A Simple Solution for Improving the Effectiveness of Traditional Information Retrieval Systems

In this paper we present a system based on the LSA paradigm to improve the performance of a traditional information retrieval system. The proposed system aims to improve both the recall and the precision capabilities of traditional search engines thanks to a semantic query expansion and a subsequent semantic results filtering. A collection of 650 documents has been used to compare the performances of the proposed system with a traditional search engine. Experimental trials show the effectiveness of the proposed solution

MetaMeth: A tool for process definition and execution

Nowadays, several different tools are used in Software Engineering; in this work we are mainly interested to those supporting the design phases. These are usually classified in three categories: CASE, CAME, CAPE tools. MetaMeth is a CAME and a CAPE tool at the same time

Artificial intelligence techniques for cancer treatment planning

An artificial intelligence system, NEWCHEM, for the development of new oncology therapies is described. This system takes into account the most recent advances in molecular and cellular biology and in cell-drug interaction, and aims to guide experimentation in the design of new optimal protocols. Further work is being carried out, aimed to embody in the system all the basic knowledge of biology, physiopathology and pharmacology, to reason qualitatively from first principles so as to be able to suggest cancer therapies.

Three-dimensional geometrical models of the liver.

In this work we used a virtual approach to study the human liver by three-dimensional geometrical models. We built the models through computer aided geometric modelling techniques starting from pictures taken during both real dissections and diagnostic medical imaging. The results show in a complete modular synthesis and with a schematic iconology the structural organization of this organ in a logic sequence of layers and topographic and spatial relationship among its components. This approach represents an amazing support to clinical anatomy for teaching and research.

Context-Aware Visual Exploration of Molecular Databases

Facilitating the visual exploration of scientific data has\ud received increasing attention in the past decade or so. Especially\ud in life science related application areas the amount\ud of available data has grown at a breath taking pace. In this\ud paper we describe an approach that allows for visual inspection\ud of large collections of molecular compounds. In\ud contrast to classical visualizations of such spaces we incorporate\ud a specific focus of analysis, for example the outcome\ud of a biological experiment such as high throughout\ud screening results. The presented method uses this experimental\ud data to select molecular fragments of the underlying\ud molecules that have intere…

A genome based vision of multi-agent systems

A set of software agents can be programmed to provide a large but finite set of services, often defined during design phase. After an evolution of the external environment, the pre-defined services could be unable to satisfy the requested quality. In this work it is proposed an agent framework capable to adapt the agents in order to improve the quality of services provided by an agent society in correspondence with a modification of the external environment. These agents are based on a biologically inspired structure (genome), that de- fines all their behaviors and knowledges. The effectiveness of the approach is proved by a set of successful experimental results

Real-time low level feature extraction for on-board robot vision systems

Robot vision systems notoriously require large computing capabilities, rarely available on physical devices. Robots have limited embedded hardware, and almost all sensory computation is delegated to remote machines. Emerging gigascale integration technologies offer the opportunity to explore alternative computing architectures that can deliver a significant boost to on-board computing when implemented in embedded, reconfigurable devices. This paper explores the mapping of low level feature extraction on one such architecture, the Georgia Tech SIMD Pixel Processor (SIMPil). The Fast Boundary Web Extraction (fBWE) algorithm is adapted and mapped on SIMPil as a fixed-point, data parallel imple…

Testing wearable IoT applications through sensor virtualization

The development of distributed IoT applications requires the integration of data provided by different sensors embedded in multiple devices. As an example, an application for health monitoring in an assisted living scenario may include several wearable and fixed nodes each carrying different sensors and running specific code. Verifying that the application is properly working according to the specifications requires assessing that the code of each node behaves consistently in all the possible use cases. Tests involving sensor data may be difficult or costly to replicate realistically and this could also slow down the development of the application in its early stages. In this paper we intro…

Was King Arthur a King by Definition?

Current research in knowledge representation distinguishes between descriptional and assertional interpretations of semantic nets. This paper explores theoretical and applicative problems, which arise from that distinction in a historic domain. A prolog implementation of KL-ONE is used as a vehicle to compare the various alternatives available to represent knowledge related to single elements of the domain insertion or not of this knowledge in semantic nets in their descriptional sense. The final section of the paper discusses the problem in relation to the theories concerning the functioning of proper names from a logical and philosophical point of view.

