Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2013 | Book

Modelling Space Perception in Urban Planning: A Cognitive AI-Based Approach Read chapter Read first chapter

Contemporary Challenges and Solutions in Applied Artificial Intelligence

Editors: Moonis Ali, Tibor Bosse, Koen V. Hindriks, Mark Hoogendoorn, Catholijn M. Jonker, Jan Treur

Publisher: Springer International Publishing

Book Series : Studies in Computational Intelligence

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

Since its origination in the mid-twentieth century, the area of Artificial Intelligence (AI) has undergone a number of developments. While the early interest in AI was mainly triggered by the desire to develop artifacts that show the same intelligent behavior as humans, nowadays scientists have realized that research in AI involves a multitude of separate challenges, besides the traditional goal to replicate human intelligence. In particular, recent history has pointed out that a variety of ‘intelligent’ computational techniques, part of which are inspired by human intelligence, may be successfully applied to solve all kinds of practical problems. This sub-area of AI, which has its main emphasis on applications of intelligent systems to solve real-life problems, is currently known under the term Applied Intelligence.

The objective of the International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE) is to promote and disseminate recent research developments in Applied Intelligence. The current book contains 30 chapters authored by participants of the 26th edition of IEA/AIE, which was held in Amsterdam, the Netherlands. The material of each chapter is self-contained and was reviewed by at least two anonymous referees, to assure a high quality. Readers can select any individual chapter based on their research interests without the need of reading other chapters. We are confident that this book provides useful reference values to researchers and students in the field of Applied Intelligence, enabling them to find opportunities and recognize challenges in the field.

Table of Contents

Frontmatter

Cognitive Modeling

Frontmatter
Modelling Space Perception in Urban Planning: A Cognitive AI-Based Approach
Abstract
The study deals with cooperative space conceptualization by humans according to the AI-based cognitive approach and the urban-planning approach of architects and planners. It carries out the diagnosis and the control of example spaces in known urban environments. The paper is oriented toward suggesting system architectures to let spatial agents add structuring degrees to navigated urban spaces and challenge relevant disorientation conditions.
The methodology draws on ontology-based text-mining analysis and statistical interpretation applied to university-class questionnaire surveys, exploring behaviours in human interaction with a space. After an introduction, a case-based discussion of the cooperative conceptualization and representation of space is carried out. The third section shows the ontological results of the case-study, with general results and follow-up discussed in the concluding section.
Dino Borri, Domenico Camarda
Facilitating Player Interaction in a Dynamic Storytelling Environment
Abstract
Enabling players to interact with stories generated using artificial intelligence planning techniques, and thus exert their own influence on the emergent narrative, is an important challenge in the development of interactive computer game worlds. We focus in this paper on story planning in a dynamic storytelling environment and the problem that arises when plan steps are reduced to primitive actions that can be executed in the game world, but lack sufficient context for players to understand their purpose from a narrative perspective. We propose a solution to this problem in which story plans are represented at two different levels of abstraction, one that allows for meaningful player interaction, and another that enables plan steps to be executed in the virtual world.
Richard Paul, Darryl Charles, Michael McNeill, David McSherry

Distributed Systems and Networks

Frontmatter
Using Agents for Dynamic Components Redeployment and Replication in Distributed Systems
Abstract
Availability is one of the important criteria that affect the usefulness and efficiency of a distributed system. It mainly depends on how the components are deployed on the available hosts. In this paper, we present a generic agent-based monitor approach that supports the dynamic component redeployment and replication mechanisms which were presented in Avala and E-Avala. Avala and E-Avala were proposed to improve availability in large and distributed component-based systems via redeployment and replication. By reifying the interaction between the system and components, agents can detect when it is necessary to change the configuration and whether redeployment or replication is more appropriate.
Nadim Obeid, Samih Al-Areqi
Prototyping and Evaluation of a Wireless Sensor Network That Aims Easy Installation
Abstract
The number of senior citizens living alone are increasing in Japan. Accordingly, the budget for social security is increasing. The percentage of burden for social security budgets reached 69.5% only for senior citizens recently, and will increase more and more. These budgets are consumed in mainly in the larger hospitals. Thus, recently “in-house” health care for senior citizens is gathering much attention in Japan. Various “home-care” products are increasingly developed and implemented to care the health of the senior citizens. However, these products are usually expensive and their self installation is very difficult. In this research, we developed a wireless sensor network system that realizes easy installation and easy operation. Our preliminary experiments demonstrate that our system can surely find some anomaly sensing information without any difficult installation procedures.
Takanobu Otsuka, Tatsunosuke Tsuboi, Takayuki Ito

