Showing papers in "Applied Artificial Intelligence in 2013"
TL;DR: An agent-based dialog simulation technique for learning new dialog strategies and evaluating conversational agents is presented and it is shown that the conversational agent reduces the time needed to complete the dialogs and improve their quality, thereby allowing the Conversational agent to tackle new situations and generate new coherent answers for the situations already present in an initial model.
Abstract: During recent years, conversational agents have become a solution to provide straightforward and more natural ways of retrieving information in the digital domain In this article, we present an agent-based dialog simulation technique for learning new dialog strategies and evaluating conversational agents Using this technique, the effort necessary to acquire data required to train the dialog model and then explore new dialog strategies is considerably reduced A set of measures has also been defined to evaluate the dialog strategy that is automatically learned and to compare different dialog corpora We have applied this technique to explore the space of possible dialog strategies and evaluate the dialogs acquired for a conversational agent that collects monitored data from patients suffering from diabetes The results of the comparison of these measures for an initial corpus and a corpus acquired using the dialog simulation technique show that the conversational agent reduces the time needed to complete the dialogs and improve their quality, thereby allowing the conversational agent to tackle new situations and generate new coherent answers for the situations already present in an initial model
66 citations
TL;DR: Two-class and one-class support vector machines (SVM) for detection of fraudulent credit card transactions are presented and the performance of binary classifiers using balanced and imbalanced datasets with one- class SVM classifiers are described and compared.
Abstract: This article presents two-class and one-class support vector machines SVM for detection of fraudulent credit card transactions. One-class SVM classification with different kernels is considered for a dataset of fraudulent credit card transactions treating the fraud transactions as outliers. The effectiveness of the two-class C-Support Vector Classification C-SVC and ν-Support Vector Machines with different kernels are also presented on a fraudulent credit card transactions dataset. We describe and compare the performance of binary classifiers using balanced and imbalanced datasets with one-class SVM classifiers. The results of these methods are demonstrated on a credit card fraud dataset to show the superiority of one-class SVM for the anomaly detection problem.
62 citations
TL;DR: A methodology to combine sensor reports in fuzzy environments based on Dempster–Shafer evidence theory is proposed and the basic probability assignment function is constructed by means of member functions.
Abstract: In multisensor systems, complementary observations from different sensors need to be combined with each other. Due to the uncertainty, sensor reports can be represented by fuzzy sets in order to efficiently deal with signal processing. In this article, a methodology to combine sensor reports in fuzzy environments based on Dempster–Shafer evidence theory is proposed. The basic probability assignment function is constructed by means of member functions. The numerical example on object recognition of a robot arm is shown to illustrate the efficiency of the presented approach.
45 citations
TL;DR: To analyze current vision-based systems from a soccer video semantic point of view such as video summarization, features analysis, and provision of augmented information, computer vision methodologies are analyzed along with their strengths and weaknesses.
Abstract: The purpose of this article is to analyze current vision-based systems from a soccer video semantic point of view such as video summarization, features analysis, and provision of augmented information. Currently, computer vision techniques are applicable in a challenging soccer context. Scene interpretation is performed based on the complexity of the semantic. For each area of vision-based systems, computer vision methodologies are analyzed along with their strengths and weaknesses. We have also investigated whether the existing approaches are equally applicable for real-time soccer video semantic analysis.
44 citations
TL;DR: A combination of support vector machine (SVM) and k-nearest neighbor (k-NN) to monitor rotational machines using vibrational data because the system is used as triage for human analysis and a very low false negative rate is more important than high accuracy.
Abstract: This article presents a combination of support vector machine SVM and k-nearest neighbor k-NN to monitor rotational machines using vibrational data. The system is used as triage for human analysis and, thus, a very low false negative rate is more important than high accuracy. Data are classified using a standard SVM, but for data within the SVM margin, where misclassifications are more like, a k-NN is used to reduce the false negative rate. Using data from a month of operations of a predictive maintenance company, the system achieved a zero false negative rate and accuracy ranging from 75% to 84% for different machine types such as induction motors, gears, and rolling-element bearings.
33 citations
TL;DR: The use of the J48 algorithm for fault diagnosis through discrete wavelet features extracted from vibration signals of good and faulty conditions of the components of a centrifugal pump is presented.
