Articial Intelligence

This paper introduces a new model of artificial cognitive architecture for intelligent systems, the Neuromodulating Cognitive Architecture (NEUCOGAR). The model is biomimetically inspired and adapts the neuromodulators role of human brains into computational environments. This way we aim at achieving more efficient Artificial Intelligence solutions based on the biological inspiration of the deep functioning of human brain, which is highly emotional. The analysis of new data obtained from neurology, psychology philosophy and anthropology allows us to generate a mapping of monoamine neuromodulators and to apply it to computational system parameters. Artificial cognitive systems can then better perform complex tasks (regarding information selection and discrimination, attention, innovation, creativity,…) as well as engaging in affordable emotional relationships with human users.

The application of cross-linking resin is an effective method for improving and controlling dimensional stability, such as the shrinkage of viscose single jersey knits. However, such treatment often leads to a significant deterioration in the bursting strength of treated fabrics. In this regard, resin treatment using a softening agent can be an additional potential solution for retaining the bursting strength of treated fabrics. Resin treatment is one kind of chemical finishing process that inhibits cellulosic textile fibre swelling during wetting, provides fibre resistance to deformation and prevents shrinkage. The key objective of this study was to model the effect of resin-finishing process variables for predicting the shrinkage control and bursting strength of viscose single jersey knitted fabrics. The MATLAB (Version 8.2.0.701) fuzzy expert system was used to model the optimum resin and softener concentrations, as well as the best curing time for the prediction of maximum shrinkage control with a minimum loss in fabric bursting strength. The optimal process variables were found to be a resin concentration of 75 g/l, a softener concentration of 45 g/l and a curing time of 225 seconds. The fuzzy expert model developed in this study was validated using experimental data. It was found that the model has the ability and accuracy to predict fabric shrinkage and bursting strength effectively in the non-linear field.

Anomaly detection is a pattern recognition task whose goal is to report the occurrence of abnormal or unknown behavior in a given system being monitored. In this paper we propose a general procedure for the computation of decision thresholds for anomaly detection in mobile communication networks. The proposed method is based on Kohonen's Self-Organizing Map (SOM) and the computation of nonparametric (i.e. percentile-based) confidence intervals. Through simulations we compare the performance of the proposed and standard SOM-based anomaly detection methods with respect to the false positive rates produced.

Drawing on feminist theory, this paper uses a feminist lens to analyze the gendered representations and discourses of artificial intelligence in cinema history. In particular, this paper conducts an in-depth analysis of the representations of female robots and AI in Spike Jonze’s Her (2013) and Alex Garland’s Ex Machina (2013).

This paper received First Class Honors at Trinity College, Dublin.
Vanessa graduated with Distinction in B.A. English Literature and Media Studies.

—Generative Adversarial Networks (GANs) are a class of Artificial Neural Network architectures for generating realistic data distributions from a small number of latent variables. The latent variables are typically drawn IID from a Normal distribution and fed as input. Empirically, it has been shown that GANs are able to produce realistic images from as few as 100 latent variables. While numerous studies have focused on modifying the original GAN architecture, few have explored the structure of the input latent variables. In this study we propose placing structure on the input for aiding GANs to converge faster, lead insight into the structure of the underlying data distribution, and produce potentially more creative outputs. To achieve a GAN with such constraints, we call our proposed architecture RemixNet. In RemixNet the latent variables are a result of multiple draws from our existing dataset and " remixed " into a new distribution. This idea of combining existing data into new data is inspired from the artistic and musical practice of collage making and remixes. For example, an artist may take an existing recording of music, modify each with a filter and combine to form a new composition. We show several experiments on the MNIST dataset to gain some intuition on various RemixNet architectures. We also compare empirically RemixNet with GAN and show that the RemixNet architecture converges significantly faster to realistic images.