A repository of fragments for agent systems design

The creation of a new design process for a specific situation using the method engineering approach is based on the composition of a set of reusable method fragments. The request for these reusable method fragments leads to the need for a repository containing standardized fragments that can be easily selected and assembled in new design processes. In this work we present a definition of method fragment coming from the work of the FIPA Technical Committee Methodology and a repository where fragments are classified according to the specific process component (activity, process role, and work product) they underpin and on the specific MAS Metamodel element(s) they work on.

Pattern-Recognition: a Foundational Approach

This paper aims at giving a contribution to the ongoing attempt to turn the theory of pattern-recognition into a rigorous science. In this article we address two problems which lie at the foundations of pattern-recognition theory: (i) What is a pattern? and (ii) How do we come to know patterns? In so doing much attention will be paid to tracing a non-arbitrary connection between (i) and (ii), a connection which will be ultimately based on considerations relating to Darwin’s theory of evolution.

A multi-agent decision support system for dynamic supply chain organization

In this work, a multi-agent system (MAS) for supply chain dynamic con- figuration is proposed. The brain of each agent is composed of a Bayesian Decision Network (BDN); this choice allows the agent for taking the best decisions esti- mating benefits and potential risks of different strategies, analyzing and managing uncertain information about the collaborating companies. Each agent collects infor- mation about customer’s orders and current market prices, and analyzes previous experiences of collaborations with trading partners. The agent therefore performs a probabilistic inferential reasoning to filter information modeled in its knowledge base in order to achieve the best performance in t…

Learning through observation and imitation: An overview of the ConSCIS architecture

High-dimensional perceptual signals and synthetic phenomenology

Synthetic phenomenology, in the sense of Chrisley, mainly focuses on the analysis of simplified perceptual signals with small or reduced dimensionality. Instead, we claim that synthetic phenomenology should be analysed in terms of dynamic perceptual signals with huge dimensionality. We claim that forms of dimensionality reduction of the perceptual signals, as done e.g. in typical robot vision applications, are characteristics of automatic “unconscious” processing. An effective “conscious” process actually deals with and must exploit the richness of the perceptual signals coming from the retina. We explore the hypothesis of a high-resolution buffer for the visual process and we discuss an ap…

Reinforcement Learning for P2P Searching

For a peer-to-peer (P2P) system holding massive amount of data, an efficient and scalable search for resource sharing is a key determinant to its practical usage. Unstructured P2P networks avoid the limitations of centralized systems and the drawbacks of a highly structured approach, because they impose few constraints on topology and data placement, and they support highly versatile search mechanisms. However their search algorithms are usually based on simple flooding schemes, showing severe inefficiencies. In this paper, to address this major limitation, we propose and evaluate the adoption of a local adaptive routing protocol. The routing algorithm adopts a simple Reinforcement Learning…

Assessing Coastal Sustainability: A Bayesian Approach for Modeling and Estimating a Global Index for Measuring Risk

Integrated Coastal Zone Management is an emerg- ing research area. The aim is to provide a global view of dif- ferent and heterogeneous aspects interacting in a geographical area. Decision Support Systems, integrating Computational Intelligence methods, can be successfully used to estimate use- ful anthropic and environmental indexes. Bayesian Networks have been widely used in the environmental science domain. In this paper a Bayesian model for estimating the Sustainable Coastal Index is presented. The designed Bayesian Network consists of 17 nodes, hierarchically organized in 4 layers. The first layer is initialized with the season and the physiographic region information. In the second la…

Kromos: Ontology based information management for ICT societies

Over the last few years, several projects for the development of innovative systems capable of collecting and sharing information have been carried out, following the increasing companies' interest on a correct knowledge management. ICT companies' managers have realized that knowledge and its management, more than the mere data, constitute fundamental part of their activities. This paper proposes a Knowledge Management System whose main feature is an underlying ontological knowledge representation. This data representation allows the specialization of the reasoning capabilities and the provision of ad hoc behaviors. The system has been designed for the management of projects and processes a…

Reasoning about Goals in BDI Agents: the PRACTIONIST Framework

Sub-Symbolic Mapping of Cyc Microtheories in Data-Driven 'Conceptual' Spaces

The presented work aims to combine statistical and cognitive-oriented approaches with symbolic ones so that a conceptual similarity relationship layer can be added to a Cyc KB microtheory. Given a specific microtheory, a LSA-inspired conceptual space is inferred from a corpus of texts created using both ad hoc extracted pages from the Wikipedia repository and the built-in comments about the concepts of the specific Cyc microtheory. Each concept is projected in the conceptual space and the desired layer of sub-symbolic relationships between concepts is created. This procedure can help a user in finding the concepts that are "sub-symbolically conceptually related" to a new concept that he wan…

