Showing papers presented at "Intelligent Systems Design and Applications in 2011"

Generalized Louvain method for community detection in large networks

Abstract: In this paper we present a novel strategy to discover the community structure of (possibly, large) networks This approach is based on the well-know concept of network modularity optimization To do so, our algorithm exploits a novel measure of edge centrality, based on the κ-paths This technique allows to efficiently compute a edge ranking in large networks in near linear time Once the centrality ranking is calculated, the algorithm computes the pairwise proximity between nodes of the network Finally, it discovers the community structure adopting a strategy inspired by the well-known state-of-the-art Louvain method (henceforth, LM), efficiently maximizing the network modularity The experiments we carried out show that our algorithm outperforms other techniques and slightly improves results of the original LM, providing reliable results Another advantage is that its adoption is naturally extended even to unweighted networks, differently with respect to the LM

An intelligent system for detecting faults in photovoltaic fields

Abstract: In this work, an intelligent system for automatic detection of fault in PV fields is proposed. This system is based on a Takagi-Sugeno-Kahn Fuzzy Rule-Based System (TSK-FRBS), which provides an estimation of the instant power production of the PV field in normal functioning, i.e, when no faults occur. Then, the estimated power is compared with the real power and an alarm signal is generated if the difference between powers overcomes a threshold. The TSK-FRBS has been trained using data collected from a PV plant simulator, during normal functioning. Preliminary tests were carried out in a simulated framework, by reproducing both normal and fault conditions. Results show that the system can recognize more than 90% of fault conditions, even when noisy data are introduced.

24-hour-ahead forecasting of energy production in solar PV systems

Abstract: This paper presents a flexible approach to forecasting of energy production in solar photovoltaic (PV) installations, using time series analysis and neural networks. Our goal is to develop a one day-ahead forecasting model based on an artificial neural network with tapped delay lines. Despite some methods already exist for energy forecasting problems, the main novelty of our approach is the proposal of a tool for the technician of a PV installation to correctly configure the forecasting model according to the particular installation characteristics. The correct configuration takes into account the number of hidden neurons, the number of delay elements, and the training window width, i.e., the appropriate number of days, before the predicted day, employed for the training. The irradiation along with the sampling hour are used as input variables to predict the daily accumulated energy with a percentage error less than 5%.

LIDAR based perception solution for autonomous vehicles

Abstract: In this work, a solution for clustering and tracking obstacles in the area covered by a LIDAR sensor is presented. It is based on a combination of simple artificial intelligence techniques and it is conceived as an initial version of a detection and tracking system for objects of any shape that an autonomous vehicle might find in its surroundings. The proposed solution divides the problem into three consecutive phases: 1) segmentation, 2) fragmentation detection and clustering and 3) tracking. The work done has been tested with real world LIDAR scan samples taken from an instrumented vehicle.

Jerk-based feature extraction for robust activity recognition from acceleration data

Abstract: A current trend in activity recognition is to use just one easily carried accelerometer, either integrated into a mobile phone, carried in a pocket, or attached to an animal's collar. The main disadvantage of this approach is that the orientation of the accelerometer is generally unknown. Therefore, one cannot separate body-related accelerations from the gravitational acceleration or determine the real directions of the observed accelerations accurately. As a solution, we introduce a new technique where jerk (changes of accelerations) is analyzed instead of the original acceleration signal. The total jerk magnitude is completely orientation-independent and it reflects only body-related accelerations. If the direction of the gravitation can be approximated even loosely, then the jerk signal can be further enriched with valuable information on jerk angles (direction changes). According to our experiments this kind of jerk-filtered signal produces robust features and can improve the recognition accuracy remarkably.

On using crowdsourcing and active learning to improve classification performance

Abstract: Crowdsourcing is an emergent trend for general-purpose classification problem solving. Over the past decade, this notion has been embodied by enlisting a crowd of humans to help solve problems. There are a growing number of real-world problems that take advantage of this technique, such as Wikipedia, Linux or Amazon Mechanical Turk. In this paper, we evaluate its suitability for classification, namely if it can outperform state-of-the-art models by combining it with active learning techniques. We propose two approaches based on crowdsourcing and active learning and empirically evaluate the performance of a baseline Support Vector Machine when active learning examples are chosen and made available for classification to a crowd in a web-based scenario. The proposed crowdsourcing active learning approach was tested with Jester data set, a text humour classification benchmark, resulting in promising improvements over baseline results.