In 1962, a checkers-playing program written by Arthur Samuel defeated a self-proclaimed master player, creating a sensation at the time for the fledgling eld of computer science called articial intelligence. The historical record refers to this event as having solved the game of checkers. This paper discusses achieving three dierent levels of solving the game: publicly (as evidenced by Samuel's

Área do Direito: Civil; Processual; Digital Resumo: Há aplicações concretas da Inteligência Artificial na área jurídica, tanto na iniciativa privada, quanto no poder público. O Poder Judiciário começa a empregar essa tecnologia em tarefas burocráticas. Mas há a possibilidade de aplicação de programas de Inteligência Artificial para auxiliar ou até mesmo automatizar a tomada de decisão judicial. O uso da Inteligência Artificial no processo decisório deve ocorrer progressivamente, pautando-se pela precaução, e com constante acompanhamento dos resultados alcançados, a fim de se assegurar a construção e operação de sistemas confiáveis, dotados de solidez e que respeitem os princípios éticos e jurídicos. Palavras-chave: Inteligência Artificial-Tomada de decisão-Automação-Processo judicial-Poder Judiciário Abstract: There are concrete applications of Artificial Intelligence in the legal area, both in the private sector and in the government. The Judiciary is beginning to employ this technology in bureaucratic tasks. But there is the possibility of applying Artificial Intelligence programs to assist or even automate judicial decision-making. The use of Artificial Intelligence in the decision-making process should occur progressively, guided by precaution, and with constant monitoring of the results achieved, in order to ensure the construction and operation of reliable systems, endowed with solidity and that respect ethical and legal principles.

The Predictive Casino is a casino that utilizes the latest technological developments to connect with its customers to deliver an exceptional personalized experience to each and every one of its patrons. Today, technology such as AI, Machine Learning, Augmented Reality, IoT, Real-time stream processing, social media, and wearables are altering the Customer Experience (CX) landscape and casino operators need to jump aboard this fast moving technology or run the risk of being left out in the cold.
The Predictive Casino reveals how these and other technologies can help shape the customer journey. The book details how the five types of analytics—descriptive, diagnostic, predictive, prescriptive, and edge analytics—affect not only the customer journey, but also just about every operating function of the casino.
Facial recognition technology can spot a customer stepping onto a casino bus at the Macau/China border and that set off alerts that can notify a host on the floor, a restaurant manager, a dealer, or even the hotel’s GM should the player be a high-end VIP. A whole other sequence of events gets triggered as the player’s favorite table is prepared, his favorite, and his or her Theo gets added to a real-time table games revenue management model that takes into account his personal play. Labor needs are also considered and alerts can be sent to the required or unneeded staff.
An IoT connected casino can make its operations smart. Connected devices can help with inventory optimization, supply chain management, labor management, waste management, as well as keep its data centers green and its energy use smart. 
Social media is no longer a vanity platform, but rather a place to both connect with current customers as well as court new ones. It is also a powerful branding channel that can be utilized to both understand a casino's position in the market, as well as a place to benchmark its position against its competitors.
Today, technology moves at break-neck speed and it can offer the potential of anticipatory capabilities, but it also comes with a confusing variety of technology and technological terms--Big Data, Cognitive Computing, CX, Data Lakes, Hadoop, Kafka, Personalization, Spark, etc., etc. The Predictive Casino will help make sense of it all, so that a casino executive can cut through the confusing technological jargon and understand why a Spark-based real-time stream processing data stream might be preferable over a TIBCO one, or an IBM one. This book will help casino executives break through the technological clutter so that they can deliver an unrivaled customer experience to each and every patron coming through their doors.

Some companies are hoping to use AI--and the treasure trove of our social media postings--to create convincing chatbot simulations of us after we die. What are the ethical worries surrounding these "legacy chatbots" that promise to keep us close to our departed loved ones? A case study authored by Colin Frick & Scott R. Stroud. More case studies at www.mediaethicsinitiative.org

Artificial intelligence is being touted as a new wave of machinic processing and productive potential. Building on concepts starting with the invention of the term artificial intelligence in the 1950s, now, machines can supposedly not only see, hear, and think, but also solve problems and learn, and in this way, it seems that actually there is a new form of humiliation for humans. This article starts with a historical overview of the forerunners of artificial intelligence, where ideas of how intelligence can be formulated according to philosophers and social theorists begin to enter the work sphere and are inextricably linked to capitalist production. However, there always already has been an artificial intelligence in power in, on the one hand, technical machines and the social machine money, and on the other, humans, making both sides (machines and humans), an interface of their mutual capitalist socialisation. The question this piece addresses is, then, what kind of capitalist socialisation will the actual forms of artificial intelligence bring?