Abstract: Monoblock centrifugal pumps play an important role in a variety of engineering applications such as in the food industry, in wastewater treatment plants, in agriculture, in the oil and gas industry, in the paper and pulp industry, and others. Condition monitoring of the various mechanical components of centrifugal pumps becomes essential for increasing productivity and reducing the number of breakdowns. Vibration-based continuous monitoring and analysis using machine learning approaches are gaining momentum. Particularly, artificial neural networks and fuzzy logic have been employed for continuous monitoring and fault diagnosis. This article presents the use of the J48 algorithm for fault diagnosis through discrete wavelet features extracted from vibration signals of good and faulty conditions of the components of a centrifugal pump. The classification accuracies of different discrete wavelet families were calculated and compared in order to find the best wavelet for the fault diagnosis of the centrifugal pump.
30 citations
TL;DR: This research work presents new position update architecture (NPUA) which consists of various artificial intelligence neural networks (AINN) that integrate both GPS and INS to overcome the drawbacks of the Kalman filter.
Abstract: An aircraft system mainly relies on a Global Positioning System GPS to provide accurate position values consistently. However, GPS receivers may encounter frequent GPS absence because of ephemeric error, satellite clock error, multipath error, and signal jamming. To overcome these drawbacks, generally a GPS is integrated with an Inertial Navigation System INS mounted inside the vehicle to provide a reliable navigation solution. INS and GPS are commonly integrated using a Kalman filter KF to provide a robust navigation solution. In the KF approach, the error models of both INS and GPS are required; this leads to the complexity of the system. This research work presents new position update architecture NPUA which consists of various artificial intelligence neural networks AINN that integrate both GPS and INS to overcome the drawbacks of the Kalman filter. The various AINNs that include both static and dynamic networks described for the system are radial basis function neural network RBFNN, backpropagation neural network BPN, forward-only counter propagation neural network FCPN, full counter propagation neural network Full CPN, adaptive resonance theory-counter propagation neural network ART-CPN, constructive neural network CNN, higher-order neural networks HONN, and input-delayed neural networks IDNN to predict the INS position error during GPS absence, resulting in different performances. The performances of the different AINNs are analyzed in terms of root mean square error RMSE, performance index PI, number of epochs, and execution time ET.
26 citations
TL;DR: This study used an embedded approach in feature selection in which the Chi-square (CHI) feature selector is a filter step and the less discriminative features are discarded.
Abstract: In text classification based on a vector space model, the high dimension of the feature may pose some problems. These problems occur not only for computational reasons, but also because of overfitting. Feature selection is an important preprocessing step used for text classification applications to reduce the vector space size, control the computational time, and maintain or improve performance. In this study, we used an embedded approach in feature selection in which the Chi-square CHI feature selector is a filter step. In this step, the less discriminative features are discarded. In the wrapper step, a novel algorithm is proposed based on the combination of the fast global search ability of the genetic algorithm GA and the positive feedback mechanism of ant colony optimization ACO. In order to validate our approach, we carried out a series of experiments on Reuters-21578 corpus, and we compare the achieved results with some other well-known techniques. The evaluation results are such that our method obtained a better performance compared with the other methods in the majority of cases.
25 citations
TL;DR: A modified distance of the DTW algorithm is proposed to improve performance of the verification phase and shows that first, the most discriminate and consistent features are velocity based, and second, the average EER for the proposed algorithm in comparison with the generalDTW algorithm shows a 5.47% decrease.
Abstract: Many people are very accustomed to the process of signing their name and having it matched for authentication. In a signature verification system, the signatures are processed to extract features that are used for verification. These features should not be duplicable. A basic problem is intraclass variations that will greatly affect the matching scores produced. The problem of distinctiveness occurs when the expectation of signatures to vary significantly between individuals is not met. There may be a large number of similarities in the feature sets used to represent the signatures of two different individuals. The efficiency of any signature verification system depends mainly on the discrimination power and robustness of the features used in the system. This study evaluates 40 functional features of viewpoint classification error and consistency for extracting the best subset once a set of features provides maximal discrimination capability between genuine and forged signatures. A modified distance of the DTW algorithm is proposed to improve performance of the verification phase. The proposed system is evaluated on the public SVC2004 signature database. The experimental results show that first, the most discriminate and consistent features are velocity based. Second, the average EER for the proposed algorithm in comparison with the general DTW algorithm shows a 5.47% decrease. Moreover, a comparative study based on a different classifier with a skilled forgery shows that the best result has an EER of 1.73% using the Parzen window classifier.