An intelligent system for electrical energy management in buildings

Abstract: Recent studies have highlighted that a significant part of the electrical energy consumption in residential and business buildings is due to an improper use of the electrical appliances. In this context, an automated power management system - capable of reducing energy wastes while preserving the perceived comfort level - would be extremely appealing. To this aim, we propose GreenBuilding, a sensor-based intelligent system that monitors the energy consumption and automatically controls the behavior of appliances used in a building. GreenBuilding has been implemented as a prototype and has been experimented in a real household scenario. The analysis of the experimental results highlights that GreenBuilding is able to provide significant energy savings.

Multi-constrained route optimization for Electric Vehicles (EVs) using Particle Swarm Optimization (PSO)

Abstract: Route optimization (RO) is an important feature of the Electric Vehicles (EVs) which is responsible for finding optimized paths between any source and destination nodes in the road network. In this paper, the RO problem of EVs is solved by using the Multi Constrained Optimal Path (MCOP) approach. The proposed MCOP problem aims to minimize the length of the path and meets constraints on total travelling time, total time delay due to signals, total recharging time, and total recharging cost. The Penalty Function method is used to transform the MCOP problem into unconstrained optimization problem. The unconstrained optimization is performed by using a Particle Swarm Optimization (PSO) based algorithm. The proposed algorithm has innovative methods for finding the velocity of the particles and updating their positions. The performance of the proposed algorithm is compared with two previous heuristics: H_MCOP and Genetic Algorithm (GA). The time of optimization is varied between 1 second (s) and 5s. The proposed algorithm has obtained the minimum value of the objective function in at-least 9.375% more test instances than the GA and H_MCOP

The use of fuzzy decision trees for coffee rust warning in Brazilian crops

Abstract: This paper proposes the use of fuzzy decision trees for coffee rust warning, the most economically important coffee disease in the world. The models were induced using field data collected during 8 years. Using different subsets of attributes from the original data, three distinct datasets were constructed. The class attribute, representing the monthly infection rate, was used to construct six datasets according to two distinct infection rates. Induced models can be used to trigger alerts when estimated monthly disease infection rates reach one of the two thresholds. The first threshold allows applying preventive actions, whereas the second one requires a curative action. The fuzzy decision tree models were compared to the ones induced by a classic decision tree algorithm, taking into account the accuracy and the syntactic complexity of the models, as well as its quality according to an expert opinion. The fuzzy models showed better accuracy power and interpretability.

Self-Organizing Maps and Scale-Invariant Maps in Echo State Networks

Abstract: In the last years a new approach for designing and training artificial Recurrent Neural Network (RNN) have been investigated under the name of Reservoir Computing (RC). One important model in the field of RC has been developed under the name of Echo State Networks (ESNs). Traditionally, an ESN uses a RNN with random untrained parameters called the reservoir. The Self-Organizing Map (SOM) and the Scale Invariant Map (SIM) are two methods of topographic maps which have been used in different tasks of unsupervised learning. Recently, new works show that is effective using the SOM to set values of the reservoir parameters. The primary goal of this work is to improve the performance of ESN using the another method SIM. Here, we present the description of these two topographic map methods and the way to apply its on the ESN initialization. We specify an original algorithm to set the reservoir weights using the SOM and SIM. Furthermore, we use artificial data set to compare the use of topographic maps to initialize the ESN with random initialization. Overall, our results show the aptitude of SIM and SOM to set the reservoir parameters.

Online lameness detection in dairy cattle using Body Movement Pattern (BMP)

Abstract: In this paper a method for real time lameness detection in dairy cattle based on back posture analysis is presented. The system utilizes image processing techniques to automatically detect lameness based on new definition called Body Movement Pattern (BMP). The traditional Locomotion Scoring (LS) system that is widely used for manual lameness detection by expert people failed to classify the selected cows from a commercial farm in Estonia. The proposed system not only performs the detection in automatic way but also categorizes the level of lameness with high accuracy. Two ellipses are fitted on the back posture and the parameters of the ellipses in relation to the head position are used as features for classification of the lameness degree. The new method has been tested on more than 1200 cows with success rate of 92%.

