From Finding to Explaining

Supporting anomaly analysis in the maritime field is a challenging problem because of the dynamic nature of the task: the definition of abnormal or suspicious behaviour is subject to change and depends on user interests. This paper provides a novel approach to support anomaly analysis in the maritime domain through the exploration of large collections of interpretation reports. Based on observables or more sophisticated patterns, the approach provides information retrieval strategies going from basic facts retrieval that guide short-term corrective actions to more complex networks of related concepts that help domain experts to understand or to explain abnormal vessel behaviours. Semantic integration is used to link various information sources, by using a commonly adopted standard. The paper seeks to explore different aspects of using information retrieval to support the analysis and interpretation of abnormal vessel behaviours for maritime surveillance.

Download Full-text

Personalized information retrieval based on context and ontological knowledge

The Knowledge Engineering Review ◽

10.1017/s0269888907001282 ◽

2008 ◽

Vol 23 (1) ◽

pp. 73-100 ◽

Cited By ~ 43

Author(s):

PH. MYLONAS ◽

D. VALLET ◽

P. CASTELLS ◽

M. FERNÁNDEZ ◽

Y. AVRITHIS

Keyword(s):

Information Retrieval ◽

Ad Hoc ◽

Effective Means ◽

User Preferences ◽

Context Modeling ◽

User Interests ◽

Automatic Interpretation ◽

User Context ◽

Definition Of ◽

Key Aspects

AbstractContext modeling has long been acknowledged as a key aspect in a wide variety of problem domains. In this paper we focus on the combination of contextualization and personalization methods to improve the performance of personalized information retrieval. The key aspects in our proposed approach are (1) the explicit distinction between historic user context and live user context, (2) the use of ontology-driven representations of the domain of discourse, as a common, enriched representational ground for content meaning, user interests, and contextual conditions, enabling the definition of effective means to relate the three of them, and (3) the introduction of fuzzy representations as an instrument to properly handle the uncertainty and imprecision involved in the automatic interpretation of meanings, user attention, and user wishes. Based on a formal grounding at the representational level, we propose methods for the automatic extraction of persistent semantic user preferences, and live, ad-hoc user interests, which are combined in order to improve the accuracy and reliability of personalization for retrieval.

Download Full-text

Short-term synaptic facilitation improves information retrieval in noisy neural networks

EPL (Europhysics Letters) ◽

10.1209/0295-5075/97/48008 ◽

2012 ◽

Vol 97 (4) ◽

pp. 48008 ◽

Cited By ~ 6

Author(s):

J. F. Mejias ◽

B. Hernandez-Gomez ◽

J. J. Torres

Keyword(s):

Neural Networks ◽

Information Retrieval ◽

Short Term ◽

Synaptic Facilitation

Download Full-text

Learning Curves: A Novel Approach for Robustness Improvement of Load Forecasting

Engineering Proceedings ◽

10.3390/engproc2021005038 ◽

2021 ◽

Vol 5 (1) ◽

pp. 38

Author(s):

Chiara Giola ◽

Piero Danti ◽

Sandro Magnani

Keyword(s):

Load Forecasting ◽

Learning Curves ◽

Machine Learning Techniques ◽

Essential Information ◽

Set Size ◽

Novel Approach ◽

Learning Techniques ◽

Energy Plant ◽

Definition Of ◽

The Right

In the age of AI, companies strive to extract benefits from data. In the first steps of data analysis, an arduous dilemma scientists have to cope with is the definition of the ’right’ quantity of data needed for a certain task. In particular, when dealing with energy management, one of the most thriving application of AI is the consumption’s optimization of energy plant generators. When designing a strategy to improve the generators’ schedule, a piece of essential information is the future energy load requested by the plant. This topic, in the literature it is referred to as load forecasting, has lately gained great popularity; in this paper authors underline the problem of estimating the correct size of data to train prediction algorithms and propose a suitable methodology. The main characters of this methodology are the Learning Curves, a powerful tool to track algorithms performance whilst data training-set size varies. At first, a brief review of the state of the art and a shallow analysis of eligible machine learning techniques are offered. Furthermore, the hypothesis and constraints of the work are explained, presenting the dataset and the goal of the analysis. Finally, the methodology is elucidated and the results are discussed.

Download Full-text

The Use of Photogrammetry in Piping Design

Proceedings of the Institution of Mechanical Engineers Part A Power and Process Engineering ◽

10.1243/pime_proc_1983_197_014_02 ◽

1983 ◽

Vol 197 (2) ◽

pp. 125-138 ◽

Cited By ~ 1

Author(s):

P A Bracewell ◽

U R Klement

Keyword(s):

Information Retrieval ◽

Mathematical Formulation ◽

Three Dimensional ◽

Cost Effective ◽

Process Industry ◽

Process Plant ◽

Definition Of ◽

High Degree ◽

Positional Data

Piping design for ‘revamp’ projects in the process industry requires the retrieval of large amounts of ‘as-built’ data from existing process plant installations. Positional data with a high degree of accuracy are required. Photogrammetry, the science of measurement from photographs, was identified in Imperial Chemical Industries plc (ICI) as a suitable tool for information retrieval. The mathematical formulation enabling the definition of three-dimensional positions from photographic information is described. The process of using ICI's photogrammetric system for the definition of complete objects such as structures and pipes is illustrated. The need for specialized photogrammetric software for design purposes is explained. A case study describing how the photogrammetric system has been applied is described and graphical outputs from this exercise are shown. It is concluded that this particular photogrammetric system has proved to be a cost effective and accurate tool for the retrieval of ‘as-built’ information.

