oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 11) Show all publications
Banaee, H., Schaffernicht, E. & Loutfi, A. (2018). Data-Driven Conceptual Spaces: Creating Semantic Representations for Linguistic Descriptions of Numerical Data. The journal of artificial intelligence research, 63, 691-742
Open this publication in new window or tab >>Data-Driven Conceptual Spaces: Creating Semantic Representations for Linguistic Descriptions of Numerical Data
2018 (English)In: The journal of artificial intelligence research, ISSN 1076-9757, E-ISSN 1943-5037, Vol. 63, p. 691-742Article in journal (Refereed) Published
Abstract [en]

There is an increasing need to derive semantics from real-world observations to facilitate natural information sharing between machine and human. Conceptual spaces theory is a possible approach and has been proposed as mid-level representation between symbolic and sub-symbolic representations, whereby concepts are represented in a geometrical space that is characterised by a number of quality dimensions. Currently, much of the work has demonstrated how conceptual spaces are created in a knowledge-driven manner, relying on prior knowledge to form concepts and identify quality dimensions. This paper presents a method to create semantic representations using data-driven conceptual spaces which are then used to derive linguistic descriptions of numerical data. Our contribution is a principled approach to automatically construct a conceptual space from a set of known observations wherein the quality dimensions and domains are not known a priori. This novelty of the approach is the ability to select and group semantic features to discriminate between concepts in a data-driven manner while preserving the semantic interpretation that is needed to infer linguistic descriptions for interaction with humans. Two data sets representing leaf images and time series signals are used to evaluate the method. An empirical evaluation for each case study assesses how well linguistic descriptions generated from the conceptual spaces identify unknown observations. Furthermore,  comparisons are made with descriptions derived on alternative approaches for generating semantic models.

Place, publisher, year, edition, pages
AAAI Press, 2018
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-70433 (URN)10.1613/jair.1.11258 (DOI)000455091500015 ()2-s2.0-85057746407 (Scopus ID)
Available from: 2018-12-04 Created: 2018-12-04 Last updated: 2019-01-23Bibliographically approved
Banaee, H. (2018). From Numerical Sensor Data to Semantic Representations: A Data-driven Approach for Generating Linguistic Descriptions. (Doctoral dissertation). Örebro: Örebro University
Open this publication in new window or tab >>From Numerical Sensor Data to Semantic Representations: A Data-driven Approach for Generating Linguistic Descriptions
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

In our daily lives, sensors recordings are becoming more and more ubiquitous. With the increased availability of data comes the increased need of systems that can represent the data in human interpretable concepts. In order to describe unknown observations in natural language, an artificial intelligence system must deal with several issues involving perception, concept formation, and linguistic description. These issues cover various subfields within artificial intelligence, such as machine learning, cognitive science, and natural language generation.The aim of this thesis is to address the problem of semantically modelling and describing numerical observations from sensor data. This thesis introduces data-driven approaches to perform the tasks of mining numerical data and creating semantic representations of the derived information in order to describe unseen but interesting observations in natural language.The research considers creating a semantic representation using the theory of conceptual spaces. In particular, the central contribution of this thesis is to present a data-driven approach that automatically constructs conceptual spaces from labelled numerical data sets. This constructed conceptual space then utilises semantic inference techniques to derive linguistic interpretations for novel unknown observations. Another contribution of this thesis is to explore an instantiation of the proposed approach in a real-world application. Specifically, this research investigates a case study where the proposed approach is used to describe unknown time series patterns that emerge from physiological sensor data. This instantiation first presents automatic data analysis methods to extract time series patterns and temporal rules from multiple channels of physiological sensor data, and then applies various linguistic description approaches (including the proposed semantic representation based on conceptual spaces) to generate human-readable natural language descriptions for such time series patterns and temporal rules.The main outcome of this thesis is the use of data-driven strategies that enable the system to reveal and explain aspects of sensor data which may otherwise be difficult to capture by knowledge-driven techniques alone. Briefly put, the thesis aims to automate the process whereby unknown observations of data can be 1) numerically analysed, 2) semantically represented, and eventually 3) linguistically described.