Visual knowledge processing in computer-assisted radiology: A consultation system

This paper presents Visual Heuristics, a consultation system for diagnosis based on thorax radiograph recording. Visual Heuristics uses both prototypical representations of physiological and pathological states and reasoning aimed to infer conclusions from pathological or physiological conditions, establishing correspondences between pathological or physiological states and semantic descriptions of images. Images are assembled with groups of descriptors that guide the recognition process, achieving the possibility of comparisons with real images on the basis of 'expected' images. The system may be employed to generate a dynamic atlas that does not contain proper images, but generates them.

On Representing Concepts in High-dimensional Linear Spaces

Producing a mathematical model of concepts is a very important issue in artificial intelligence, because if such a model were found this, besides being a very interesting result in its own right, would also contribute to the emergence of what we could call the ‘mathematics of thought.’ One of the most interesting attempts made in this direction is P. Gardenfors’ theory of conceptual spaces, a ¨ theory which is mostly presented by its author in an informal way. The main aim of the present article is contributing to Gardenfors’ theory of conceptual spaces ¨ by discussing some of the advantages which derive from the possibility of representing concepts in high-dimensional linear spaces.

Mathematical Patterns and Cognitive Architectures

Mathematical patterns are an important subclass of the class of patterns. The main task of this paper is examining a particular proposal concerning the nature of mathematical patterns and some elements of the cognitive architecture an agent should have to recognize them.

Three-dimensional geometrical models of the inguinal region. Towards a new stereology.

In this work we studied the inguinal-abdominal region and the inguinal canal using three-dimensional geometrical models. We built the models through computer aided geometric modeling techniques on the basis of observations during real dissections, operations and diagnostic medical imaging. The obtained models show in a complete modular synthesis and with a schematic iconology the structural organization of the anatomical districts in a logic sequence of layers and topographic and spatial relationships among its components. The models represent an amazing support to anatomy and clinical anatomy for teaching and research purposes on organogenesis, surgery and diagnosis.

Motion analysis using the novelty filter

Abstract An original approach to the motion analysis, based on the novelty filter, is proposed. The novelty filter stresses the novelties occurring in a pattern representing an image of the scene under consideration with respect to patterns representing previous images of the same scene, so that visual information about the motion of the objects is obtained. The novelty filter may be implemented by a neural network architecture, taking advantage of the capabilities of massive parallelism, adaptive learning and noise robustness. The novelty filter may learn the entire trajectory of an object, through an incremental learning of a sequence of images capturing the scene, thus emphasizing if the…

QUALITATIVE MODELING OF CELL GROWTH PROCESSES

In this paper we present a qualitative physics model to reason about cell growth processes and cell-drug interactions, to be used in the knowledge base of NEWCHEM, an expert system intended to guide experimentation in the design of new optimal protocols in cancer treatment, After a brief discussion of the contributions that artificial intelligence techniques could make in cancer research and a brief presentation of some currently developed expert systems, some details of the proposed model based on the Forbus and Kuipers approaches to qualitative physics are given and its implementation as a LISP program is briefly discussed.

An intelligent assistant for medical knowledge discovery

Nowadays the availability of a huge amount of raw medical data makes it possible to use suitable data mining techniques to produce new knowledge. Usually, only data mining experts are able enough to carry out such tasks, and not so many researchers in medical ¯eld are also skilled in data analysis. This paper describes the Medical Knowledge Discovery Assistant (MKDA), a web based framework able to advice a medical researcher in such tasks. MKDA plans a Knowledge Discovery Process (KDP) on the basis of the requests of the user and of a set of rules in a knowledge base. The requests of the user are related to accu- racy, computational load, type of the produced model. They de¯ne the goal to b…

Planning by imagination in Cicerobot, a robot for museum tours

A cognitive architecture for ambient intelligence systems

Nowadays, the use of intelligent systems in homes and workplaces is a well-established reality. Research efforts are moving towards increasingly complex Ambient Intelligence (AmI) systems that exploit a wide variety of sensors, software modules and stand-alone systems. Unfortunately, using more data often comes at a cost, both in energy and computational terms. Finding the right trade-off between energy savings, information costs and accuracy of results is a major challenge, especially when trying to integrate many heterogeneous modules. Our approach fits into this scenario by proposing an ontology-based AmI system with a cognitive architecture, able to perceive the state of the surrounding…

