164 Hits in 2.1 sec

Tree Mining in Mental Health Domain

Maja Hadzic, Fedja Hadzic, Tharam Dillon
2008 Proceedings of the 41st Annual Hawaii International Conference on System Sciences (HICSS 2008)  
The number of mentally ill people is increasing globally each year. Despite major medical advances, the identification of genetic and environmental factors responsible for mental illnesses still remains unsolved and is therefore a very active research focus today. Semi-structured data structure is predominantly used to enable the meaningful representations of the available mental health knowledge. Data mining techniques can be used to efficiently analyze these semi-structured mental health
more » ... Tree mining algorithms can efficiently extract frequent substructures from semi-structured knowledge representation such as XML. In this paper we demonstrate effective application of the tree mining algorithms on records of mentally ill patients. The extracted data patterns can provide useful information to help in prevention of mental illness and assist in delivery of effective and efficient mental health services.
doi:10.1109/hicss.2008.474 dblp:conf/hicss/HadzicHD08 fatcat:vwbj4i5nozdvbm5mqcqvep6xki

Povijesni pregled razvoja riječke tvornice papira

Maja Hadžić, Branka Lozo
2011 Drvna industrija  
doi:10.5552/drind.2011.1035 fatcat:jamkcaee6nd2zhf4ispfiuktdy

Ontology Design Approaches [chapter]

Maja Hadzic, Pornpit Wongthongtham, Tharam Dillon, Elizabeth Chang
2009 Studies in Computational Intelligence  
doi:10.1007/978-3-642-01904-3_5 fatcat:2bviypfukzdevmg762hvmrlm2e

Mining of patient data: towards better treatment strategies for depression

Maja Hadzic, Fedja Hadzic, Tharam S. Dillon
2010 International Journal of Functional Informatics and Personalised Medicine  
To find these hard to detect anomalies we will make use outlier detection strategy presented in (Hadzic et al. 2007 ).  ...  It was mentioned earlier that we aim to use outlier detection and analysis technique (Hadzic et al. 2007 ) for removal of anomalies from the data.  ... 
doi:10.1504/ijfipm.2010.037150 fatcat:5vis6ualafhzxgvau3cytrdwde

Thinking PubMed: an Innovative System for Mental Health Domain

Maja Hadzic, Russel D'Souza, Fedja Hadzic, Tharam Dillon
2008 2008 21st IEEE International Symposium on Computer-Based Medical Systems  
Information regarding mental illness is dispersed over various resources but even within a specific resource, such as PubMed, it is difficult to link this information, to share it and find specific information when needed. Specific and targeted searches are very difficult with current search engines as they look for the specific string of letters within the text rather than its meaning. In this paper we present Thinking PubMed as a system that results from synergy of ontology and data mining
more » ... hnologies and performs intelligent information searches using the domain ontology. Furthermore, the Thinking PubMed analyzes and links the retrieved information, and extracts hidden patterns and knowledge using data mining algorithms. This is a new generation of information-seeking tool where the ontology and datamining work in concert to increase the value of the available information.
doi:10.1109/cbms.2008.20 dblp:conf/cbms/HadzicDHD08 fatcat:aanc6fx3ebaa3k42ras7nb4cee

Creating interoperability within healthcare industry

Chen Wu, Maja Hadzic
2008 2008 6th IEEE International Conference on Industrial Informatics  
During the last decade, a number of health initiatives have been undertaken in Australia. However, Australian medical systems still suffer from the chronic problem of inability to share information essential to the health and wellbeing of patients. The major causes for this are (1) the lack of a standardized format in which patient information is being kept, and (2) the lack of infrastructure to enable sharing of the information among different organizations and institutions. In this paper we
more » ... opose the use of ontologies, to enable effective translation between different EHR formats, and use of web services to enable efficient information exchange and sharing. The proposed solution has the potential to greatly improve the way patient information is being used, and consequently reduce the associated costs in both human and financial terms.
doi:10.1109/indin.2008.4618312 fatcat:xighcsmcxnf65fvmhi4bzugafm