Place, publisher, year, edition, pages
Örebro: Örebro University, 2018. p. 188
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 78
Keywords
Semantic representations, Conceptual spaces, Natural language generation, Temporal rule mining, Physiological sensors, Health monitoring system
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-65318 (URN)978-91-7529-240-3 (ISBN)
Public defence
2018-04-20, Örebro universitet, Teknikhuset, Hörsal T, Fakultetsgatan 1, Örebro, 13:15 (English)
Opponent
Supervisors
Available from: 2018-02-28 Created: 2018-02-28 Last updated: 2018-03-28Bibliographically approved
Vajdi, A., Haspel, N. & Banaee, H. (2015). A New DP Algorithm for Comparing Gene Expression Data Using Geometric Similarity. In: Proceedings 2015 IEEE International Conference on Bioinformatics and Biomedicine: . Paper presented at IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2015), Washington, DC, USA, November 9-12, 2015 (pp. 1157-1161). New York: IEEE conference proceedings
Open this publication in new window or tab >>A New DP Algorithm for Comparing Gene Expression Data Using Geometric Similarity
2015 (English)In: Proceedings 2015 IEEE International Conference on Bioinformatics and Biomedicine, New York: IEEE conference proceedings , 2015, p. 1157-1161Conference paper, Published paper (Refereed)
Abstract [en]

Microarray gene expression data comes as a time series, where the expression level of a gene is recorded at specific time points. Comparing the time series produced by two genes can give us information about the regulatory or inhibitory relationship between the genes. We present a Dynamic Programming (DP) method to compare gene expression data using geometric similarity. We aim to detect similarities and relationships between genes, based on their expression time series. By representing the time series as polygons and compare them, we can find relationships that are not available when the two time series are compared point-by-point. We applied our algorithm on a dataset of 343 regulatory pairs from the alpha dataset and compared them to randomly generated pairs. Using an SVM classifier, we find the optimal similarity score that separates the regulatory dataset from the random pairs. Our results show that we can detect similar pairs better than simple Pearson correlation and we outperform many of the existing methods. This method is an ongoing approach, that can be applied to finding the similarity of any data that can convert to 2D polygon. In the future, we plan to introduce this method as a new classifier.

Place, publisher, year, edition, pages
New York: IEEE conference proceedings, 2015
Series
IEEE International Conference on Bioinformatics and Biomedicine-BIBM, ISSN 2156-1125
Keywords
gene expression time series, clustering, Polygons, dynamic programming, polygonal chain alignment
National Category
Computer Sciences Biological Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-51688 (URN)10.1109/BIBM.2015.7359846 (DOI)000377335600307 ()2-s2.0-84962385706 (Scopus ID)978-1-4673-6798-1 (ISBN)
Conference
IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2015), Washington, DC, USA, November 9-12, 2015
Available from: 2016-08-17 Created: 2016-08-17 Last updated: 2018-09-12Bibliographically approved
Banaee, H. & Loutfi, A. (2015). Data-driven rule mining and representation of temporal patterns in physiological sensor data. IEEE journal of biomedical and health informatics, 19(5), 1557-1566
Open this publication in new window or tab >>Data-driven rule mining and representation of temporal patterns in physiological sensor data
2015 (English)In: IEEE journal of biomedical and health informatics, ISSN 2168-2194, E-ISSN 2168-2208, Vol. 19, no 5, p. 1557-1566Article in journal (Refereed) Published
Abstract [en]

Mining and representation of qualitative patterns is a growing field in sensor data analytics. This paper leverages from rule mining techniques to extract and represent temporal relation of prototypical patterns in clinical data streams. The approach is fully data-driven, where the temporal rules are mined from physiological time series such as heart rate, respiration rate, and blood pressure. To validate the rules, a novel similarity method is introduced, that compares the similarity between rule sets. An additional aspect of the proposed approach has been to utilize natural language generation techniques to represent the temporal relations between patterns. In this study, the sensor data in the MIMIC online database was used for evaluation, in which the mined temporal rules as they relate to various clinical conditions (respiratory failure, angina, sepsis, ...) were made explicit as a textual representation. Furthermore, it was shown that the extracted rule set for any particular clinical condition was distinct from other clinical conditions.