Symbolic representation of the EEG for sleep stage classification

Abstract: Manual visualization-based sleep stage classification is a time-consuming task prone to errors. Since the correct identification of sleep stages is vital for the correct identification of sleep disorders and for the research in this field in general, there is a growing demand for efficient automatic classification methods. However, there is still no symbolic representation of the biomedical signals that leads to a reliable and accurate automatic sleep classification system. This work presents the application of a novel method for symbolic representation of the EEG and evaluates its potential as information source for a sleep stage classifier, in this case a SVM classifier. The data is first analyzed using Self-Organizing Maps (SOM) and a mutual information (MI)-based variable selection algorithm. Preliminary results of sleep data classification provide success rates around 70%. These results are promising since only EEG is used, and there is still room for improvement in this new symbolic representation of the signal.

Towards integrating fuzzy logic capabilities into an ontology-based Inductive Logic Programming framework

Abstract: Ontologies based on Description Logics (DLs) have proved to be useful in formally sharing knowledge across applications. Recently, several tools have extended ontologies with fuzzy logic capabilities in order to apply ontology-based reasoning to vague and imprecise domains. This paper first analyses the state of the art in tools for fuzzy ontologies management and then describes how some of the most significant ones have been integrated in order to extend an ontology-based Inductive Logic Programming (ILP) system with fuzzy logic capabilities. A fuzzy version of a well-known ILP test case has been developed in order to validate the approach. This research represents a first step towards fuzzy inductive reasoning for OWL ontologies.

Hierarchical multi-label classification for protein function prediction: A local approach based on neural networks

Abstract: In Hierarchical Multi-Label Classification problems, each instance can be classified into two or more classes simultaneously, differently from conventional classification. Additionally, the classes are structured in a hierarchy, in the form of either a tree or a directed acyclic graph. Hence, an instance can be assigned to two or more paths from the hierarchical structure, resulting in a complex classification problem with possibly hundreds of classes. Many methods have been proposed to deal with such problems, some of them employing a single classifier to deal with all classes simultaneously (global methods), and others employing many classifiers to decompose the original problem into a set of subproblems (local methods). In this work, we propose a novel local method named HMC-LMLP, which uses one Multi-Layer Perceptron per hierarchical level. The predictions in one level are used as inputs to the network responsible for the predictions in the next level. We make use of two distinct Multi-Layer Perceptron algorithms: Back-propagation and Resilient Back-propagation. In addition, we make use of an error measure specially tailored to multi-label problems for training the networks. Our method is compared to state-of-the-art hierarchical multi-label classification algorithms, in protein function prediction datasets. The experimental results show that our approach presents competitive predictive accuracy, suggesting that artificial neural networks constitute a promising alternative to deal with hierarchical multi-label classification of biological data.

A preliminary study of ordinal metrics to guide a multi-objective evolutionary algorithm

Abstract: There are many metrics available to measure the goodness of a classifier when working with ordinal datasets. These measures are divided into product-moment and association metrics. In this paper, the behavior of several metrics is studied in different situations. In addition, two new measures associated with an ordinal classifier are defined: the maximum and the minimum mean absolute error of all the classes. From the results of this comparison, a pair of metrics is selected (one associated to the overall error and another one to the error of the class with lowest level of classification) to guide the evolution of a multi-objective evolutionary algorithm, obtaining good results in generalization on ordinal datasets.

Bayesian networks classifiers for gene-expression data

Abstract: In this work, we study the application of Bayesian networks classifiers for gene expression data in three ways: first, we made an exhaustive state-of-art of Bayesian classifiers and Bayesian classifiers induced from microarray data. Second, we propose a preprocessing scheme for gene expression data, to induce Bayesian classifiers. Third, we evaluate different Bayesian classifiers for this kind of data, including the C-RPDAG classifier presented by the authors.

Short-term daily peak load forecasting using fast learning neural network

Abstract: Load forecasting has been an inevitable issue in electric power supply in past. It is always desired to predict the load requirements in order to generate and supply electric power efficiently. In this research, a neuro-evolutionary technique known as Cartesian Genetic Algorithm evolved Artificial Neural Network (CGPANN) has been deployed to develop a peak load forecasting model for the prediction of peak loads 24 hours ahead. The proposed model presents the training of all the parameters of Artificial Neural Network (ANN) including: weights, topology and functionality of individual nodes. The network is trained both on annual as well as quarterly bases, thus obtaining a unique model for each season.