20 citations
TL;DR: The compared values of liquefaction potential obtained by neural network and neuro-fuzzy models shows that trained artificial neural network models' prediction capability are better than that of neuro- fBuzzy models.
Abstract: In this study, standard penetration test dependent bore-log charts of different boreholes were collected for selected locations in order to prepare the datasets. Datasets were applied to the Idriss and Boulanger method to evaluate liquefaction potential. Complete datasets were used for development of neural network and neuro-fuzzy models. Feed forward backpropagation algorithm with a multilayer perceptron network is utilized to analyze the liquefaction occurrence in different locations. To meet the objective, 159 sets of geotechnical data were collected, out of which 133 datasets were used for development of models and 26 datasets were used for validation. Neural network models were trained with six input vectors by optimum numbers of hidden layers, epoch, and suitable transfer functions. Neuro-fuzzy models have been developed using the Takagi–Sugeno–Kang reliant approach. The predicted values of liquefaction potential by artificial neural networks and neuro-fuzzy models were compared with an empirical method i.e., Idriss and Boulanger method. The compared values of liquefaction potential obtained by neural network and neuro-fuzzy models shows that trained artificial neural network models' prediction capability are better than that of neuro-fuzzy models.
16 citations
TL;DR: Results indicate that the proposed ACO-based embedded optimal controller outperforms the nonoptimal controllers and the conventional genetic algorithm (GA) optimal controllers.
Abstract: This article presents an intelligent system-on-a-programmable-chip-based SoPC ant colony optimization ACO motion controller for embedded omnidirectional mobile robots with three independent driving wheels equally spaced at 120 degrees from one another. Both ACO parameter autotuner and kinematic motion controller are integrated in one field-programmable gate array FPGA chip to efficiently construct an experimental mobile robot. The optimal parameters of the motion controller are obtained by minimizing the performance index using the proposed SoPC-based ACO computing method. These optimal parameters are then employed in the ACO-based embedded kinematic controller in order to obtain better performance for omnidirectional mobile robots to achieve trajectory tracking and stabilization. Experimental results are conducted to show the effectiveness and merit of the proposed intelligent ACO-based embedded controller for omnidirectional mobile robots. These results indicate that the proposed ACO-based embedded optimal controller outperforms the nonoptimal controllers and the conventional genetic algorithm GA optimal controllers.
TL;DR: A fuzzy logic (FL)-based food security risk level assessment system is designed and presented and could be used as a starting point in developing tools that may either assess current food Security risk or predict periods or regions of impending pressure on food supply.
Abstract: A fuzzy logic FL-based food security risk level assessment system is designed and is presented in this article. Three inputs—yield, production, and economic growth—are used to predict the level of risk associated with food supply. A number of previous studies have related food supply with risk assessment for particular types of food, but none of the work was specifically concerned with how the wider food chain might be affected. The system we describe here uses the Mamdani method. The resulting system can assess risk level against three grades: severe, acceptable, and good. The method is tested with UK United Kingdom cereal data for the period from 1988 to 2008. The approach is discussed on the basis that it could be used as a starting point in developing tools that may either assess current food security risk or predict periods or regions of impending pressure on food supply.
TL;DR: It is argued that these two types of selection techniques are complementary to each other and a fusion strategy is proposed to sequentially combine the ranking criteria of multiple filters and a wrapper method.
Abstract: Many classification techniques have been successfully applied to credit scoring tasks. However, using them blindly may lead to unsatisfactory results. Generally, credit datasets are large and are characterized by redundant features and nonrelevant data. Hence, classification techniques and model accuracy could be hampered. To overcome this problem, this study explores a variety of filter and wrapper feature selection methods for reducing nonrelevant features. We argue that these two types of selection techniques are complementary to each other. A fusion strategy is then proposed to sequentially combine the ranking criteria of multiple filters and a wrapper method. Evaluations on three credit datasets show that feature subsets selected by fusion methods are either superior to or at least as adequate as those selected by individual methods.
TL;DR: This study applied a genetic algorithm to evolve a team in the mode of One Flag CTF in Quake III Arena to behave intelligently and enhances the original game AI and assists game designers in tuning the parameters more effectively.
