scholarly journals Lightweight Adaptation of Classifiers to Users and Contexts: Trends of the Emerging Domain

2015 ◽  
Vol 2015 ◽  
pp. 1-29 ◽  
Author(s):  
Elena Vildjiounaite ◽  
Georgy Gimel’farb ◽  
Vesa Kyllönen ◽  
Johannes Peltola
Keyword(s):  
Domain Knowledge ◽  
Computer Applications ◽  
Training Data ◽  
Design Time ◽  
Classifier Adaptation ◽  
Application Characteristics ◽  
Definition Of ◽  
Context Specific ◽  
Application Developers ◽  
Intelligent Computer

Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairlylightweightways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.

Formal Metamodeling for Secure Model-Driven Engineering

2021 ◽  
Vol 12 (2) ◽  
pp. 46-67
Author(s):  
Liliana Maria Favre
Keyword(s):  
Cloud Computing ◽  
Formal Specifications ◽  
Model Driven Engineering ◽  
Model Driven ◽  
Transformation Rules ◽  
Systematic Development ◽  
Definition Of ◽  
Context Specific ◽  
Theoretical Foundations

Systems and applications aligned with new paradigms such as cloud computing and internet of the things are becoming more complex and interconnected, expanding the areas in which they are susceptible to attacks. Their security can be addressed by using model-driven engineering (MDE). In this context, specific IoT or cloud computing metamodels emerged to support the systematic development of software. In general, they are specified through semiformal metamodels in MOF style. This article shows the theoretical foundations of a method for automatically constructing secure metamodels in the context of realizations of MDE such as MDA. The formal metamodeling language Nereus and systems of transformation rules to bridge the gap between formal specifications and MOF are described. The main contribution of this article is the definition of a system of transformation rules called NEREUStoMOF for transforming automatically formal metamodeling specifications in Nereus to semiformal-MOF metamodels annotated in OCL.

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

2021 ◽  
pp. 2050012
Author(s):  
Peilian Zhao ◽  
Cunli Mao ◽  
Zhengtao Yu
Keyword(s):  
Sentiment Analysis ◽  
Domain Knowledge ◽  
Opinion Mining ◽  
Data Augmentation ◽  
Training Data ◽  
Knowledge Graph ◽  
Fine Grained ◽  
Learning Framework ◽  
Proposed Model ◽  
Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

scholarly journals Towards Semantic Interoperability for Electronic Health Records

2007 ◽  
Vol 46 (03) ◽  
pp. 332-343 ◽  
Author(s):  
P. Knaup ◽  
E. J. S. Hovenga ◽  
S. Heard ◽  
S. Garde
Keyword(s):  
Electronic Health Records ◽  
Domain Knowledge ◽  
Semantic Interoperability ◽  
Health Records ◽  
Face To Face ◽  
Telephone Interviews ◽  
Development Organisation ◽  
Knowledge Governance ◽  
Electronic Health ◽  
Definition Of

Summary Objectives: In the field of open electronic health records (EHRs), openEHR as an archetype-based approach is being increasingly recognised. It is the objective of this paper to shortly describe this approach, and to analyse how openEHR archetypes impact on health professionals and semantic interoperability. Methods: Analysis of current approaches to EHR systems, terminology and standards developments. In addition to literature reviews, we organised face-to-face and additional telephone interviews and tele-conferences with members of relevant organisations and committees. Results: The openEHR archetypes approach enables syntactic interoperability and semantic interpretability – both important prerequisites for semantic interoperability. Archetypes enable the formal definition of clinical content by clinicians. To enable comprehensive semantic interoperability, the development and maintenance of archetypes needs to be coordinated internationally and across health professions. Domain knowledge governance comprises a set of processes that enable the creation, development, organisation, sharing, dissemination, use and continuous maintenance of archetypes. It needs to be supported by information technology. Conclusions: To enable EHRs, semantic interoperability is essential. The openEHR archetypes approach enables syntactic interoperability and semantic interpretability. However, without coordinated archetype development and maintenance, ‘rank growth’ of archetypes would jeopardize semantic interoperability. We therefore believe that openEHR archetypes and domain knowledge governance together create the knowledge environment required to adopt EHRs.