Evolutionary Algorithms

Frontmatter
Winner Determination in Combinatorial Reverse Auctions
Abstract
Since commercially efficient, combinatorial auctions are getting more interest than traditional auctions. However, winner determination problem is still one of the main challenges of combinatorial auctions. In this paper, we propose a new method based on genetic algorithms to address two important issues in the context of combinatorial reverse auctions: determining the winner(s) in a reasonable processing time and reducing the procurement cost. Indeed, not much work has been done using genetic algorithms to determine the winner(s) specifically for combinatorial reverse auctions. To evaluate the performance of our method, we conducted several experiments comparing our proposed method with another method related to determining winner(s) in combinatorial reverse auctions. The experiment results clearly demonstrate the superiority of our method in terms of processing time and procurement cost.
Shubhashis Kumar Shil, Malek Mouhoub, Samira Sadaoui
Virus Transmission Genetic Algorithm
Abstract
In this paper we propose a novel Virus Transmission Genetic Algorithm, which is inspired by the evolution of immune defense and the infection transmission model. Containing one virus population and one host population, the VTGA simulates biological infections by using new operators such as virus infection and virus spread. To study the effectiveness, we apply the algorithm to several function optimization problems, several travelling salesman problems and a forest planning problem. Results of the experiments show that the VTGA performs well at searching for optimal solutions and preserving diversity of population.
Weixin Ling, Walter D. Potter
Automated Phenotype-Genotype Table Understanding
Abstract
Scholarly writing in the broad area of experimental biomedicine is a genre that has a rhetorical style that exhibits some easily identifiable stylistic features: division of the paper into well-defined sections (Introduction, Methods, Results, Discussion), and the use of tables and figures to organize and express important results. Tables and figures have stylistic features, as well: titles, captions, content.
Shifta Ansari, Robert E. Mercer, Peter Rogan

Knowledge Representation and Reasoning

Frontmatter
An Implementation of a Menu-List Recommendation System Providing Feedback from User
Abstract
People are increasingly searching for recipes online when they cook. At “cookpad” [1], Japan’s most popular recipe site, users can search for and contribute recipes. But since such recipe sites often fail to provide detailed nutrition information, users have to determine balanced nutrition by themselves. Hence, our system, which recommends a menu-list based on nutritional balance and considers user feedback about its recommended menu-list. When users input what they actually have eaten, our system recommends meals based on the feedback information after considering the entire nutritional content. The experimental results suggest that our system can provide useful nutrition information. These results were validated by a nutritional expert.
Chika Nishikawa, Akihiko Nagai, Takayuki Ito, Satomi Maruyama
On Representing and Sharing Knowledge in Collaborative Problem Solving
Abstract
In this paper, we propose an agent-based framework for collaborative problem-solving. We emphasize the knowledge representation and knowledge sharing issues. We employ a three-valued based Temporal First-Order Nonmonotonic Logic that allows an explicit representation of events/actions and can handle dialogue game protocols and temporal aspects explicitly. A prototype is developed with a case to guide and assist evacuees in an emergency evacuation from a building.
Heba Al-Juaidy, Lina Abu Jaradeh, Duha Qutaishat, Nadim Obeid