Keywords
Data-driven modeling, health informatics, linguistic representation, pattern abstraction, physiological sensor data, sensor data analysis, temporal rule mining
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-46037 (URN)10.1109/JBHI.2015.2438645 (DOI)000360791200004 ()26340684 (PubMedID)2-s2.0-84940989008 (Scopus ID)
Available from: 2015-10-07 Created: 2015-10-07 Last updated: 2018-01-11Bibliographically approved
Banaee, H., Ahmed, M. U. & Loutfi, A. (2015). Descriptive Modelling of Clinical Conditions with Data-driven Rule Mining in Physiological Data. In: Proceedings of the 8th International conference of Health Informatics (HEALTHINF 2015): . Paper presented at HEALTHINF 2015 : HEALTHINF 8th International Conference on Health Informatics, 12-15 january, Lisabon, Portugal. SciTePress
Open this publication in new window or tab >>Descriptive Modelling of Clinical Conditions with Data-driven Rule Mining in Physiological Data
2015 (English)In: Proceedings of the 8th International conference of Health Informatics (HEALTHINF 2015), SciTePress, 2015Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an approach to automatically mine rules in time series data representing physiologicalparameters in clinical conditions. The approach is fully data driven, where prototypical patterns are mined foreach physiological time series data. The generated rules based on the prototypical patterns are then describedin a textual representation which captures trends in each physiological parameter and their relation to the otherphysiological data. In this paper, a method for measuring similarity of rule sets is introduced in order tovalidate the uniqueness of rule sets. This method is evaluated on physiological records from clinical classesin the MIMIC online database such as angina, sepsis, respiratory failure, etc.. The results show that the rulemining technique is able to acquire a distinctive model for each clinical condition, and represent the generatedrules in a human understandable textual representation

Place, publisher, year, edition, pages
SciTePress, 2015
Keywords
rule mining, pattern abstraction, health parameters, physiological time series, clinical condition.
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-39650 (URN)978-989-758-068-0 (ISBN)
Conference
HEALTHINF 2015 : HEALTHINF 8th International Conference on Health Informatics, 12-15 january, Lisabon, Portugal
Available from: 2014-12-14 Created: 2014-12-14 Last updated: 2018-01-11Bibliographically approved
Ahmed, M. U., Banaee, H., Rafael-Palou, X. & Loutfi, A. (2015). Intelligent Healthcare Services to Support Health Monitoring of Elderly. In: INTERNET OF THINGS: USER-CENTRIC IOT, PT I. Paper presented at 1st International Conference on IoT Technologies for HealthCare, HealthyIoT, October 27-29, Rome, Italy, 2014 (pp. 178-186). Springer, 150
Open this publication in new window or tab >>Intelligent Healthcare Services to Support Health Monitoring of Elderly
2015 (English)In: INTERNET OF THINGS: USER-CENTRIC IOT, PT I, Springer, 2015, Vol. 150, p. 178-186Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposed an approach of intelligent healthcare services to support health monitoring of old people through the project named SAAPHO. Here, definition and architecture of the proposed healthcare services are presented considering six different health parameters such as: 1) physical activity, 2) blood pressure, 3) glucose, 4) medication compliance, 5) pulse monitoring and 6) weight monitoring. The outcome of the proposed services is evaluated in a case study where total 201 subjects from Spain and Slovenia are involved for user requirements analysis considering 1) end users, 2) clinicians, and 3) field study analysis perspectives. The result shows the potentiality and competence of the proposed healthcare services for the users.