Domain Ontology Usage Analysis Framework

Jamshaid Ashraf, Maja Hadzic
2011 2011 Seventh International Conference on Semantics, Knowledge and Grids  
The Semantic Web (also known as Web of Data) is growing fast and becoming a decentralized knowledge platform for publishing and sharing information. The web ontologies pro-mote the establishment of a shared understanding between data providers and data consumers, allowing for automated information processing and effective and efficient information retrieval. The majority of existing research efforts is focused around ontology engineering, ontology evaluation and ontology evolution. This work
more » ... s a step further and evaluates the ontology usage. In this paper, we present an Ontology USage Analysis Framework (OUSAF) and a set of metrics used to measure the ontology usage. The implementation of the proposed framework is illustrated using the example of GoodRelations ontology (GRO). GRO has been well adopted by the semantic ecommerce community, and the OUSAF approach has been used to analyse GRO usage in the dataset comprised of RDF data collected from the web.
doi:10.1109/skg.2011.33 dblp:conf/skg/AshrafH11 fatcat:oifl4gp5kff2tgep2gibovlkea

Priporočila za telesno dejavnost nosečnic

Mateja Videmšek, Eda Bokal Vrtačnik, Darija Šćepanović, Lidija Žgur, Naja Videmšek, Maja Meško, Damir Karpljuk, Jože Štihec, Vedran Hadžić
2015 Zdravniški Vestnik  
Properly selected and prescribed physical activity during pregnancy has a favorable effects on the health of pregnant women and the fetus, and is excellent preparation for childbirth. Absolute and relative contraindications to exercise during pregnancy are well defined, as well as the warning signs to terminate exercise while pregnant. Knowledge of these is essential for physically active pregnant women and exercise professionals that work with pregnant women. Pregnant women should be
more » ... physically active every day of the week for at least 30 minutes. The term moderate is thoroughly and clearly defined in the guidelines. Resistance exercises during pregnancy are safe but it is advised to use light loads and a large number of repetitions (e.g. 15-20 repetitions). Strength exercises for the pelvic floor muscles deserves a special place during pregnancy. Appropriate forms of physical activity for pregnant women are walking and jogging, swimming and aquatic exercise, cycling, Pilates and yoga, aerobics, fitness and cross-country skiing. Certain forms of physical activity need special adjustments (alpine skiing, ice skating and rollerblading, racket sports, team ball games, horseback riding and scuba diving).
doi:10.6016/zdravvestn.1220 fatcat:bb6p6u3cp5hsdndw7sxjiz6emu

Towards the Mental Health Ontology

Maja Hadzic, Meifania Chen, Tharam S. Dillon
2008 2008 IEEE International Conference on Bioinformatics and Biomedicine  
Lots of research have been done within the mental health domain, but exact causes of mental illness are still unknown. Concerningly, the number of people being affected by mental conditions is rapidly increasing and it has been predicted that depression would be the world's leading cause of disability by 2020. Most mental health information is found in electronic form. Application of the cutting-edge information technologies within the mental health domain has the potential to greatly increase
more » ... he value of the available information. Specifically, ontologies form the basis for collaboration between research teams, for creation of semantic web services and intelligent multi-agent systems, for intelligent information retrieval, and for automatic data analysis such as data mining. In this paper, we present Mental Health Ontology which can be used to underpin a variety of automatic tasks and positively transform the way information is being managed and used within the mental health domain.
doi:10.1109/bibm.2008.59 dblp:conf/bibm/HadzicCD08 fatcat:sg6tsk53pfcxro4wmfcc7r7ypu

Towards a methodology for Lipoprotein Ontology

Meifania Chen, Maja Hadzic
2010 2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS)  
doi:10.1109/cbms.2010.6042680 dblp:conf/cbms/ChenH10 fatcat:msack5kkbbbmlh25aytdm52l2a

Use and Modeling of Multi-agent Systems in Medicine

Maja Hadzic, Darshan Dillon, Tharam Dillon
2009 2009 20th International Workshop on Database and Expert Systems Application  
Multi-Agent System (MAS), and more specifically, ontology-based MAS, are increasingly being proposed and used within the medical domain. In this paper we represent an ontology-based multi-agent system specifically designed to intelligently retrieve information about human diseases. The human disease ontology is organized according to the four dimensions: disease types, symptoms, causes and treatments. The multi-agent system consists of four different types of agent: Interface, Manger,
more » ... n and Smart agent. We use of UML 2.1 to model social and goal-driven nature of agents. We believe that UML 2.1 has not only provided a way for standardized notation of MAS, but also for effective representation of the dynamic processes associated with these MAS. Keywords-UML, modeling of multi-agent systems, ontologybased multi-agent systems, information retrieval.
doi:10.1109/dexa.2009.7 dblp:conf/dexaw/HadzicDD09 fatcat:gxy26tkrabcidohncsleuytiyq