Machine Learning Applications

Frontmatter
Constructing Language Models for Spoken Dialogue Systems from Keyword Set
Abstract
Spoken dialogue systems (SDSs) need language models (LMs) for automatic speech recognizers (ASRs) for each domain. This is because domain-specific words such as proper nouns differ in domains, and they must be recognized correctly to accomplish the task.We propose a method to construct a class N-gram LM only from a set of domain-specific words (i.e., words in target relational database for retrieval). This problem setting corresponds to a situation where we construct a new spoken dialogue system; i.e., there is no sufficient corpus available in the target domain.We use a similar-domain corpus and assign class labels to it using machine learning. Because no sufficient training data are available, we create an initial training corpus by string matching and then use it as training data. The experimental results showed that our approach is promising: ASR accuracy for domain-specific words improved.
Kazunori Komatani, Shojiro Mori, Satoshi Sato
A Speaker Diarization System with Robust Speaker Localization and Voice Activity Detection
Abstract
In real-world auditory scene analysis of human-robot interactions, three types of information are essential and need to be extracted from the observation data – who speaks when and where. We present a speaker diarization system that is used to accomplish the resolution. Multiple signal classification (MUSIC) is a powerful method for voice activity detection (VAD) and direction of arrival (DOA) estimation. We propose our system and compare its performance in VAD and DOA with the method based on MUSIC algorithm.
Yangyang Huang, Takuma Otsuka, Hiroshi G. Okuno
A Content Fusion System Based on User Participation Degree on Microblog
Abstract
Microblog users generally publish their opinions by using condensed text with some non-textual content. Besides, post responses from participants often include noise such as chaotic messages or unrelated information to the theme. Thus, we propose a Feature-based Filtering Model attempts to filter these noises. Moreover, we propose a method, which select the responses based on user participation degree, Maximum Discussion Group Detection (MDGD), to solve the problem of ignored information by current content fusion approaches. Briefly, the posts with higher user participation degree are selected to extract the short text from original post and its responses. The related content from several microblog platforms is also referred to enrich the fusion results. In the experiments, the test data set is collected from the microblog platforms of Plurk and Facebook. Finally, the Normalized Discounted Cumulative Gain (NDCG) metrics show that our method is capable to provide qualified extraction results.
Wo-Chen Liu, Meng-Hsuan Fu, Kuan-Rong Lee, Yau-Hwang Kuo
Network Intrusion Detection System Based on Incremental Support Vector Machine
Abstract
Based on simple incremental SVM, we proposed an improved incremental SVM algorithm (ISVM), and combined it into a kernel function U-RBF and applied it into network intrusion detection. The simulation results show that the improved kernel function U-RBF has played some role in saving training time and test time. The ISVM has eased the oscillation phenomenon in the process of the learning to some extent, and the stability of ISVM is relatively good.
Haiyi Zhang, Yang Yi, Jiansheng Wu
Use of Fuzzy Information for Heterogeneous Performance Evaluation
Abstract
Personnel performance appraisals have been practiced in many organizations and institutions with the purpose for salary adjustments, promotions, training, and other decisions that affect employee status in the company. Human judgments, including preferences are often vague and cannot be estimated in exact numerical values. This paper uses a method under the linguistic framework for heterogeneous performance evaluation, which allocates different weights for assessor members to use linguistic terms in order to express their fuzzy preferences for candidate solutions and for individual judgments. The introduced method has been used in the empirical study, and the results have been analyzed.
Mohammad Anisseh, Mohammad Reza Shahraki