Abstract: Evolving game agents in a first-person shooter game is important to game developers and players. Choosing a proper set of parameters in a multiplayer game is not a straightforward process because consideration must be given to a large number of parameters, and therefore requires effort and thorough knowledge of the game. Thus, numerous artificial intelligence AI techniques are applied in the designing of game characters’ behaviors. This study applied a genetic algorithm to evolve a team in the mode of One Flag CTF in Quake III Arena to behave intelligently. The source code of the team AI is modified, and the progress of the game is represented as a finite state machine. A fitness function is used to evaluate the effect of a team's tactics in certain circumstances during the game. The team as a whole evolves intelligently, and consequently, effective strategies are discovered and applied in various situations. The experimental results have demonstrated that the proposed evolution method is capable of evolving a team's behaviors and optimizing the commands in a shooter game. The evolution strategy enhances the original game AI and assists game designers in tuning the parameters more effectively. In addition, this adaptive capability increases the variety of a game and makes gameplay more interesting and challenging.
TL;DR: A recently developed variant of a very popular global optimization technique—the particle swarm optimization (PSO) algorithm—has been used for solving the problem of camera calibration for a stereo camera system modeled by pin-hole camera model.
Abstract: Camera calibration is an essential issue in many computer vision tasks in which quantitative information of a scene is to be derived from its images. It is concerned with the determination of a set of parameters from the given images. In literature, it has been modeled as a nonlinear global optimization problem and has been solved using various optimization techniques. In this article, a recently developed variant of a very popular global optimization technique—the particle swarm optimization PSO algorithm—has been used for solving this problem for a stereo camera system modeled by pin-hole camera model. Extensive experiments have been performed on synthetic data to test the applicability of the technique to this problem. The simulation results, which have been compared with those obtained by a real coded genetic algorithm RCGA in literature, show that the proposed PSO performs a bit better than RCGA in terms of computational effort.
TL;DR: The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system (ANFIS) and generated a fuzzy inference system that made it possible to predict the output (surface roughness) based on the given inputs.
Abstract: This work considers the effect of the depth of cut, feed, and number of revolutions on the roughness of the machined surface. The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system ANFIS. Those data were used to generate a fuzzy inference system that made it possible to predict the output surface roughness based on the given inputs feed, number of revolutions, and depth of cut. The surface roughness results obtained by the fuzzy inference system FIS were compared with the surface roughness results obtained by neural networks, moving linear least square method and moving linear least absolute deviation method on the same set of experimental data. These methods and systems for prediction of surface roughness are helpful when solving practical technological problems in a manufacturing process, first by determining the cutting parameter values that will add to the demanded quality of a product, and later when optimizing the technological process.
TL;DR: A grey neural prediction scheme is presented for online ship roll motion prediction using a variable structure radial basis function network (RBFN) to represent the time-varying dynamics of nonlinear system.
Abstract: Ship's roll motion at sea is a complex system featured by nonlinearity, uncertainty, and time-varying dynamics. In this paper, a grey neural prediction scheme is presented for online ship roll motion prediction. The grey data processing approach is employed to alleviate the unfavorable effects of the uncertainty exhibited in measurement data, and grey relational analysis method is also involved to determine the structure of the grey prediction scheme. To represent the time-varying dynamics of nonlinear system, a variable structure radial basis function network RBFN is online constructed by learning samples in a sliding data window sequentially. Simulations of ship roll motion prediction are conducted via different approaches to validate the effectiveness of the proposed variable-RBFN-based grey prediction method. Measurement data employed in simulation is obtained during sea trials of the scientific research and training ship Yu Kun. Simulation results demonstrate the efficiency and accuracy of the proposed prediction method.
TL;DR: Experimental results show superior performance of the proposed algorithm in terms of correct classification rate, and it shows robustness to variations in clothing and carrying condition.
Abstract: Gait-based gender identification has received great attention from biometric researchers in the vision field because of its potential in different applications. Gait-based gender identification will help a human identification system to focus only on the identified gender-related features, which can improve the search speed and efficiency of the retrieval system by limiting the subsequent searching space to either a male database or a female database. In this study, after preprocessing, five binary moment features and four spatial features are extracted from a human silhouette. Then the extracted features are used for training and testing pattern classifiers. We have successfully achieved our objective with one gait cycle and nine features of normal video sequences only. To evaluate the performance of the proposed algorithm, experiments have been conducted by using probablistic neural network PNN and support vector machine SVM on the benchmark CASIA B database. Experimental results show superior performance of our approach in terms of correct classification rate, and it shows robustness to variations in clothing and carrying condition.