A bottom-up oblique decision tree induction algorithm

Abstract: Decision tree induction algorithms are widely used in knowledge discovery and data mining, specially in scenarios where model comprehensibility is desired. A variation of the traditional univariate approach is the so-called oblique decision tree, which allows multivariate tests in its non-terminal nodes. Oblique decision trees can model decision boundaries that are oblique to the attribute axes, whereas univariate trees can only perform axis-parallel splits. The majority of the oblique and univariate decision tree induction algorithms perform a top-down strategy for growing the tree, relying on an impurity-based measure for splitting nodes. In this paper, we propose a novel bottom-up algorithm for inducing oblique trees named BUTIA. It does not require an impurity-measure for dividing nodes, since we know a priori the data resulting from each split. For generating the splitting hyperplanes, our algorithm implements a support vector machine solution, and a clustering algorithm is used for generating the initial leaves. We compare BUTIA to traditional univariate and oblique decision tree algorithms, C4.5, CART, OC1 and FT, as well as to a standard SVM implementation, using real gene expression benchmark data. Experimental results show the effectiveness of the proposed approach in several cases.

Edge detection using F-transform

Abstract: This contribution shows how the technique of F-transform can be used for handling the problem of edge detection. A justification of the proposed approach is given and the based on it algorithm is presented. Various examples demonstrate effectiveness of the proposed algorithm and compare it with some established techniques.

Modeling serious games using AOSE methodologies

Abstract: Lately, serious games are a useful tool to learn how humans interact with each other and their environment. The best serious games are simulations that have the appearance of a game, but whose events and / or processes are non-game. Usually they include business domains and military operations (many games are popular entertainment on the basis of business and military operations, but with simpler rules). On the other hand, one of the purposes of Agent-Oriented Software Engineering is the creation of methodologies and tools that enable inexpensive development and maintenance of agent-based software. The relationship between serious games and Agent-Oriented Software Engineering is also clear given that software agents (perhaps intelligent) are used as virtual players or actors in many computer games and simulations, that the agent paradigm is of great interest in social behavior and interaction among agents (that can be thought of as players in a game), and also that the development process for agents is very close to the process of game development.

Optimal PMU placement for power system observability using differential evolution

Abstract: This paper investigates the application of differential evolution (DE) algorithm for the problem of optimal placement of phasor measurement units (PMUs) in an electric power network. The problem is to determine the minimum number of PMUs and their respective locations to make the system observable. In order to cope with the continuous changes in the power system's topology, the optimization problem is formulated considering not only the new PMUs to be installed but also the existing ones to be retained or relocated. Additionally, the new formulation takes into account the locations, if any, at which PMUs shall or shall not be placed. The effectiveness of the proposed method is verified via IEEE 14-bus, 30-bus, 39-bus and 57-bus standard systems.

WCOID: Maintaining case-based reasoning systems using Weighting, Clustering, Outliers and Internal cases Detection

Abstract: The success of a Case Based Reasoning (CBR) system depends on the quality of case data and the speed of the retrieval process that can be expensive in time especially when the number of cases gets large. To guarantee this quality, maintenance the contents of a case base becomes necessarily. In this paper, we propose a novel case base maintenance (CBM) policy named WCOID - Weighting, Clustering, Outliers and Internal cases Detection, using, in addition to clustering and outliers detection methods, feature weights in the process of improving the competence of our reduced case base. The purpose of our WCOID case base maintenance policy is to reduce both the storage requirements and search time and to focus on balancing case retrieval efficiency and competence for a large size case base. WCOID is mainly based on the idea that a large case base with weighted features is transformed to a small case base.

Inferring user personality in social networks: A case study in Facebook

Abstract: In the context of adaptive intelligent systems, it is essential to build user models to be considered with adaptation purposes. Personality is an interesting user feature to be incorporated in user models; it may lead to know the user needs or preferences in different situations. In this direction, eliciting user personality is needed. This information should be obtained as unobtrusively as possible, yet without compromising the reliability of the model built. In this paper, we present a method for eliciting user personality by analyzing user interactions within the social network Facebook, with the goal of mining behavioral patterns. We have developed TP2010, a Facebook application based on the ZKPQ-50-cc questionnaire, to get information about both the user personality and his interactions within Facebook. We have built a classifier model starting from the analysis of a set of data from more than 11000 users. The results show that it is feasible to get information about the user personality by analyzing data from social network interactions.