Optimization

Frontmatter
Designing Loss-Aware Fitness Function for GA-Based Algorithmic Trading
Abstract
In these days, an algorithmic trading in stock or foreign exchange (henceforth forex) market is in fashion, and needs for automatically performing stable asset management are growing. Machine learning techniques are increasingly used to construct trading rules of the algorithmic trading, as researches on the algorithmic trading advance. Our study aims to build an automatic trading agent, and in this paper, we concentrate in designing a module which determines trading rules by machine learning. We use Genetic Algorithm (henceforth GA), and we build trading rules by learning parameters of technical indices. Our contribution in this paper is that we propose new fitness functions in GA, in order to make them robuster to change of market trends. Although profits were used as a fitness function in the previous study, we propose the fitness functions which pay more attention to not making a loss than to gaining profits. As a result of our experiment using real TSE(Tokyo Stock Exchange) data for eight years, the proposed method has outperformed the previous method in terms of gained profits.
Yuya Arai, Ryohei Orihara, Hiroyuki Nakagawa, Yasuyuki Tahara, Akihiko Ohsuga
Watching Subgraphs to Improve Efficiency in Maximum Clique Search
Abstract
This paper describes a new technique referred to as watched subgraphs which improves the performance of BBMC, a leading state of the art exact maximum clique solver (MCP). It is based on watched literals employed by modern SAT solvers for Boolean constraint propagation. The paper proposes to watch two subgraphs of critical sets during MCP search to efficiently compute new steps and bounds. Reported results validate the approach as the size and density of problem instances rise, while achieving comparable performance in the general case.
Pablo San Segundo, Cristobal Tapia, Alvaro Lopez
Decision Making and Optimization for Inspection Planning under Parametric Uncertainty of Underlying Models
Abstract
Certain fatigued structures must be inspected in order to detect fatigue damages that would otherwise not be apparent. A technique for obtaining optimal inspection strategies is proposed for situations where it is difficult to quantify the costs associated with inspections and undetected failure. For fatigued structures, for which failures (fatigue damages) are only detected at the time of inspection, it is important to be able to determine the optimal times of inspection. Fewer inspections will lead to lower fatigue reliability of the structure upon demand, and frequent inspections will lead to higher cost. When there is a fatigue reliability requirement, the problem is usually to develop an inspection strategy that meets the reliability requirements. It is assumed that only the functional form of the underlying invariant distribution of time-to-failure is specified, but some or all of its parameters are unspecified. The invariant embedding technique proposed in this paper allows one to construct an optimal inspection strategy under parametric uncertainty. This strategy represents a sequence of inspection times satisfying the specific criterion, which takes into account the predetermined value of the conditional fatigue reliability of the structure. A numerical example is given.
Nicholas Nechval, Gundars Berzins, Vadim Danovich, Konstantin Nechval
Topological Feature Mining for Rambling Activities
Abstract
A method for investigating rambling activities of moving objects is proposed. The goal is to construct common metrics used in various environments for characterizing the trajectory followed by rambling objects. Rambling activities are multi-stop,multi-purpose trips with trajectories with many intersections.Mathematical knot theory is introduced to examine the topological relation between intersections. The trajectories in an environment are represented in a vector space consisting of prime knots. Like a prime number, a prime knot is universal; thus, it is possible to compare the features of rambling activities across environments. An experiment using real-world taxi trajectories demonstrated that our method effectively classifies rambling activities according to daytime, nighttime, and a special event.
Masakatsu Ohta, Miyuki Imada

Pattern Recognition

Frontmatter
Confusion Matrix Based Reweighting
Abstract
This paper introduces a method to rebalance the output of classification algorithms using the corresponding confusion matrices. This is done by modifying the classification output, i.e. reweighting predictions, when they can be interpreted as probabilities. The method is evaluated and analyzed via experiments involving a number of classifiers and both standard and real life datasets. Our results show that confusion matrix based reweighting can be used to achieve certain kinds of balance in classification, while maintaining the same level of accuracy.
Vincent Damian Warmerdam, Zoltán Szlávik
Web Performance Forecasting with Kriging Method
Abstract
Due to the substantial growth of communication network in last years, the access to the Internet network is crucial for the society. Therefore, there is a necessity of research on Web systems forecasting. This work presents a proposal of the application of the geostatistical estimation - the Kriging method, which give spatio-temporal information about forecast of network throughput. The database was created on the basis of Multiagent Internet Measurement System MWING. In the research the connections between an agent in Gdańsk and European serverswere considered. The preliminary structural analysis of the data, which are necessary to use the Kriging method was conducted. Next a spatial forecast of the total time of downloading data from Web servers with a four days time advance was calculated. The results were analyzed and comparedwith other simulationmethods results from the same database.
Leszek Borzemski, Anna Kamińska-Chuchmała