The aim of the text is to clarify why machines are economically productive only in capitalism and therefore in our society are capitalistic machines. They are capitalist not only because they increase the productive power of the capitalist valorisation, but this valorisation first of all is producing these machines, or at least it produces their productivity and hence 'the machinic' of machines. To understand this production of the machinic, we must understand them, as, for example, Heidegger, Simondon or Deleuze and Guattari have shown, from their context: From their non-technical essence, from their connection with other machines and from the social essence of the machinic. But in this context, first of all and in the last instance, we have to understand with Marx their entanglement with the capitalist valorisation. This can be shown for three different types of machines: The physical machine, the calculation machine and the social machine: Money. What all three have in common and almost defines them as machines is that all three naturalise relations by quantifying them. The classical physical machine quantifies the relation of nature, the calculation machine quantifies information and meaning, and the money machine quantifies the relations of our society. I will concentrate on the physical and the money machine only. The technique to quantify is for both the same: Measurement. This quantification and naturalisation by measurement is why both are-although or especially because they are opposed types of machines-interfaces to the capitalist valorisation process, and in this functioning as interfaces, we have to search their non-technical essence.

—Recently, Convolutional Neural Networks (CNNs) have become a preferred deep learning artificial neural network of choice for computer assisted medical image analysis. These models are structured as a series of multiple hierarchical processing layers that can automatically learn feature representations from raw images. CNNs have in the past not been in common use, especially in the medical imaging field, due to issues such as insufficient image datasets. The revolution in CNN models has been attributed to powerful parallel processing hardware architectures, increasing number of image datasets and improved training strategies. Utilizing these deep learning techniques are enabling medical experts such as pathologists to utilize artificial intelligence to transform the world of medicine for faster and more accurate diagnoses. In this paper, a two stage model for classifying breast histopathological images is proposed. In the first stage, a CNN is used for extracting features from the images through a feature learning process. The extracted features are then used in the second stage to training classical machine learning models that include the Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Logistic Regression (LR) models. The SVM classifier performs best with accuracies of up to 99.84%.

L’intelligenza è virtualmente inconoscibile: ciò di cui possiamo fare esperienza sono atti, attraverso cui l’esplicarsi dell’intelligenza influisce sulla realtà esterna al soggetto e può essere campionato, in una dimensione intersoggettiva. Come nel test di Turing, ciò che conosciamo sono gli effetti di un altro, la cui realtà (il cui noumeno) resta per noi nascosto dietro un paravento. È dunque possibile, con questi presupposti, determinare se la natura di questo altro sia umana o artificiale? Ovviamente no.
Ma soprattutto, per citare lo scambio di battute tra un umano e un host – avanzato animatrone al servizio dei visitatori all’interno del parco a tema di Westworld (secondo episodio della prima stagione): quando William, l’uomo, chiede “Are you real?” (sei reale?) la risposta è “If you can’t tell, does it matter?”: se non riesci a distinguere la differenza, la risposta non ha importanza.
L’attribuzione di umanità a un’entità dotata di intelligenza diviene un esercizio privo di fondamento teorico. D’altronde molta fantascienza, sulla pagina scritta come sul piccolo e grande schermo, si è divertita a mostrare come nel momento in cui l’identità di un essere creato imita perfettamente quella umana, nel momento in cui la differenza tra umano e artificiale diventa letteralmente impercettibile, la domanda stessa sulla sua natura cessa di avere senso. Ad essere chiamata in causa è piuttosto la fondazione antropocentrica del nostro criterio morale, si prenda come termine di confronto un’identità intesa come insieme di facoltà e caratteri smaterializzati, dai “risvegli” di coscienze nate in universi finzionali, come Solo in Nirvana (Salvatores 1997), piuttosto che emerse dalla matassa di informazione del web, come il Webmind della trilogia del risveglio di Robert J. Sawyer (2009-2011), o dalla complessità di un sistema operativo come la Her del film omonimo (Jonz, 2013). O si tratti al contrario di ricreazione del corpo nella sua precipua fisicità, come quella reificata e sensuale dei droidi di Ex_machina (Garland, 2014), o, ancora, si tratti di creature che dell’uomo assommano entrambi gli aspetti, offrendone un duplicato tragicamente convincente, come gli androidi di Philip K. Dick portati sul grande schermo da Ridley Scott (Blade Runner, 1982) e Denis Villeneuve (Blade Runner 2049, 2017), o quelli di Michael Crichton (Westworld, 1973) rivisitati ora sul piccolo schermo da Jonathan Nolan e Lisa Joy per la HBO (2016-).