Lipoprotein ontology as a functional knowledge base

Meifania Chen, Maja Hadzic
2009 2009 22nd IEEE International Symposium on Computer-Based Medical Systems  
The advances of high throughput research in the biomedical domain have resulted in an onslaught of data being generated at an exponential rate. As a result, researchers face challenges in navigating through overwhelming amounts of information in order to derive relevant scientific insights. Ontologies address these issues by providing explicit description of biomedical entities and a platform for the integration of data, thereby enabling a more efficient retrieval of information. There have
more » ... major efforts in the development of biomedical ontologies in the recent years; however no such ontology exists for lipoproteins, which play a crucial role in various biological and cellular functions. Dysregulation in lipoprotein metabolism is significantly associated with an increased risk to cardiovascular disease, the leading cause of mortality in the world today. The aim of this paper is to propose a preliminary framework for Lipoprotein Ontology, with particular focus on the etiology and treatment of lipoprotein dysregulation. This may provide a novel and effective strategy for managing at risk individuals.
doi:10.1109/cbms.2009.5255333 dblp:conf/cbms/ChenH09 fatcat:xzg45b6fm5av5jel3upwydgeeq

Ontology Support for Biomedical Information Resources

Tharam Dillon, Elizabeth Chang, Maja Hadzic
2008 2008 21st IEEE International Symposium on Computer-Based Medical Systems  
The increasing body of distributed and heterogeneous information and the autonomous, heterogeneous and dynamic nature of information resources are important issues hindering effective and efficient data access, retrieval and knowledge sharing. The importance of ontologies has been recognised within the biomedical domain and work has begun on developing and sharing biomedical ontologies. In this paper, we define ontology and ontology commitments and explain the main characteristics and
more » ... tions of ontology models. Ontologies are highly expressive knowledge models and as such increase expressiveness and intelligence of a system. We highlight the significance of ontologies in a variety of semi-automatic and automatic tasks, and provide an illustrative example of an ontology-based multi-agent system designed to intelligently retrieve information about human diseases from a number of heterogeneous and dispersed information resources.
doi:10.1109/cbms.2008.21 dblp:conf/cbms/DillonCH08 fatcat:rpgo3dhtfva67feujl3tfthb6q

Web Semantics for Intelligent and Dynamic Information Retrieval Illustrated within the Mental Health Domain [chapter]

Maja Hadzic, Elizabeth Chang
2008 Lecture Notes in Computer Science  
Much of the available information covering various knowledge domains is distributed across various information resources. The issues of distributed and heterogeneous information that often come without semantics, lack an underlying knowledge base or autonomy, and are dynamic in nature of are hindering efficient and effective information retrieval. Current search engines that are based on syntactic keywords are fundamental for retrieving information often leaving the search results meaningless.
more » ... ncreasing semantics of web content (web semantics) would solve this problem and enable the web to reach its full potential. This would allow machines to access web content, understand it, retrieve and process the data automatically rather then only display it. In this paper we illustrate how the ontology and multi-agent system technologies which underpin this vision can be effectively implemented within the mental health domain. The full realisation of this vision is still to come.
doi:10.1007/978-3-540-89784-2_10 fatcat:ib7usqphgrhsvefykqkn3cc2oq

Using coalgebra and coinduction to define ontology-based multi-agent systems

Maja Hadzic, Elizabeth Chang
2008 International Journal of Metadata, Semantics and Ontologies  
In our previous work (Hadzic and Chang, 2005a; Hadzic et al., 2006) , we showed how ontologies can be used by multi-agent systems in intelligent information retrieval processes.  ...  The GHDO-based Holonic Multi-agent Structure (GHMS) (Hadzic et al., 2006) is a nested hierarchy of four holarchies.  ... 
doi:10.1504/ijmso.2008.023568 fatcat:gsgp3p7ct5ehtfzshbdgyud72u
« Previous Showing results 1 — 15 out of 164 results