An Effective Solution to Regression Problem by RBF Neuron Network

2015 ◽  
Vol 6 (4) ◽  
pp. 57-74 ◽  
Author(s):  
Dang Thi Thu Hien ◽  
Hoang Xuan Huan ◽  
Le Xuan Minh Hoang
Keyword(s):  
Regression Function ◽  
Training Data ◽  
Neuron Network ◽  
Open Problems ◽  
Regression Problem ◽  
Rbf Network ◽  
Network Training ◽  
Hidden Layer ◽  
Definition Of ◽  
Selection Of

Radial Basis Function (RBF) neuron network is being applied widely in multivariate function regression. However, selection of neuron number for hidden layer and definition of suitable centre in order to produce a good regression network are still open problems which have been researched by many people. This article proposes to apply grid equally space nodes as the centre of hidden layer. Then, the authors use k-nearest neighbour method to define the value of regression function at the center and an interpolation RBF network training algorithm with equally spaced nodes to train the network. The experiments show the outstanding efficiency of regression function when the training data has Gauss white noise.

scholarly journals LINKING INTERACTIVE OPTIMIZATION FOR URBAN PLANNING WITH A SEMANTIC 3D CITY MODEL

2018 ◽  
Vol IV-4 ◽  
pp. 179-186 ◽  
Author(s):  
N. Schüler ◽  
G. Agugiaro ◽  
S. Cajot ◽  
F. Maréchal
Keyword(s):  
Urban Planning ◽  
Data Model ◽  
Active Management ◽  
Specific Information ◽  
Exploration Process ◽  
Interactive Optimization ◽  
Potential Applications ◽  
City Model ◽  
Definition Of ◽  
Context Specific

<p><strong>Abstract.</strong> The cities in which we live are constantly evolving. The active management of this evolution is referred to as urban planning. The according development process could go in many directions resulting in a large number of potential future scenarios of a city. The planning support system URB<sup>io</sup> adopts interactive optimization to assist urban planners in generating and exploring those various scenarios. As a computer-based system it needs to be able to efficiently handle all underlying data of this exploration process, which includes both methodology-specific and context-specific information. This article describes the work carried out to link URB<sup>io</sup> with a semantic city model. Therefore, two key requirements were identified and implemented: (a) the extension of the CityGML data model to cope with many scenarios by the proposition of the Scenario Application Domain Extension (ADE) and (b) the definition of a data model for interactive optimization. Classes and features of the developed data models are motivated, depicted and explained. Their usability is demonstrated by walking through a typical workflow of URB<sup>io</sup> and laying out the induced data flows. The article is concluded with stating further potential applications of both the Scenario ADE and the data model for interactive optimization.</p>

Chapter 8. A Constraint-Based Approach to Learning and Reasoning

2021 ◽  
Author(s):  
Michelangelo Diligenti ◽  
Francesco Giannini ◽  
Marco Gori ◽  
Marco Maggini ◽  
Giuseppe Marra
Keyword(s):  
Neural Networks ◽  
Prior Knowledge ◽  
Domain Knowledge ◽  
Graphical Model ◽  
Expressive Power ◽  
Training Data ◽  
Markov Logic ◽  
Exact Inference ◽  
Logic Models ◽  
Effectiveness Of Training

Neural-symbolic models bridge the gap between sub-symbolic and symbolic approaches, both of which have significant limitations. Sub-symbolic approaches, like neural networks, require a large amount of labeled data to be successful, whereas symbolic approaches, like logic reasoners, require a small amount of prior domain knowledge but do not easily scale to large collections of data. This chapter presents a general approach to integrate learning and reasoning that is based on the translation of the available prior knowledge into an undirected graphical model. Potentials on the graphical model are designed to accommodate dependencies among random variables by means of a set of trainable functions, like those computed by neural networks. The resulting neural-symbolic framework can effectively leverage the training data, when available, while exploiting high-level logic reasoning in a certain domain of discourse. Although exact inference is intractable within this model, different tractable models can be derived by making different assumptions. In particular, three models are presented in this chapter: Semantic-Based Regularization, Deep Logic Models and Relational Neural Machines. Semantic-Based Regularization is a scalable neural-symbolic model, that does not adapt the parameters of the reasoner, under the assumption that the provided prior knowledge is correct and must be exactly satisfied. Deep Logic Models preserve the scalability of Semantic-Based Regularization, while providing a flexible exploitation of logic knowledge by co-training the parameters of the reasoner during the learning procedure. Finally, Relational Neural Machines provide the fundamental advantages of perfectly replicating the effectiveness of training from supervised data of standard deep architectures, and of preserving the same generality and expressive power of Markov Logic Networks, when considering pure reasoning on symbolic data. The bonding between learning and reasoning is very general as any (deep) learner can be adopted, and any output structure expressed via First-Order Logic can be integrated. However, exact inference within a Relational Neural Machine is still intractable, and different factorizations are discussed to increase the scalability of the approach.