TL;DR: The article focuses on the evolved ANN, which provides the position of a robot in a space, as in a Cartesian coordinate system, corroborating with the evolutionary robotic research area and showing its practical viability.
Abstract: This work addresses the evolution of an artificial neural network ANN to assist in the problem of indoor robotic localization. We investigate the design and building of an autonomous localization system based on information gathered from wireless networks WN. The article focuses on the evolved ANN, which provides the position of a robot in a space, as in a Cartesian coordinate system, corroborating with the evolutionary robotic research area and showing its practical viability. The proposed system was tested in several experiments, evaluating not only the impact of different evolutionary computation parameters but also the role of the transfer functions on the evolution of the ANN. Results show that slight variations in the parameters lead to significant differences on the evolution process and, therefore, in the accuracy of the robot position.
TL;DR: This article focuses on peer-to-peer (P2P) multicasting, which combines concepts of P2P systems and multicasting solutions; in other words, the multicast tree is constructed using end hosts (peers) and proposes two heuristic algorithms based on evolutionary approach and Tabu Search methods.
Abstract: The growing volume of Internet traffic, increasing popularity of streaming services, and limited scalability of existing network techniques trigger the need to develop new delivery solutions based on a multicasting approach. Multicasting—defined as a one-to-many delivery technique—enables effective distribution of many kinds of content to end users. In this article we focus on peer-to-peer P2P multicasting, which combines concepts of P2P systems and multicasting solutions; in other words, the multicast tree is constructed using end hosts peers. Because P2P multicasting can be applied to deliver content with high reliability requirements, we introduce to P2P multicasting additional survivability constraints that guarantee delivery of content in the case of network failures. We formulate a mixed-integer programming MIP optimization problem of survivable P2P multicasting. Because the problem is nondeterministic polynomial time NP-hard and exact methods such as branch-and-cut can be applied for only a relatively small problem instance, we propose two heuristic algorithms based on evolutionary approach and Tabu Search methods. Extensive computational experiments show that both heuristic algorithms provide results close to optimal—the average gap to optimal results is 0.26% and 5.15% in the case of evolutionary and Tabu Search methods, respectively.
TL;DR: A strong theorem is presented to show the convergence of the proposed distributed learning automata-based algorithm to the optimal solution, and confirms that MDLRD significantly outperforms the other methods in terms of the average hop count, average hit ratio, and control message overhead.
Abstract: Centralized or hierarchical administration of the classical Grid resource discovery approaches is unable to efficiently manage the highly dynamic large‐scale Grid environments. In this study, a multi-attribute distributed learning automata-based resource discovery algorithm called MDLRD is proposed for large-scale peer-to-peer P2P Grids. Taking advantage of the learning automata theory, the proposed method routes the resource query through the path having the minimum expected hop count toward the Grid peers including the requested resources. Therefore, MDLRD significantly reduces the message overhead of the unstructured P2P resource discovery methods in which the resource queries are flooded within the network. Furthermore, MDLRD fully supports the multi-attribute range query that is impossible in structured P2P resource discovery approaches. A strong theorem is presented to show the convergence of the proposed distributed learning automata-based algorithm to the optimal solution. To investigate the performance of the proposed method, several simulation experiments are conducted. The obtained results confirm that MDLRD significantly outperforms the other methods in terms of the average hop count, average hit ratio, and control message overhead.
TL;DR: It is shown that the proposed method outperforms the conventional one and the similarities among the resulting semantic representations are used for cross-language document retrieval.
Abstract: A nonlinear semantic mapping procedure is proposed for cross-language document retrieval. The method relies on a nonlinear space reduction technique for constructing semantic embeddings of multilingual document collections. In the proposed method, an independent embedding is constructed for each language in the multilingual collection and the similarities among the resulting semantic representations are used for cross-language document retrieval. Two variants of the proposed method are implemented and compared with a standard cross-language information retrieval technique. It is shown that the proposed method outperforms the conventional one.
