Intelligent Systems and Technologies

This chapter introduces a number of intelligent methodologies and techniques stemmed from Artificial Intelligence (AI). An overview of various intelligent models arisen from expert systems, artificial neural networks, fuzzy logic, genetic algorithms, decision trees, and agent technologies is presented. Application examples of these intelligent models in various domains are also presented. Then, the contribution of each chapter included in this book is described. A summary of concluding remarks is presented at the end of the chapter.

In complicated industrial and organizational relationships between employees or workers, it is difficult to offer good opportunities for their psychological and skill growth, since our progressive information and industrial societies have created many menial tasks. Redesigning subgroups in a personnel network for work rotation is a method that organizes employees appropriately to address these types of problems. In this article, we focus on a fuzzy density analysis of subgroups where employees are connected via their relationships with fuzzy values. However, it becomes extremely hard to rearrange those employees when there are vast numbers of them, meaning it is an NP-hard problem. In the personnel network, all the possible cohesive subgroups can be detected by making the best use of DNA oligonucleotides, which is also applied as a method by which to rearrange employees via fuzzy values based on the results of a fuzzy density analysis.

Individuals encoding potential rules to model an actual partition of samples into categories may be evolved by means of several well-known evolutionary classification techniques. Nevertheless, since a canonical evolutionary algorithm progresses towards one (global or local) optimum, some special construction or certain additional method are designed and attached to the classifier in order to maintain several basins of attraction of the different prospective rules. With the aim of offering a simpler option to these complex approaches and with an inspiration from the state-of-the-art cooperative coevolutionary algorithms, this chapter presents a novel classification tool, where rules for each class are evolved by a distinct population. Prototypes evolve simultaneously while they collaborate towards the goal of a good separation, in terms of performance and generalization ability. A supplementary archiving mechanism, which preserves a variety of the best evolved rules and eventually yields a thorough and diverse rule set, increases the forecasting precision of proposed technique. The novel algorithm is tested against two real-world decision problems regarding tumor diagnosis and obtained results demonstrate the initial presumption.

Four different localized representation methods and two manifold learning procedures are compared in terms of recognition accuracy for several face processing tasks. The techniques under investigation are: a) Non-negative Matrix Factorization (NMF); b) Local Non-negative Matrix Factorization (LNMF); c) Independent Components Analysis (ICA); d) NMF with sparse constraints (NMFsc); e) Locality Preserving Projections (Laplacianfaces); and f) Orthogonal Projection Reduction by Affinity (OPRA). A systematic comparative analysis is conducted in terms of distance metric used, number of selected features, and sources of variability on AR, Yale, and Olivetti face databases. Results indicate that the relative performance ranking of the methods is highly task dependent, and varies significantly upon the distance metric used.

The paper explores the flow (positively) invariant sets with respect to the trajectories of recurrent neural networks (RNNs). There are considered two types of sets, namely with arbitrary time-dependence and exponentially decreasing. The sets can have general shapes, defined by Hölder p-norms. The first part of the paper develops criteria for testing the existence of invariant sets. The second part analyzes the connections between the invariant sets and the stability of the RNN equilibrium points. Besides the novelty and the theoretical interest of the whole approach, the results corresponding to the usual p-norms (p = 1,2, ∞ ) yield numerically tractable procedures for testing the invariance properties.

Bioinformatics is a very interesting an active area that tackles difficult problems with lots of data that may have noise, missing values, uncertainties, etc. This chapter shows how the techniques that Soft Computing provides are appropriate to solve some Bioinformatics problems. This idea is then illustrated by showing several resolution techniques for one of the key problems of the Bioinformatics area: the Protein Structure Comparison problem.

Legacy codes are valuable assets that are difficult or even impossible to be rebuild each time when the underlying computing architecture is changed at conceptual or physical levels. New software engineering technologies, like the ones supporting the concept of service oriented architecture, promises to allow the easy use of the legacy codes. Despite this promise, the transition towards a service oriented architecture is not a straightforward task especially for the legacy codes with a rich user interface: the part mostly affected by the architectural change is the interface. This paper describes the transforming path that was followed in the case of a ten years old expert system for solving initial value problems for ordinary differential equations, emphasizing how the new interface should look like to preserve the code functionality despite the conceptual switch from a human user to a software code. The use of statefull Web services allows also preserving the large database of problems and methods of the expert code, as well as its special functionality that allows the extension of this database, in the benefit of any user of the service, human or another software code. This transformation path can be easily followed by other similar legacy codes, especially those designed for scientific computing. Moreover, the part of the expert system specially designed to deal with parallel computing techniques is extended in order to take advantage of the latest achievements in what concerns the hardware architectures, more precisely, to be able to exploit the advantages of multicore systems. In this context it is proved that parallelism across the numerical method that requires a small number of processors and can profit from the shared memory available to all cores can improve the response time of the expert code.