Knowledge-Based Induction of Clinical Prediction Rules

2011 ◽  
pp. 350-375
Author(s):  
Mila Kwiatkowska ◽  
M. Stella Atkins ◽  
Les Matthews ◽  
Najib T. Ayas ◽  
C. Frank Ryan
Keyword(s):  
Domain Knowledge ◽  
Medical Knowledge ◽  
Data Sets ◽  
Clinical Prediction ◽  
Clinical Prediction Rules ◽  
Prediction Rules ◽  
Integrative Framework ◽  
Knowledge Based ◽  
The Creation ◽  
Definition Of

This chapter describes how to integrate medical knowledge with purely inductive (data-driven) methods for the creation of clinical prediction rules. It addresses three issues: representation of medical knowledge, secondary analysis of medical data, and evaluation of automatically induced predictive models in the context of existing knowledge. To address the complexity of the domain knowledge, the authors have introduced a semio-fuzzy framework, which has its theoretical foundations in semiotics and fuzzy logic. This integrative framework has been applied to the creation of clinical prediction rules for the diagnosis of obstructive sleep apnea, a serious and under-diagnosed respiratory disorder. The authors use a semio-fuzzy approach (1) to construct a knowledge base for the definition of diagnostic criteria, predictors, and existing prediction rules; (2) to describe and analyze data sets used in the data mining process; and (3) to interpret the induced models in terms of confirmation, contradiction, and contribution to existing knowledge.

ODARM

2010 ◽  
pp. 40-56
Author(s):  
Fu Xiao ◽  
Xie Li
Keyword(s):  
Intrusion Detection ◽  
Outlier Detection ◽  
Domain Knowledge ◽  
Reduction Rate ◽  
Main Idea ◽  
False Positives ◽  
Training Data ◽  
Intrusion Detection Systems ◽  
Data Mining Technique ◽  
Detection Systems

Intrusion Detection Systems (IDSs) are widely deployed with increasing of unauthorized activities and attacks. However they often overload security managers by triggering thousands of alerts per day. And up to 99% of these alerts are false positives (i.e. alerts that are triggered incorrectly by benign events). This makes it extremely difficult for managers to correctly analyze security state and react to attacks. In this chapter the authors describe a novel system for reducing false positives in intrusion detection, which is called ODARM (an Outlier Detection-Based Alert Reduction Model). Their model based on a new data mining technique, outlier detection that needs no labeled training data, no domain knowledge and little human assistance. The main idea of their method is using frequent attribute values mined from historical alerts as the features of false positives, and then filtering false alerts by the score calculated based on these features. In order to filter alerts in real time, they also design a two-phrase framework that consists of the learning phrase and the online filtering phrase. Now they have finished the prototype implementation of our model. And through the experiments on DARPA 2000, they have proved that their model can effectively reduce false positives in IDS alerts. And on real-world dataset, their model has even higher reduction rate.

scholarly journals Literature mining for context-specific molecular relations using multimodal representations (COMMODAR)

2020 ◽  
Vol 21 (S5) ◽  
Author(s):  
Jaehyun Lee ◽  
Doheon Lee ◽  
Kwang Hyung Lee
Keyword(s):  
Biological Networks ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Main Idea ◽  
Relation Extraction ◽  
Literature Mining ◽  
Computing Methodologies ◽  
Multimodal Representations ◽  
Relational Resources ◽  
Context Specific

Abstract Biological contextual information helps understand various phenomena occurring in the biological systems consisting of complex molecular relations. The construction of context-specific relational resources vastly relies on laborious manual extraction from unstructured literature. In this paper, we propose COMMODAR, a machine learning-based literature mining framework for context-specific molecular relations using multimodal representations. The main idea of COMMODAR is the feature augmentation by the cooperation of multimodal representations for relation extraction. We leveraged biomedical domain knowledge as well as canonical linguistic information for more comprehensive representations of textual sources. The models based on multiple modalities outperformed those solely based on the linguistic modality. We applied COMMODAR to the 14 million PubMed abstracts and extracted 9214 context-specific molecular relations. All corpora, extracted data, evaluation results, and the implementation code are downloadable at https://github.com/jae-hyun-lee/commodar. Ccs concepts • Computing methodologies~Information extraction • Computing methodologies~Neural networks • Applied computing~Biological networks.

Sign in / Sign up

Export Citation Format

Share Document