Problem Solving

Frontmatter
Application of the Swarm Intelligence Algorithm for Investigating the Inverse Continuous Casting Problem
Abstract
In the paper a proposal of procedure for solving the inverse problem of continuous casting is presented. The proposed approach consists in applying the swarm intelligence algorithm imitating the behavior of ants for minimizing an appropriate functional which enables to determine the unknown cooling conditions of the process.
Edyta Hetmaniok, Damian Słota, Adam Zielonka
Estimating Mental States of a Depressed Person with Bayesian Networks
Abstract
In this work in progress paper we present an approach based on Bayesian Networks to model the relationship between mental states and empirical observations in a depressed person. We encode relationships and domain expertise as a Hierarchical Bayesian Network. Mental states are represented as latent (hidden) variables and the measurements found in the data are encoded as a probability distribution generated by such latent variables; we provide examples of how the network can be used to estimate mental states.
Michel C. A. Klein, Gabriele Modena
Multi-objective Optimization Algorithms for Microchannel Heat Sink Design
Abstract
This paper investigates the performance of four multi-objective optimization algorithms namely the GAM, MOGA, SPEA2 and NSGA-II on the optimization of a microchannel heat sink based on the total thermal resistance and pumping power. Two case studies with different formulation methodologies were selected for the optimizations. The optimizations results showed that both SPEA2 and NSGA-II algorithms exhibited excellent performance in terms of the number of the optimal solutions, maintaining the desirable diversity and convergence speed toward the Pareto optimal front as compared to GAM and MOGA.
Ahmed Mohammed Adham, Normah Mohd-Ghazali, Robiah Ahmad
Solution of the Inverse Stefan Problem by Applying the Procedure Based on the Modified Harmony Search Algorithm
Abstract
In the paper we present an algorithm for solving the two-phase onedimensional inverse Stefan problem with the temperature measurements given in selected points of the solid phase as an additional information. Proposed procedure bases on the modified Harmony Search algorithm and solving of the considered problem consists in reconstruction of the function describing the heat transfer coefficient.
Edyta Hetmaniok, Damian Słota, Adam Zielonka, Roman Wituła

Robotics

Frontmatter
Cascade Safe Formation Control for a Fleet of Underactuated Surface Vessels Using the DCOP Approach
Abstract
This paper considers the formation control of multiple underactuated surface vessel. A distributed cooperative control using the relative information among neighboring vehicles is proposed such that the flock of multiple vehicles forms a desired geometric formation pattern whose center moves along a desired trajectory. In order to guarantee safe flock navigation and interaction of vehicles with the environment, we propose to extend the designed formation tracking controller to more sophisticated algorithm that prevent the vehicles from colliding with environmental obstacles with unknown sizes and locations based on a Decentralized Constrained Optimizing Problem “DCOP” strategy.
Alejandro Rozenfeld, Jawhar Ghommam, Rodrigo Picos, Gerardo Acosta
UMH’s Navigation in Unknown Environment Based on Pre-planning Guided Fuzzy Reactive Controller
Abstract
Based on the sparse A* search (SAS) algorithm and the fuzzy reactive controller (FRC), we propose a novel method of navigation for unmanned helicopter (UMH). SAS is applied to plan a path based on the understanding of pre-known obstacles and threats. Then, UMH travels along the path. The FRC, which employs Mamdani fuzzy methodology and pre-planning guidance, monitors the flight process and react in real-time to keep flight safety. Simulations show that this approach can find out the global optimal path and realize dynamic navigation for UMH.
Xuzhi Chen, Zhijun Meng, Wei He, Kaipeng Wang