The aim of this paper is to define a new methodology that allows the comparison of the effectiveness among some of the major artificial intelligence techniques (random technique, taboo search, data mining, evolutionary algorithms). This methodology is applied in the sequencing production process in job shop environments, in a problem with N orders, and M machines, where each of the orders must pass through every machine regardless of its turn. These techniques are measured by the variables of total makespan time, total idle time, and machine utilization percentage.
Initially, a theoretical review was conducted and showed the usefulness and effectiveness of artificial intelligence in the sequencing production processes. Subsequently and based on the experiments presented, the obtained results showed that these techniques have an effectiveness higher than 95%, with a confidence interval of 99.5% measured by the variables under study.

ó Multi-Robot Systems (MRS) are, nowadays, an im- portant research area within Robotics and Articial Intelligence and a growing number of systems has been recently presented in the literature. Since application domains and tasks that are faced by MRS are of increasing complexity, the ability of the robots to cooperate can be regarded as a fundamental feature. In this paper,

Language games represent one of the most fascinating challenges of research in artificial intelligence. In this paper we give an overview of WebCrow, a system that tackles crosswords using the Web as a knowledge base. This appears to be a novel approach with respect to the available literature. It is also the first solver for non-English crosswords and it has been designed to be potentially multilingual. Although WebCrow has been implemented only in a preliminary version, it already displays very interesting results reaching the performance of a human beginner: crosswords that are "easy" for expert humans are solved, within competition time limits, with 80% of correct words and over 90% of correct letters.

Intervenção na Mesa "A Inteligência Artificial no RGPD europeu e na LGPD europeia", integrada no I Congresso Internacional Lusófono de Inteligência Artificial, Filosofia e Direito. Organizado pela Universidade Federal do Rio de Janeiro, dia 20 de setembro de 2021.

In this work, we underline the benefit of techniques derived from distributed artificial intelligence, i.e. multi-agent systems, to the study of economical behavior. It aims to focus on the level of individual behaviors, as a bottom-up approach to understand the rise of economical phenomena like price fluctuation within a financial market or volatility within a labor market. In this paper, we propose an agent-based model of human decision making: CODAGE (Cognitive Decision AGEnt). In the CODAGE model, the decision maker is modeled by an entire multi-agent system, where each agent is in charge a particular sub-process of the whole decision. The architecture is intended to be as generic as possible. It could be viewed as an agentbased decision framework, in which different decision heuristics and biases could be implemented. We illustrate this approach with a simulation of a small experimental financial market, for which our model was able to replicate some human decision behaviors.

Introdotto nel 2010, il Guiding Case System (GCS) cinese ha sin da sùbito attirato l’attenzione della dottrina occidentale (soprattutto — seppur non esclusivamente  — statunitense), stante la sua assoluta peculiarità. Infatti, benché ad uno sguardo superficiale esso possa apparire un ulteriore indice della progressiva convergenza tra sistemi giuridici e la stessa, usuale, definizione dell’istituto (descritto, con espressione ormai in voga, ma dal significato incerto, come una case law with Chinese characteristics) richiami alla mente la dottrina dello stare decisis, il GCS si discosta tanto dalla tradizione angloamericana da rendere inopportuno ogni riferimento alla stessa; d’altro canto, se esso mostra maggiori elementi di affinità con strumenti di formazione in via amministrativa di precedenti (più o meno) vincolanti che vanno diffondendosi nei sistemi (ormai solo tendenzialmente) di civil law — e, in particolare, con la súmula brasiliana —, neppure riesce perfettamente assimilabile ad alcuno di essi.
La reale comprensione dell’istituto richiede piuttosto di indagarne l’inquadramento nel sistema (giuridico, politico-istituzionale e culturale) cinese; si scopre, così, che esso non rappresenta che una tappa, significativa ma intermedia, di un fenomeno di dimensioni più ampie, e probabilmente di anche maggior interesse comparatistico, in quanto espressione di una tendenza comune a tutti gli organi giurisdizionali di vertice: l’institutional pragmatism della suprema Corte del Popolo (SPC), la cui attività negli ultimi decenni appare motivata, più che dalla volontà di obbedire al Partito o dalla compiuta interiorizzazione dell’ideologia comunista — che pure possono ispirare i singoli consiglieri —, dall’obiettivo di fondo di ritagliarsi un ruolo (maggiormente) autonomo nel panorama istituzionale del Paese e rafforzare « its own financial security and sociopolitical status ». Un percorso lungo e graduale, ma al quale l’intelligenza artificiale, più recentemente, ha dato una spinta propulsiva non indifferente, confermando, una volta di più, che « la tecnologia non è né buona né cattiva, ma non è neppure neutrale » .