Fuzzy Rule Based Classification Systems versus crisp robust learners trained in presence of class noise's effects: A case of study

Abstract: The presence of noise is common in any real-world dataset and may adversely affect the accuracy, construction time and complexity of the classifiers in this context. Traditionally, many algorithms have incorporated mechanisms to deal with noisy problems and reduce noise's effects on performance; they are called robust learners. The C4.5 crisp algorithm is a well-known example of this group of methods. On the other hand, models built by Fuzzy Rule Based Classification Systems are widely recognized for their robustness to imperfect data, but also for their interpretability. The aim of this contribution is to analyze the good behavior and robustness of Fuzzy Rule Based Classification Systems when noise is present in the examples' class labels, especially versus robust learners. In order to accomplish this study, a large number of datasets are created by introducing different levels of noise into the class labels in the training sets. We compare a Fuzzy Rule Based Classification System, the Fuzzy Unordered Rule Induction Algorithm, with respect to the C4.5 classic robust learner which is considered tolerant to noise. From the results obtained it is possible to observe that Fuzzy Rule Based Classification Systems have a good tolerance, in comparison to the C4.5 algorithm, to class noise.

On the role of fuzzy quantified statements in linguistic summarization of data

Abstract: In this paper a discussion on some of the key problems in fuzzy linguistic summarization of data in introduced. Also a description on the stages that the summarization process involving fuzzy quantified statements should accomplish is presented.

Optimal fuzzy controller for voltage control in distribution systems

Abstract: The increasing diffusion of distributed generation plants in recent years highlights problems concerning voltage regulation in medium voltage (MV) radial distribution networks. Among various possible control techniques able to regulate voltage profiles, intelligent systems based ones seems to be very promising. In particular, fuzzy control techniques are very interesting for a wide range of applicative fields like power distribution systems control, allowing regulation of voltage profiles handling uncertainty/vagueness and imprecise information. This paper presents a decentralized fuzzy based control technique finalized to realize a local regulation of voltage profiles at buses where wind power generators are connected, in order to avoid their disconnection. Validation of the proposed control system has been carried out by simulations conducted on a real MV Italian radial distribution system.

TF-SIDF: Term frequency, sketched inverse document frequency

Abstract: Exact calculation of the TF-IDF weighting function in massive streams of documents involves challenging memory space requirements. In this work, we propose TF-SIDF, a novel solution for extracting relevant words from streams of documents with a high number of terms. TF-SIDF relies on the Count-Min Sketch data structure, which allows to estimate the counts of all the terms in the stream. Results of the experiments conducted with two dataset show that this sketch-based algorithm achieves good approximations of the TF-IDF weighting values (as a rule, the top terms with highest TF-IDF values remaining the same), while substantial savings in memory usage are observed. It is also observed that the performance is highly correlated with the sketch size, and that wider sketch configurations are preferable given the same sketch size.

Improving accuracy of recommendation system by means of Item-based Fuzzy Clustering Collaborative Filtering

Abstract: Predicting user preferences is a challenging task. Different approaches for recommending products to the users are proposed in literature and collaborative filtering has been proved to be one of the most successful techniques. Some issues related to the quality of recommendation and to computational aspects still arise (e.g., scalability and cold-start recommendations). In this paper, we propose an Item-based Fuzzy Clustering Collaborative Filtering (IFCCF) in order to ensure the benefits of a model-based technique improving the quality of suggestions. Experimentation led by predicting ratings of MovieLens and Jester users makes this promising and worth to be further investigated in a cross-domain dataset.

Machine printed handwritten text discrimination using Radon transform and SVM classifier

Abstract: Discrimination of machine printed and handwritten text is deemed as major problem in the recognition of the mixed texts. In this paper, we address the problem of identifying each type by using the Radon transform and Support Vector Machines, which is conducted at three steps: preprocessing, feature generation and classification. New set of features is generated from each word using the Radon transform. Classification is used to distinguish printed text from handwritten. The proposed system is tested on IAM databases. The recognition rate of the proposed method is calculated to be over 98%.

An efficient multi-objective evolutionary optimizer to design all-optical networks considering physical impairments and CAPEX

Abstract: In this paper we propose efficient operators for a well known multi-objective evolutionary optimizer, called NSGA II, applied to design all-optical networks regarding the network topology and the device specifications in order to both minimize the capital expenditure to build the network and to maximize the overall network performance. From the experiments, we perceived that it is better to use an uniform crossover, to include preferences a priori and to initialize the individuals emphasizing the network topology.