Building agents with agents and patterns

The use of design patterns proved successful in lowering the development time and number of errors when producing software with the object-oriented paradigm. Now the need for a reuse technique is occurring for the emergent agent paradigm, for which a great effort is currently spending in methodology definitions. In this work we present our experiences in the identification, description, production and use of agents patterns. A repository of patterns was enriched during these years so to request a classification criteria and a documentation template useful to help user during the selection

DAISY: a distributed architecture for intelligent SYstem

Distributed perceptual systems are endowed with different kind of sensors, from which information flows to suitable modules to perform useful elaborations for decisions making. In this paper a new distributed architecture, named 'Distributed Architecture for Intelligent SYstem' (DAISY), is proposed. It is based on the concept of co-operating behavioral agents supervised by a 'Central Engagement Module'. This module integrates the processing of data coming from the behavioral agents with a symbolic level of representation, by the introduction of a 'conceptual space' intermediate analogue representation. The DAISY project is under development; experiments on navigation and exploration for an …

Are there individual concepts? Proper names and individual concepts in SI—Nets

We discuss some aspects of the role played by descriptional knowledge in expressions denoting individual objects. In knowledge representation systems such as KL-ONE and KRYPTON which use semantic networks to express descriptional information, the problem is to establish whether the use of individual concepts in a network is justified. In the light of theoretical and applicational considerations, in the proposed solution only definite descriptions are considered as being characterizable by means of definitions. Vice versa, proper names, in the strict sense, will be treated as having no definitional dimension, and as such only appear in the assertional knowledge base. A description is given o…

A qualitative model of the HIV vital cycle

Qualitative modelling is a recent artificial intelligence approach to physical system modelling. This approach has been successfully applied in several fields. On the basis of an analysis and qualitative modelling of cell growth, we reckon that a qualitative model of the vital cycle of HIV can be proposed, including the phases in which HIV can be attacked. The actions of antiviral drugs can also be qualitatively modelled, provided their action mechanism is known, even only in a broad sense.

A Cognitive Approach to Robot Self-Consciousness

An agent-based system for maritime search and rescue operations

Maritime search and rescue operations are critical missions involving personnel, boats, helicopter, aircrafts in a struggle against time often worsened by adversary sea and weather conditions. In such a context, telecommunication and in- formation systems may play a crucial role sometimes concurring to successfully accomplish the mission. In this paper we present an application able to localize the vessel who has launched a rescue request and to plan the most effective path for rescue assets. The application has been realised as a distributed and open multi-agent system deployed on rescue vehicles as well as on a land maritime stations of the Italian Coast Guard. The system is going to be t…

A multimodal chat-bot based information technology system

The proposed system integrates chat-bot and speech recognition technologies in order to build a versatile, user-friendly, virtual assistant guide with information retrieval capabilities. The system is adaptable to the user needs of mobility being also usable on different devices (i.e. PDAs, Smartphone). The system has been implemented on a Qtek 9090 with Windows Mobile 2003 and a simulation for the cultural heritage domain is here presented.

A metamodelling-based approach for method fragment comparison

Several different approaches to Situational Method Engineering exist. They differ in terms of the primary element of the paradigm: the method fragment definition. Here, we introduce four method fragment definitions from the literature and compare their metamodels according to structural and functional criteria. The structural comparison showed a general alignment of some concepts that are sometimes referred with different names while the study of the compositional aspects results in evidence of substantial differences.

Malware detection through low-level features and stacked denoising autoencoders

In recent years, the diffusion of malicious software through various channels has gained the request for intelligent techniques capable of timely detecting new malware spread. In this work, we focus on the application of Deep Learning methods for malware detection, by evaluating their effectiveness when malware are represented by high-level, and lowlevel features respectively. Experimental results show that, when using high-level features, deep neural networks do not significantly improve the overall detection accuracy. On the other hand, when low-level features, i.e., small pieces of information extracted through a light processing, are chosen, they allow to increase the capability of corr…

Acting on Conceptual Spaces in Cognitive Agents

Conceptual spaces were originally introduced by G ardenfors as a bridge between symbolic and connectionist models of information representation. In our opinion, a cognitive agent, besides being able to work within his (current) conceptual space, must also be able to `produce a new space' by means of `global' operations. These are operations which, acting on a conceptual space taken as a whole, generate other conceptual spaces.