Lexical ontologies are fundamental resources for any linguistic application with wide coverage. The reference lexical ontology is the ensemble made of Princeton WordNet, a huge semantic network, and SUMO&MILO ontology, the concepts of which are labelling each synonymic series of Princeton WordNet. This lexical ontology was developed for English language, but currently there are more than 50 similar projects for languages all over the world. RoWordNet is one of the largest lexical ontologies available today. It is sense-aligned to the Princeton WordNet 2.0 and the SUMO&MILO concept definitions have been translated into Romanian. The paper presents the current status of the RoWordNet and some recent enhancement of the knowledge encoded into it.

Fuzzy querying means selecting the database objects that more or less respect a non-Boolean condition. The relative object qualification is defined as a new kind of user’s preference expressing; related with this, the AMONG operator is able to compute the fulfillment degree of the relative selection criteria. Two special cases of the relative object qualification are discussed in the paper; they are referring to qualifying database objects relatively to particular values of other attributes. Solutions to model and to evaluate them are proposed.

Human-computer dialogue is already a rather mature research field [10] that already boiled down to several commercial applications, either service or task-oriented [11]. Nevertheless, several issues remain to be tackled, when unrestricted, spontaneous dialogue is concerned: barge-in (when users interrupt the system or interrupt each other) must be properly handled, hence Voice Activity Detection is a crucial point [13]. Moreover, when multi-party interactions are allowed (i.e., the machine engages simultaneously in dialogue with several users), supplementary robustness constraints occur: the speakers have to be properly tracked, so that each utterance is mapped to a certain speaker that had produced it. This is needed in order to perform a reliable analysis of input utterances [2].

The passive greenhouses are independent of any conventional energetic infrastructures (electricity, gas, hot water, etc.) They are relying exclu sively on alternative energy sources: sun, wind, geo-thermal, etc. Their extensive use facilitates a massive ecological reconstruction of our pla net, which could eventually reduce the CO₂ con cen tration in the atmosphere and the consequent global heating. The paper is approaching the passive greenhouses’ control, proposing a fuzzy-interpolative controller with internal model. Simulations performed with a structural model are provided.

There are many applications where the exact position and dynamics of different objects are needed in real time. We propose a system that is able to locate simultaneously several “objects” and to present them, in real time, on a map. The system is dedicated mainly to airports for tracking maintenance cars and persons (in this last case the system works as a personal locator device) and to avoid disasters that could happen on the runway. Several results and aspects of the system are investigated and presented.

Today, Learning Management Systems are the most popular technique for delivering learning material to students electronically. Despite the success and popularity of such systems, there is evidence which highlights that courses which rely solely on Learning Management Systems, have a significantly higher dropout rate than that experienced by courses operating in a classroom environment. Factors such as an absence of interaction with tutors and other students, combined with a lack of stimulation caused by unappealing user interfaces can contribute to the high attrition rates. This chapter examines these issues and explores possible solutions. Particular emphasis is placed on the use of Three Dimensional onscreen Graphical User Interfaces to stimulate users which can be combined with multi-user and synchronous communication techniques to facilitate meaningful interaction. Research indicates that there is also a need to include the social aspects of classroom-based teaching within e-learning environments, an issue which has not been fully explored in the literature. This chapter describes our own system, called Collaborative Learning Environments with Virtual Reality, the design of which includes tools for social interaction between students. To date no major evaluation of Three Dimensional interfaces for e-learning has been conducted. This chapter describes the approach and positive results of an evaluation conducted to determine the usability of CLEV-R.

The technical core of an e-leaning project is the LMS (Learning Management System) that is being used. This chapter reviews several e-learning platforms and discusses the importance of open source e-learning platforms and analyzes the total costs of implementation/educational output ratio. The result of the assessment shows that the open platform Moodle outperforms the majority of other platforms and it is used in a wide variety of e-learning projects at different academic levels, both college and university. Finally, we describe a Moodle LMS case study, the eCNDS (Computer Network and Distributed Systems E-Laboratory) at The Faculty of Electronics and Telecommunications from Technical University “Gheorghe Asachi” of Iasi.

We describe in this paper a complete informational model based on the geographical information system technology for organizing the Romanian territory archaeological information and to put it in an electronically accessible form, while remaining similar in content with a classic archaeological atlas. Geographical and archaeological databases were designed and implemented, along with interfaces for their manipulation and an interface for archaeological atlas consultation. The system has already been implemented using information specific to a narrow archaeological area, in the hydrographical basin of the Bahluiet River in the Iasi County.