Download Full-text

Semantic Representation of a Geo-Social User Profile for a Personalised Information Retrieval

Journal of Information & Knowledge Management ◽

10.1142/s0219649221500441 ◽

2021 ◽

pp. 2150044

Author(s):

Tahar Rafa ◽

Samir Kechid

Keyword(s):

Information Retrieval ◽

Information Search ◽

Semantic Representation ◽

User Profile ◽

Search Process ◽

Search System ◽

User Interactions ◽

User Interests ◽

Situational Contexts ◽

User Query

The user-centred information retrieval needs to introduce semantics into the user modelling for a meaningful representation of user interests. The semantic representation of the user interests helps to improve the identification of the user’s future cognitive needs. In this paper, we present a semantic-based approach for a personalised information retrieval. This approach is based on the design and the exploitation of a user profile to represent the user and his interests. In this user profile, we combine an ontological semantics issued from WordNet ontology, and a personal semantics issued from the different user interactions with the search system and with his social and situational contexts of his previous searches. The personal semantics considers the co-occurrence relations between relevant components of the user profile as semantic links. The user profile is used to improve two important phases of the information search process: (i) expansion of the initial user query and (ii) adaptation of the search results to the user interests.

Download Full-text

Abstract P563: Prognosis Driven Definition of Carotid Near-Occlusion With Full Collapse

Stroke ◽

10.1161/str.52.suppl_1.p563 ◽

2021 ◽

Vol 52 (Suppl_1) ◽

Author(s):

Charith Cooray ◽

Thomas Gu ◽

Allan J Fox ◽

Elias Johansson

Keyword(s):

Ischemic Stroke ◽

Carotid Stenosis ◽

Risk Markers ◽

Inclusion Criteria ◽

Short Term ◽

Residual Stenosis ◽

Kaplan Meier ◽

Near Occlusion ◽

Definition Of ◽

Distal Artery

Introduction: Carotid near-occlusion is a severe carotid stenosis causing distal artery collapse of varying degree. Near-occlusion is often divided into a “full collapse” group with a threadlike distal lumen, and the often overlooked “without full collapse” group with a normal-appearing, albeit small, distal lumen. By this division by appearance, symptomatic near-occlusion with full collapse has been reported to have worse short-term prognosis than those without full collapse, no other division has been assessed for prognosis. The aim of this study was to assess if a measurement based definition of full collapse might improve prognostic discrimination. Methods: 99 consecutive patients with symptomatic near-occlusion diagnosed on CT-angiography were included. The risk of preoperative recurrent ipsilateral ischemic stroke within 28 days of presenting event was assessed with Kaplan-Meier analysis, censoring at revascularization. We assessed residual stenosis diameter, distal ICA diameter, ICA-ratio (side-to-side), and ICA-ECA ratio as risk markers. Results: By appearance, the 28-day risk of stroke tended to be higher for full collapse (27%, 11/42) than without full collapse (11%, 6/57), p=0.054 (figure). The best new definition of full collapse was distal ICA diameter ≤2.0 mm and/or ICA ratio ≤0.47. 10 patients were reclassified by this new definition compared to appearance definition, 5 in each direction. By the new definition, 28-day risk of stroke was higher in full collapse (34%, 14/42) than without full collapse (5%, 3/57), p<0.001 (fig 1B). Conclusions: Compared to the appearance based definition, our new definition of separating near-occlusions into with and without full collapse yields similar groups sizes but better prognostic discrimination. This new definition could be used as inclusion criteria in future treatment trials.

Download Full-text

Short Term Solar Power Generation Forecasting: A Novel Approach

2018 International Conference on Photovoltaic Science and Technologies (PVCon) ◽

10.1109/pvcon.2018.8523919 ◽

2018 ◽

Cited By ~ 3

Author(s):

Fatih Serttas ◽

Fatih Onur Hocaoglu ◽

Emre Akarslan

Keyword(s):

Power Generation ◽

Solar Power ◽

Short Term ◽

Solar Power Generation ◽

Novel Approach

Download Full-text

Generating Collaborative Systems for Digital Libraries: a Model-Driven Approach

Information Technology and Libraries ◽

10.6017/ital.v29i4.3128 ◽

2010 ◽

Vol 29 (4) ◽

pp. 171 ◽

Cited By ~ 2

Author(s):

Alessio Malizia ◽

Paolo Bottoni ◽

S. Levialdi

Keyword(s):

Digital Library ◽

User Interfaces ◽

Digital Libraries ◽

Automatic Generation ◽

Visual Language ◽

Domain Experts ◽

Model Driven ◽

Neutral Models ◽

Definition Of ◽

High Level

The design and development of a digital library involves different stakeholders, such as: information architects, librarians, and domain experts, who need to agree on a common language to describe, discuss, and negotiate the services the library has to offer. To this end, high-level, language-neutral models have to be devised. Metamodeling techniques favor the definition of domainspecific visual languages through which stakeholders can share their views and directly manipulate representations of the domain entities. This paper describes CRADLE (Cooperative-Relational Approach to Digital Library Environments), a metamodel-based framework and visual language for the definition of notions and services related to the development of digital libraries. A collection of tools allows the automatic generation of several services, defined with the CRADLE visual language, and of the graphical user interfaces providing access to them for the final user. The effectiveness of the approach is illustrated by presenting digital libraries generated with CRADLE, while the CRADLE environment has been evaluated by using the cognitive dimensions framework.

Download Full-text