One smart speaker to rule them all, one sensor to find them, one device to bring them all and in the Internet of Things bind them. Conversational User Interfaces (CUI) represent an interactive phenomenon that is disrupting social interactions as we knew them. The spectrum of legal issues that arises from these user-device relationships has a wide range of impacts on society. This paper addresses seven legal issues arising from these interactions that affect Privacy and Law concerning consumer protection, profiling, liability, security, neutrality, influence and data protection. It aims to prompt an interdisciplinary discussion between Human-Computer Interaction, legal and Privacy researchers in order to address the lack of regulation around aspects of CUI and stimulate legal, policy and design confrontations. CCS CONCEPTS • Applied computing → Law; • Security and privacy → Human and societal aspects of security and privacy; • Human-centered computing → Natural language interfaces; Empirical studies in HCI .

A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications.

Abstract—Search and Rescue scenarios offer a wide variety of issues for analysis and experimentation in robotics, from mechanical architecture up to AI research themes. In this paper after briefly describing our robot configuration, we address the main issues of autonomous rescue tasks. Moreover, we explain algorithms and methods used by our modules in order to achieve a semi-autonomous exploration and victim detection system. Index Terms—Search and Rescue Robots, Intelligent Sys-tems.

The development of cognitive vision systems that autonomously learn how to interact with their environment through input from sensors is a major challenge for the Computer Vision, Machine Learning and Artificial Intelligence communities. This paper presents a framework in which a symbolic inference engine is integrated with a perceptual system. The rules of the inference engine are learned from audio-visual observation of the world, to form an interactive perceptual agent that can respond suitably to its environment. From the video and audio input streams interesting objects are identified using an attention mechanism. Unsupervised clustering of the objects into perceptual categories generates a symbolic data stream. Inductive Logic Programming is then used to generalise rules from this symbolic data. Although in principle the framework could be applicable to a wide range of domains (perhaps of most interest to the automatic programming of robots), it is demonstrated here in simple game playing scenarios. First the agent observes humans playing a game, and then attempts to play using the learned perceptual categories and symbolic protocols.

The game of Go is one of the games that still withstand classical Artificial Intelligence approaches. Hence, it is a good testbed for new AI methods. Amongst them, Monte-Carlo led to promising results. This method consists of building an evaluation function by averaging the outcome of several randomized games. The paper introduces a new strategy, which we call Objective Monte-Carlo, to improve this evaluation. Objective Monte-Carlo is composed of two parts. The first one is a move-selection strategy that adjusts the amount of exploration and exploitation automatically. We show experimentally that it outperforms the two classical strategies previously proposed for Monte-Carlo Go: Simulated Annealing and Progressive Pruning. The second part of our algorithm is a new backpropagation strategy. We show that it gives better results than Minimax in this context. Finally we discuss the extension of this method to other problems.

Self-awareness is an aspect of consciousness that is highly developed in humans in comparison with other animals. A human being unaware of his or her personal characteristics, of what he or she knows and doesn't know, can do and cannot do, wants and doesn't want, has experienced and is experiencing, etc., would surely be dicult to communicate with naturally. Therefore

A pandemic is a contagious disease outbreak that happens over a large geographic area and affects a great portion of the population while new pathogens appear for which people have less immunity and no vaccines are available. The disease can spread from person to person in a very short time. Health workers are at greater risk of infection because of patients who are carriers. In the 21st century,where everyone is connected through digital technologies, information and communication technology (ICT) plays a critical role in improving healthcare for individuals and larger communities. ICT can be divided into a wide variety of application domains that signify its importance as a major technological paradigm. It is currently drawing large attention because of its potential to alleviate the burden on healthcare systems caused by the rise in chronic diseases, aging populations and pandemic situations. This study surveyed substantial knowledge on how effective ICT healthcare solutions can ...

