Filters








155,455 Hits in 6.6 sec

Knowledge-based computer-aided decision support in prenatal toxoplasmosis screening (TempToxopert)

Karl Boegl, Nadejda Anastassova, Klaus-Peter Adlassnig, Andrea Rappelsberger, Michael Hayde, Arnold Pollak
2005 AMIA Annual Symposium Proceedings  
Based on actual and past individual findings, the system generates case-specific interpretative reports consisting of a diagnostic hypothesis, recommendations for further treatment, and interpretations  ...  Expert knowledge about diagnostics, screening strategies, and treatment of toxoplasmosis during pregnancy was collected and represented as a rule-based decision graph.  ...  Based on actual and past individual findings, the system generates case-specific interpretative reports consisting of a diagnostic hypothesis, recommendations for further treatment, and interpretations  ... 
pmid:16779184 pmcid:PMC1560889 fatcat:726fpygiingzle2wf27aell5qa

Knowledge Graph Representation Reasoning for Recommendation System

Tao Li, Hao Li, Sheng Zhong, Yan Kang, Yachuan Zhang, Rongjing Bu, Yang Hu
2020 Journal of New Media  
KGRS first obtains reasoning paths of knowledge graph and embeds the entities of paths into vectors based on knowledge representation learning TransD algorithm, then uses LSTM and soft attention mechanism  ...  KGRS is tested on the movielens-100k dataset.  ...  Recommendation Based on Knowledge Graph Knowledge graph contains rich information of users and items, which also provides more intuitive and targeted interpretation for the generation of recommended items  ... 
doi:10.32604/jnm.2020.09767 fatcat:fn2o7ccckrembi7vmxpeydxduy

Knowledge-based interpretation of toxoplasmosis serology test results including fuzzy temporal concepts--the ToxoNet system

D Kopecky, M Hayde, A R Prusa, K P Adlassnig
2001 Studies in Health Technology and Informatics  
The computer system ToxoNet processes the results of serological antibody tests having been performed during pregnancy by means of a knowledge base containing medical knowledge on the interpretation of  ...  By applying this knowledge ToxoNet generates interpretive reports consisting of a diagnostic interpretation and recommendations for therapy and further testing.  ...  Firstly it is possible to specify more than one interpretation (consisting of a diagnosis and recommendations for therapy and further testing) for a single node in the decision graph, each of them belonging  ... 
pmid:11604787 fatcat:32wqquaoenexdncxofoewxnko4

Knowledge Graph Embeddings with node2vec for Item Recommendation [chapter]

Enrico Palumbo, Giuseppe Rizzo, Raphaël Troncy, Elena Baralis, Michele Osella, Enrico Ferro
2018 Lecture Notes in Computer Science  
We empirically compare a set of state-of-the-art knowledge graph embeddings algorithms on the task of item recommendation on the Movielens 1M dataset.  ...  In this paper, we show that the item recommendation problem can be seen as a specific case of knowledge graph completion problem, where the "feedback" property, which connects users to items that they  ...  Thus, we compare a set of state-of-the-art knowledge graph completion algorithms based on knowledge graph embeddings (TransE [3] , TransH [14] , TransR [9] ) on the problem of item recommendation.  ... 
doi:10.1007/978-3-319-98192-5_22 fatcat:npssnl7vgbeuphydjy34psh6ma

Fuzzy systems in medicine

Klaus-Peter Adlassnig
2001 European Society for Fuzzy Logic and Technology  
Examples of the application of type-n hzzy sets to model medical concepts and of fuzzy logic, fuzzy decision graphs, fuzzy control, and fuzzy automata in medical diagnosis, interpretative analysis of test  ...  with a function that provides knowledge-based decision support.  ...  Steltzer for their immense work in setting up practical and useful medical knowledge bases in several areas of internal, laboratory, and intensive care medicine.  ... 
dblp:conf/eusflat/Adlassnig01 fatcat:xvgqlnizkfhlblci3lqsschkme

Towards Evaluating an Ontology-Based Data Matching Strategy for Retrieval and Recommendation of Security Annotations for Business Process Models [chapter]

Ioana Ciuciu, Yan Tang, Robert Meersman
2012 Lecture Notes in Business Information Processing  
a dedicated knowledge base.  ...  Its supporting tool, called Knowledge Annotator (KA), is using ontology-based data matching algorithms and strategy in order to infer the recommendations the best fitted to the user design intent, from  ...  The outcome of the annotator and the quality of the recommendations are dependent on the knowledge base updates and on the domain expert responsible for managing the knowledge base.  ... 
doi:10.1007/978-3-642-34044-4_6 fatcat:fimsh3ox45dtrnk5inxjdduxim

An Interpretable Music Similarity Measure Based on Path Interestingness [article]

Giovanni Gabbolini, Derek Bridge
2021 arXiv   pre-print
We find paths in the graph between a seed and a target item; we score those paths based on their interestingness; and we aggregate those scores to determine the similarity between the seed and the target  ...  We introduce a novel and interpretable path-based music similarity measure.  ...  For example, knowledge graphs have been applied to recommender systems [2] and question answering [3] . In this work, we use knowledge graphs to gauge music similarity.  ... 
arXiv:2108.01632v2 fatcat:k2kdfiugrzc6ngejkgvi5f47dy