TL;DR: This study finds the optimum coefficients of the IIR digital filter through PSO and it is found that the calculated values are more optimal than the FDA tool and GA available for the design of the filter in MATLAB.
Abstract: In this article, a novel approach for infinite-impulse response IIR digital filters using particle swarm optimization PSO is presented. IIR filter is essentially a digital filter with recursive responses. Because the error surface of digital IIR filters is generally nonlinear and multimodal, so global optimization techniques are required in order to avoid local minima. This study is based on a heuristic way to design IIR filters. PSO is a powerful global optimization algorithm introduced in combinatorial optimization problems. This study finds the optimum coefficients of the IIR digital filter through PSO. It is found that the calculated values are more optimal than the FDA tool and GA available for the design of the filter in MATLAB. Design of low-pass and high-pass IIR digital filters is proposed in order to provide an estimate of the transition band. The simulation results of the employed examples show an improvement on the transition band. The stability of designed filters is described by the position of Pole-Zeros.
TL;DR: This study finds some 3C product-buying behavior patterns, including customer purchase preferences and customer purchase demands, in order to generate different 3C segmentation marketing alternatives.
Abstract: Segmentation is particularly challenging in current markets. Hence, companies operating on consumer markets face significant implementation complexities. However, successful implementation of market segmentation is reported problematic, despite being extensively researched and widely acknowledged as a powerful concept in practice. The desired outcome, and the knowledge discovery of market segmentation, is to reap the benefits of competitive advantage. This study takes Computers/Communications/Consumer 3C products as an example and uses a two-step data mining approach to the cluster analysis and association rules to analyze customer channels and product segmentation. Moreover, we look at what kinds of products and brands customers of different segments prefer and how these preferences differ in relation to varying channel types. Thus, this study finds some 3C product-buying behavior patterns, including customer purchase preferences and customer purchase demands, in order to generate different 3C segmentation marketing alternatives.
TL;DR: To diagnose diabetic retinopathy, a new EYENET model is proposed that was obtained by combining the modified probabilistic neural network (PNN) and a modified radial basis function Neural network (RBFNN), and hence, it possesses the advantages of both models.
Abstract: Diabetic retinopathy DR is an eye disease caused by complications of diabetes and it should be detected early for effective treatment. As diabetes progresses, the vision of a patient may start to deteriorate and lead to diabetic retinopathy. Two types were identified: nonproliferative diabetic retinopathy NPDR and proliferative diabetic retinopathy PDR. In this study, to diagnose diabetic retinopathy, we have proposed a new EYENET model that was obtained by combining the modified probabilistic neural network PNN and a modified radial basis function neural network RBFNN, and hence, it possesses the advantages of both models. The features such as blood vessels and hemorrhages of the NPDR image and exudates of the PDR image are extracted from the raw images using image-processing techniques and are fed to the classifier for classification. A total of 600 fundus images were used, out of which 400 were used for training, and 200 images were used for testing. Experimental results show that PNN has an accuracy of 96%, modified PNN has an accuracy of 97.5%, RBFNN has an accuracy of 93.5%, modified RBFNN has an accuracy of 95.5%, and the proposed EYENET model has an accuracy of 98.5%. This infers that our proposed model outperforms all other models.
TL;DR: A short-term intelligent forecasting method based on g-SVM and the proposed PSO is put forth, and the results of its application to car-sales forecasting indicate that the forecasting method is feasible and effective.
Abstract: In view of the dissatisfactory forecasting capability of standard support vector machine SVM for product sale series with normal distribution noises, a new SVM, called g-SVM, with Gaussian function used as its loss function, is proposed. It is theoretically proved that an adjustable parameter of g-SVM is equal to not only the upper bound of the proportion of erroneous samples to total samples but also the lower bound of the proportion of support vectors to total samples; in other words, the number of erroneous samples is fewer than or equal to that of support vectors. A new version of particle swarm optimization PSO with the integration of Logistic mapping and standard PSO is proposed for an optimal parameter combination of g-SVM. With the above, a short-term intelligent forecasting method based on g-SVM and the proposed PSO is then put forth. The results of its application to car-sales forecasting indicate that the forecasting method is feasible and effective.
TL;DR: A novel bilevel particle swarm optimization algorithm (BPSO) is designed and it can solve BLPP without any assumed conditions of the problem and the results support the finding that BPSO is effective in optimizing BLPP.