Nowadays, artificial intelligence technologies are developing at an unprecedented rate. It is clear that the most important reason for this is the contributions provided by all branches of science that support artificial intelligence technologies. In the world, the areas where artificial intelligence technologies are recognized by the public are the robots used in the industrial sector, software playing intelligence games, and easily accessible programs that can translate language and the security sector. This study, It will focus on the security sector in terms of the areas where artificial intelligence contributes , and will seek an answer to the question of how artificial intelligence technologies can be used in crime prevention activities of the law enforcement especially in internal security. The aim of the study is to determine the areas of use of artificial intelligence technologies during the activities of law enforcement to prevent crime. The study was conducted and compiled on a theoretical basis by literature review. First, an answer to the question of what artificial intelligence technologies are will be sought, and then the relationship of artificial intelligence with security will be determined. Finally, the answer to the question of what aspects and how the law enforcement, which is a security actor, may need in artificial intelligence technology in its activities related to the prevention of crime will be determined./ Bugünlerde, yapay zekâ teknolojileri geçmiş ile hiç karşılaştırılamayacak ölçüde hızla gelişiyor. Bunun en önemli sebebinin yapay zekâ teknolojilerini destekleyen tüm bilim dallarının sağlamış olduğu katkılar olduğu açık. Dünyada, yapay zekâ teknolojilerinin kamuoyu tarafından tanınır olduğu alanlar; sanayi sektöründe kullanılan robotlar, zekâ oyunları oynayan yazılımlar, dil çevirisi yapabilen ve kolay ulaşılabilir programlar ile güvenlik sektörüdür. Bu çalışma; yapay zekânın katkı sağladığı alanlar bakımından güvenlik sektörüne odaklanacak ve özellikle iç güvenlikte kolluğun suç önleme faaliyetlerinde yapay zekâ teknolojilerinin nasıl kullanılabileceği sorusuna cevap arayacaktır. Bu çalışma ile kolluk kuvvetlerinin suçun önlenmesine ilişkin faaliyetlerinin yerine getirilmesi sırasında yapay zekâ teknolojilerinin kullanım alanlarının tespit edilmesi de amaçlanmaktadır. Çalışma, literatür taraması yapılarak teorik bir zeminde yürütülmüş ve derlenmiştir. İlk olarak yapay zekâ teknolojilerinin ne olduğu sorusuna cevap aranacak, müteakiben yapay zekânın güvenlik ile ilişkisi tanımlanacaktır. Son olarak ise, bir güvenlik aktörü olan kolluğun suçun önlenmesine ilişkin faaliyetlerinde yapay zekâ teknolojisinde hangi hususlarda ve nasıl ihtiyaç duyabileceği sorusunun cevabının tespiti yapılacaktır.

Monte Carlo simulations have been successfully used in classic turn-based games such as backgammon, bridge, poker, and Scrabble. In this paper, we apply the ideas to the problem of planning in games with imperfect information, stochasticity, and simultaneous moves. The domain we consider is real-time strategy games. We present a framework -MCPlan -for Monte Carlo planning, identify its performance parameters, and analyze the results of an implementation in a capturethe-flag game.

Artificial Intelligence is the real time solution for solving the problems in these days. The paper covers the contribution of the various other technologies like NLG, NLP, Big Data, Narrative Science, Cloud, and Machine Learning for the improvement of the systems of artificial intelligence. The relationship between artificial intelligence and the other technology forms has proved to be effective and it is evident that the relation will help in making the systems better.

The article aims at establishing a logical approach to class-based data modeling. After a discussion on class-based formalisms for data modeling, we introduce a family of logics, called Description Logics, which stem from research on Knowledge Representation in Artificial Intelligence. The logics of this family are particularly well suited for specifying data classes and relationships among classes, and are equipped with both formal semantics and inference mechanisms. We demonstrate that several popular data modeling formalisms, including the Entity-Relationship Model, and the most common variants of object-oriented data models, can be expressed in terms of specific logics of the family. For this purpose we use a unifying Description Logic, which incorporates all the features needed for the logical reformulation of the data models used in the various contexts. We also discuss the problem of devising reasoning procedures for the unifying formalism, and show that they provide valuable supports for several important data modeling activities.