An interpretable music similarity measure based on path interestingness

Giovanni Gabbolini, Derek Bridge
2021 Zenodo  
We find paths in the graph between a seed and a target item; we score those paths based on their interestingness; and we aggregate those scores to determine the similarity between the seed and the target  ...  We introduce a novel and interpretable path-based music similarity measure.  ...  For example, knowledge graphs have been applied to recommender systems [2] and question answering [3] . In this work, we use knowledge graphs to gauge music similarity.  ... 
doi:10.5281/zenodo.5624648 fatcat:f727gkurwzfspgcrruwgfoweue

How to make latent factors interpretable by feeding Factorization machines with knowledge graphs [article]

Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio, Azzurra Ragone, Joseph Trotta
2019 arXiv   pre-print
By relying on the information encoded in the original knowledge graph, we have also evaluated the semantic accuracy and robustness for the knowledge-aware interpretability of the final model.  ...  Model-based approaches to recommendation can recommend items with a very high level of accuracy.  ...  Among interpretable models for Recommender Systems (RS), we may distinguish between those based on Content-based (CB) approaches and those based on Collaborative filtering (CF) ones.  ... 
arXiv:1909.05038v1 fatcat:osz7iuamsfblxmeybeyysc3wp4

Development of a clinical decision support system for diabetes care: A pilot study

Livvi Li Wei Sim, Kenneth Hon Kim Ban, Tin Wee Tan, Sunil Kumar Sethi, Tze Ping Loh, Corentin Cras-Méneur
2017 PLoS ONE  
However, the Diabetes Dashboard did not significantly improve the identification of patients requiring treatment adjustment or the amount of time spent on each case scenario.  ...  Management of complex chronic diseases such as diabetes requires the assimilation and interpretation of multiple laboratory test results.  ...  These alerts were similarly designed based on the recommended testing intervals for diabetes-related disease monitoring by Ministry of Health (Table 2) . Interactive time-series graphs.  ... 
doi:10.1371/journal.pone.0173021 pmid:28235017 pmcid:PMC5325565 fatcat:vkuzw7hxrbetrjodvmhpms43ve

Book announcements

1994 Discrete Applied Mathematics  
Knowledge verification. System evaluation). Verification and validation recommendations (Validation testing. Validation test cases. Acceptance criteria. Testing documentation. Revalidation.  ...  Overview of recommendations in process model (Planning phase. Coverage analysis (Coverage of knowledge base. Coverage of equivalence classes). Test case suggestions)). Evaluation of SAVES.  ... 
doi:10.1016/0166-218x(94)00003-4 fatcat:oczm7j3xrjglpi6xu6gw462xs4

Local Model-Agnostic Explanations for Black-box Recommender Systems Using Interaction Graphs and Link Prediction Techniques

Marta Caro-Martínez, Guillermo Jiménez-Díaz, Juan A. Recio-García
2021 International Journal of Interactive Multimedia and Artificial Intelligence  
This current work proposes a local model-agnostic, explanation-by-example method for recommender systems based on knowledge graphs to leverage this knowledge requirement.  ...  Through the proper transformation of these knowledge graphs into item-based and user-based structures, link prediction techniques are applied to find similarities between the nodes and to identify explanatory  ...  However, in the case of the graph-based approaches, the performance improves.  ... 
doi:10.9781/ijimai.2021.12.001 fatcat:nyls65sh4zej5duj6ejhdvzmay

Graphing else matters: exploiting aspect opinions and ratings in explainable graph-based recommendations [article]

Iván Cantador, Andrés Carvallo, Fernando Diez, Denis Parra
2022 arXiv   pre-print
In particular, current recommendation methods based on graph embeddings have shown state-of-the-art performance. These methods commonly encode latent rating patterns and content features.  ...  We then adapt and evaluate state-of-the-art graph embedding techniques over graphs generated from Amazon and Yelp reviews on six domains, outperforming baseline recommenders.  ...  Graph-based recommendation explanations The vast majority of works on graph-based recommenders aims to produce path-based interpretations of generated recommendations, although it has been stated that  ... 
arXiv:2107.03226v2 fatcat:777hnvwc6rfy5evqvaxbi6mzpy

A Personalized and Collaborative eLearning Materials Recommendation Scenario Using Ontology-Based Data Matching Strategies [chapter]

Ioana Ciuciu, Yan Tang
2010 Lecture Notes in Computer Science  
It is based on three main components: 1) a semantically enriched content management system (CMS), playing the role of knowledge base, 2) a 3D anatomy browser and 3) an ontology-based matching strategy  ...  Together with the collaborative knowledge base, which allows knowledge to be represented in natural language and to be further reused, the evaluation methodology becomes the main contribution of the paper  ...  Based on these results, the system can recommend learning materials that can provide missing competencies or improve the existing skills.  ... 
doi:10.1007/978-3-642-16961-8_81 fatcat:uzinagadb5c7voowz66md6cbia

Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation [article]

Yuan Zhang, Xiaoran Xu, Hanning Zhou, Yan Zhang
2019 arXiv   pre-print
Through extensive experiments, we show that our proposed framework can achieve state-of-the-art recommendation performance and meanwhile provide interpretable recommendation reasons.  ...  In this paper, we propose an end-to-end joint learning framework to get around these limitations without introducing any extra overhead by distilling structured knowledge from a differentiable path-based  ...  arbitrary in the extreme case) probability mass on unobserved ones.  ... 
arXiv:1912.08422v1 fatcat:4cp5ni6cmnc27os54wc4rjqufa
« Previous Showing results 1 — 15 out of 155,455 results