Abstract: This study considers joint pricing and lot-sizing policies in a single-manufacturer–single-retailer system. Because a supply chain is a hierarchical system, we adopt a bilevel programming technique to establish a bilevel joint pricing and lot-sizing model guided by the manufacturer. The objective of the problem here is to respectively maximize the manufacturer's and the retailer's net profits by determining the manufacturer's and retailer's lot size, the wholesale price and the retail price simultaneously. Following the properties of the bilevel programming problem BLPP, we design a novel bilevel particle swarm optimization algorithm BPSO, and it can solve BLPP without any assumed conditions of the problem. BPSO shows a good performance on eight benchmark bilevel problems. Then BPSO is employed to solve the proposed bilevel model, and the experimental data are used to analyze the features of the proposed bilevel model, and the results support the finding that BPSO is effective in optimizing BLPP.
TL;DR: The experiments show that the hybrid profiling framework and two hybrid recommendation approaches can alleviate the problem in an intrusive manner and decrease the degree of preference conflict without decreasing the accuracy of the recommendation.
Abstract: Multicriteria recommender systems typically gather the user preferences by asking a user to rate different aspects of an item on a sliding scale explicitly. However, this approach could possibly cause intrusiveness and conflict on user preferences. For example, an individual's preference on each aspect of an item may conflict with an overall preference. To overcome such limitations, we proposed the hybrid profiling framework to generate a set of useful implicit dataset to support multicriteria recommender systems. We also proposed two hybrid multicriteria recommendation approaches, namely the user-attribute-based UAB and the user-item matching UIM to improve recommendation accuracy. Finally, we conducted experiments to confirm the efficiency of the proposed approaches. The experiments show that the profiling framework and two hybrid recommendation approaches can alleviate the problem in an intrusive manner and decrease the degree of preference conflict without decreasing the accuracy of the recommendation. They also show that our proposed hybrid multicriteria recommendation approaches can significantly outperform both the traditional collaborative filtering and the simple multicriteria filtering approaches.
TL;DR: A multilayer perceptron (MLP) ANN is proposed to control generator excitation trained with low-dimensional input space and has been trained offline to avert the risk potential of online training, illustrating preeminence of the proposed neurocontroller-based excitation system over the conventional controllers-basedexcitation system.
Abstract: Control of the synchronous generator, also referred to as an alternator, has always remained very significant in power system operation and control. Alternator output is proportional to load angle, but as the parameter is moved up, the power system security approaches the extreme limit. Hence, generators are operated well below their steady state stability limit for the secure operation of a power system. This raises demand for efficient and fast controllers. Artificial intelligence, specifically artificial neural network ANN, is emerging very rapidly and has become an efficient tool for operation and control of power systems. ANN requires considerable time to tune weights, but it is fast and accurate once tuned properly. Previously, ANNs have been trained with high-dimensional input space or have been trained online. Hence, either one requires considerable time to yield the control signal or is a bit risky technique to apply in interconnected power systems. In this study, a multilayer perceptron MLP ANN is proposed to control generator excitation trained with low-dimensional input space. Moreover, MLP has been trained offline to avert the risk potential of online training. The results illustrate preeminence of the proposed neurocontroller-based excitation system over the conventional controllers-based excitation system.
TL;DR: The proposed novel fusion of evolutionary fuzzy clustering with a neural network yields superior performance in classification and pattern recognition problems.
Abstract: In this article, a new hybrid intelligent model comprising a cluster allocation and adaptation component is developed for solving classification and pattern recognition problems. Its computation ability has been verified through various benchmark problems and biometric applications. The proposed model consists of two components: cluster distribution and adaptation. In the first module, mean patterns are distributed into the number of clusters based on the evolutionary fuzzy clustering, which is the basis for network structure selection in next module. In the second module, training and subsequent generalization is performed by the syndicate neural networks SNN. The number of SNNs required in the second module will be same as the number of clusters. Whereas each network contains as many output neurons as the maximum number of members assigned to each cluster. The proposed novel fusion of evolutionary fuzzy clustering with a neural network yields superior performance in classification and pattern recognition problems. Performance evaluation has been carried out over a wide spectrum of benchmark problems and real-life biometric recognition problems with noise and occlusion. Experimental results demonstrate the efficacy of the methodology over existing ones.