Representing agent policies compactly is essential for improving the scalability of multi-agent planning algorithms. In this paper, we focus on developing a pruning technique that allows us to merge certain observations within agent policies, while minimizing loss of value. This is particularly important for solving finite-horizon decentralized POMDPs, where agent policies are represented as trees, and where the size of policy trees grows exponentially with the number of observations. We introduce a value-based observation compression technique that prunes the least valuable observations while maintaining an error bound on the value lost as a result of pruning. We analyze the characteristics of this pruning strategy and show empirically that it is effective. Thus, we use compact policies to obtain significantly higher values compared with the best existing DEC-POMDP algorithm.

The game of Go is one of the games that still withstand classical Artificial Intelligence approaches. Hence, it is a good testbed for new AI methods. Amongst them, Monte-Carlo led to promising results. This method consists of building an evaluation function by averaging the outcome of several randomized games. The paper introduces a new strategy, which we call Objective Monte-Carlo, to improve this evaluation. Objective Monte-Carlo is composed of two parts. The first one is a move-selection strategy that adjusts the amount of exploration and exploitation automatically. We show experimentally that it outperforms the two classical strategies previously proposed for Monte-Carlo Go: Simulated Annealing and Progressive Pruning. The second part of our algorithm is a new backpropagation strategy. We show that it gives better results than Minimax in this context. Finally we discuss the extension of this method to other problems.

The use of the agent/multi-agent system paradigm has increased sharply as an important field of research within the Artificial Intelligence area. In recent times, the application of this paradigm seems appropriate for solving complex problems which require intelligence and bounded response times. This paper presents Simba : an architecture based on Artis agents as its main component for the development of real-time multi-agent systems. The Artis agent architecture guarantees an agent response that satisfies all its critical temporal restrictions in a real-time environment. The main feature of Simba systems is their applicability for complex, distributed, real-time domains. The architecture allows the communication among agents taking into account their hard temporal restrictions.

Many service enterprise systems such as the airport departure systems are typical multistage multi- variable systems with non-linear complex interactions between stages. These systems function over a wide range of operating conditions and are subject to random disturbances, which further enhance the non-linear characteristics. Also, there are many uncertain factors which often makes it is dicult to describe the process

Digital text documents are spread in various formats, the most widely used formats today include word format, and PDF format. This research will try to make text search application in text document using vector space approach model. The document format used is a PDF document. Text in PDF will be extracted and then made rank using vector space model. The PDF document consists of ten pages and each page contains a hadith. In general the system can search from the PDF document quite well and able to display the list of results in accordance with the relevance rank with the question.

The use of the agent/multi-agent system paradigm has increased sharply as an important field of research within the Artificial Intelligence area. In recent times, the application of this paradigm seems appropriate for solving complex problems which require intelligence and bounded response times. This paper presents Simba: an architecture based on Artis agents as its main component for the development of real-time multi-agent systems. The Artis agent architecture guarantees an agent response that satisfies all its critical temporal restrictions in a real-time environment. The main feature of Simba systems is their applicability for complex, distributed, real-time domains. The architecture allows the communication among agents taking into account their hard temporal restrictions. In order to show the use of systems of this kind, the paper describes the design of a multi-agent system for the distributed intelligent control of a residential building.

The DARPA Urban Challenge required robots to drive 60 miles on suburban roads while following the rules of the road in interactions with human drivers and other robots. Tartan Racing's Boss won the competition, completing the course in just over 4 hours. This paper describes the software infrastructure developed by the team to support the perception, planning, behavior generation, and other artificial intelligence components of Boss. We discuss the organizing principles of the infrastructure, as well as details of the operator interface, interprocess communications, data logging, system configuration, process management, and task framework, with attention to the requirements that led to the design. We identify the requirements as valuable re-usable artifacts of the development process.

Many service enterprise systems such as the airport departure systems are typical multistage multi- variable systems with non-linear complex interactions between stages. These systems function over a wide range of operating conditions and are subject to random disturbances, which further enhance the non-linear characteristics. Also, there are many uncertain factors which often makes it is dicult to describe the process

This chapter is a transdisciplinary study on the fundaments of cognition, considering this process at human level as the combination of biological and (multi)cultural values. The main idea is to describe the skill of human beings for using several heuristics for task-solving activities as a process of combining and blending techniques, something that is called here as “blended cognition”. This rich and complex way of dealing with multi-heuristic frameworks provides not only a more adequate model for the understanding of real human cognition, but also it is of the most interest for the design of creative and adaptive artificial intelligences