper proposes the application of evolutionary fuzzy models (EFMs) for suspended sediment concentration estimation. The EFMs are improved by the combination of two methods, fuzzy logic and differential evolution. The accuracy of EFMs is compared with those of the adaptive neuro-fuzzy, neural networks and rating curve models. The daily streamflow and suspended sediment data belonging to two stations, Quebrada Blanca Station and Rio Valenciano Station, operated by the US Geological Survey (USGS) are used as case studies. The mean square errors and determination coefficient statistics are used for evaluating the accuracy of the models. Based on the comparison of the results, it is found that the EFMs give better estimates than the other techniques.
Conference Paper
Scheduling, routing, and layout tasks are examples of hard operations-research problems that have broad application in industry. Typical algorithms for these problems combine some form of gradient descent to find local minima with some strategy for escaping nonoptimal local minima and traversing the search space. Our idea is to divide these two subtasks cleanly between human and computer: in our paradigm of human-guided sample search the computer is responsible only for finding local minima using a simple search method; using information visualization, the human identifies promising regions of the search space for the computer to explore, and also intervenes to help it escape nonoptimal local minima. This is a specific example of a more general strategy, that of combining heuristic-search and information-visualization techniques in an interactive system. We are applying our approach to the problem of capacitated vehicle routing with time windows (CVRTW). We describe the design and implementation of our initial prototype, some preliminary results, and our plans for future work.
Article
Design of optimal plans for environmental planning and management applications should ideally consider the multiple quantitative and qualitative criteria relevant to the problem. For example, in ground water monitoring design problems, qualitative criteria such as acceptable spatial extent and shape of the contaminant plume predicted from the monitored locations can be equally important as the typical quantitative criteria such as economic costs and contaminant prediction accuracy. Incorporation of qualitative criteria in the problem-solving process is typically done in one of two ways: (a) quantifying approximate representations of the qualitative criteria, which are then used as additional criteria during the optimization process, or (b) post-optimization analysis of designs by experts to evaluate the overall performance of the optimized designs with respect to the qualitative criteria. These approaches, however, may not adequately represent all of the relevant qualitative information that affect a human expert involved in design (e.g. engineers, stakeholders, regulators, etc.), and do not necessarily incorporate the effect of the expert's own learning process on the suitability of the final design. The Interactive Genetic Algorithm with Mixed Initiative Interaction (IGAMII) is a novel approach that addresses these limitations by using a collaborative human–computer search strategy to assist users in designing optimized solutions to their applications, while also learning about their problem. The algorithm adaptively learns from the expert's feedback, and explores multiple designs that meet her/his criteria using both the human expert and a simulated model of the expert's responses in a collaborative fashion. The algorithm provides an introspection-based learning framework for the human expert and uses the human's subjective confidence measures to adjust the optimization search process to the transient learning process of the user. This paper presents the design and testing of this computational framework, and the benefits of using this approach for solving groundwater monitoring design problems.
Conference Paper
The authors have been working on the modeling and simulation of environmental systems. We have developed an object oriented approach mainly based on discrete events and object oriented simulation. In order to validate our approach, we applied it to the simulation of watershed behavior; the results were quite satisfactory. However, a more accurate rainfall/runoff model is necessary in order to take into account hourly flow variations, particularly for flood prediction. As our first approach was not efficient enough to do this, we chose to define a new one based on artificial neural networks (ANNs) and geographic information systems (GIS) paradigms
Article
Multi-objective evolutionary algorithms (MOEAs) that use non-dominated sorting and sharing have been criticized mainly for: (1) their O(MN<sup>3</sup>) computational complexity (where M is the number of objectives and N is the population size); (2) their non-elitism approach; and (3) the need to specify a sharing parameter. In this paper, we suggest a non-dominated sorting-based MOEA, called NSGA-II (Non-dominated Sorting Genetic Algorithm II), which alleviates all of the above three difficulties. Specifically, a fast non-dominated sorting approach with O(MN<sup>2</sup>) computational complexity is presented. Also, a selection operator is presented that creates a mating pool by combining the parent and offspring populations and selecting the best N solutions (with respect to fitness and spread). Simulation results on difficult test problems show that NSGA-II is able, for most problems, to find a much better spread of solutions and better convergence near the true Pareto-optimal front compared to the Pareto-archived evolution strategy and the strength-Pareto evolutionary algorithm - two other elitist MOEAs that pay special attention to creating a diverse Pareto-optimal front. Moreover, we modify the definition of dominance in order to solve constrained multi-objective problems efficiently. Simulation results of the constrained NSGA-II on a number of test problems, including a five-objective, seven-constraint nonlinear problem, are compared with another constrained multi-objective optimizer, and the much better performance of NSGA-II is observed