Special Session on Decision Support for Safety-Related Systems

Frontmatter
Developing Context-Free Grammars for Equation Discovery: An Application in Earthquake Engineering
Abstract
In the machine-learning area of equation discovery (ED) context-free grammars (CFG) can be used to generate equation structures that best describe the dependencies in a given data set. Our goal is to investigate the possible strategies of incorporating domain knowledge into a CFG, and evaluate the effect on the obtained results in the ED process. As a case study, the Lagramge ED system is used to discover equations that predict the peak ground acceleration (PGA) in an earthquake event. Existing equations for PGA represent rich domain knowledge and are used to form three different CFGs. The obtained results demonstrate that the inclusion of domain knowledge in the CFG which is neither too general, neither too specific, may lead to new, high-precision equation models for PGA.
Štefan Markič, Vlado Stankovski
Neural Networks to Select Ultrasonic Data in Non Destructive Testing
Abstract
In recent years, research concerning the automatic interpretation of data from non destructive testing (NDT) is being focused with an aim of assessing embedded flaws, quickly and accurately in a cost effective fashion. This is because data yielded by NDT techniques or procedures are usually in the form of signals or images which often do not present direct information of the structure’s condition. Signal processing has provided powerful techniques to extract the desired information on material characterization and defect detection from ultrasonic signals. The imagery available can add additional and significant dimension in NDT information. The task of this work is to minimize the volume of data to process replacing ultrasonic images type TOFD by sparse matrix, as there is no reason to store and operate on a huge number of zeros, especially when large structures are inspected. A combination of two types of neural networks, a perceptron and a Self Organizing Map (SOM) of Kohonen is used to distinguish between a noise signal from a defect signal in one hand, and to select the sparse matrix elements which correspond to the locations of the defects in the other hand. This new approach to data storage will provide an advantage for the implementations on embedded systems as it allows the normalization of the sparse matrix by fixing its dimension.
Thouraya Merazi Meksen, Malika Boudraa, Bachir Boudraa

Special Session on Innovations in Intelligent Computation and Applications

Frontmatter
Stairway Detection Based on Extraction of Longest Increasing Subsequence of Horizontal Edges and Vanishing Point
Abstract
Detection of stair region from a stair image is very crucial for autonomous climbing navigation and alarm system for blinds and visually impaired. In this regard, a framework is proposed in this paper for detecting stairways from stair images. For detection of the stair region, a natural property of stair is utilized that is steps of a stair appear sorted by their length from top to bottom of the stair. Based on this idea, initially, horizontal edge detection is performed on the stair image for detecting stair edges. In second step, longest horizontal edges are extracted from the edge image through edge linking. In third step, longest increasing subsequence (LIS) algorithm is applied on the horizontal edge image for extracting stair edge. Finally, the vanishing point is calculated from these sets of horizontal lines to confirm the detection of stair candidate region. Various stair images are used with a variety of conditions to test the proposed framework and results are presented to prove its effectiveness.
Kaushik Deb, S. M. Towhidul Islam, Kazi Zakia Sultana, Kang-Hyun Jo
A Heuristic to the Multiple Container Loading Problem with Preference
Abstract
In this paper, we address the Multiple Container Loading Problem with Preference (MCLPP). It is derived from the real problems proposed by an audio equipment manufacturer. In the MCLPP, the numbers of various types of boxes can be adjusted based on box preferences.We need to add or delete boxes in a restricted way so that the ratio of the total preference of boxes to the total cost of containers is maximized.We develop a three-step search scheme to solve this problem. Test data is modified from existing benchmark test data for the multiple container loading cost minimization problem. Computational experiments show our approach is able to provide high quality solutions and they satisfy the need of the manufacturer.
Tian Tian, Andrew Lim, Wenbin Zhu
Backmatter
Metadata
Title
Contemporary Challenges and Solutions in Applied Artificial Intelligence
Editors
Moonis Ali
Tibor Bosse
Koen V. Hindriks
Mark Hoogendoorn
Catholijn M. Jonker
Jan Treur
Copyright Year
2013
Publisher
Springer International Publishing
Electronic ISBN
978-3-319-00651-2
Print ISBN
978-3-319-00650-5
DOI
https://doi.org/10.1007/978-3-319-00651-2

Premium Partner

    Image Credits