Place, publisher, year, edition, pages
Springer, 2015
Series
Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering, ISSN 1867-8211 ; 150
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-36619 (URN)10.1007/978-3-319-19656-5_26 (DOI)000365176500026 ()978-3-319-19656-5 (ISBN)978-3-319-19655-8 (ISBN)
Conference
1st International Conference on IoT Technologies for HealthCare, HealthyIoT, October 27-29, Rome, Italy, 2014
Projects
SAAPHO
Available from: 2014-09-16 Created: 2014-09-16 Last updated: 2018-01-11Bibliographically approved
Banaee, H. & Loutfi, A. (2014). Using Conceptual Spaces to Model Domain Knowledge in Data-to-Text Systems. In: Proceedings of the 8th International Natural Language Generation Conference: . Paper presented at 8th International Natural Language Generation(INLG)Conference, 19-21 June, Philadelphia, Pennsylvania, USA (pp. 11-15). Association for Computational Linguistics
Open this publication in new window or tab >>Using Conceptual Spaces to Model Domain Knowledge in Data-to-Text Systems
2014 (English)In: Proceedings of the 8th International Natural Language Generation Conference, Association for Computational Linguistics, 2014, p. 11-15Conference paper, Published paper (Refereed)
Abstract [en]

This position paper introduces the utilityof the conceptual spaces theory to conceptualisethe acquired knowledge in data-totextsystems. A use case of the proposedmethod is presented for text generationsystems dealing with sensor data. Modellinginformation in a conceptual spaceexploits a spatial representation of domainknowledge in order to perceive unexpectedobservations. This ongoing work aimsto apply conceptual spaces in NLG forgrounding numeric information into thesymbolic representation and confrontingthe important step of acquiring adequateknowledge in data-to-text systems.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2014
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-39444 (URN)
Conference
8th International Natural Language Generation(INLG)Conference, 19-21 June, Philadelphia, Pennsylvania, USA
Projects
SAAPHO
Available from: 2014-12-09 Created: 2014-12-09 Last updated: 2018-01-11Bibliographically approved
Banaee, H., Ahmed, M. U. & Loutfi, A. (2013). A framework for automatic text generation of trends in physiological time series data. In: IEEE International Conference on Systems, Man, and Cybernetics, 13-16 Oct. 2013, Manchester: . Paper presented at IEEE International Conference on Systems, Man, and Cybernetics, 13-16 Oct. 2013, Manchester (pp. 3876-3881). IEEE conference proceedings
Open this publication in new window or tab >>A framework for automatic text generation of trends in physiological time series data
2013 (English)In: IEEE International Conference on Systems, Man, and Cybernetics, 13-16 Oct. 2013, Manchester, IEEE conference proceedings, 2013, p. 3876-3881Conference paper, Published paper (Refereed)
Abstract [en]

Health monitoring systems using wearable sensorshave rapidly grown in the biomedical community. The mainchallenges in physiological data monitoring are to analyse largevolumes of health measurements and to represent the acquiredinformation. Natural language generation is an effective methodto create summaries for both clinicians and patients as it candescribe useful information extracted from sensor data in textualformat. This paper presents a framework of a natural languagegeneration system that provides a text-based representation ofthe extracted numeric information from physiological sensorsignals. More specifically, a new partial trend detection algorithmis introduced to capture the particular changes and events ofhealth parameters. The extracted information is then representedconsidering linguistic characterisation of numeric features. Ex-perimental analysis was performed using a wearable sensor and demonstrates a possible output in natural language text.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2013
Keywords
Health monitoring, physiological data analysis, body area networks, natural language generation, linguistic summarisation
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-32260 (URN)10.1109/SMC.2013.661 (DOI)000332201904002 ()2-s2.0-84890455979 (Scopus ID)978-1-4799-0652-9 (ISBN)
Conference
IEEE International Conference on Systems, Man, and Cybernetics, 13-16 Oct. 2013, Manchester
Available from: 2013-11-06 Created: 2013-11-06 Last updated: 2018-01-11Bibliographically approved
Banaee, H., Ahmed, M. U. & Loutfi, A. (2013). Data mining for wearable sensors in health monitoring systems: a review of recent trends and challenges. Sensors, 13(12), 17472-17500
Open this publication in new window or tab >>Data mining for wearable sensors in health monitoring systems: a review of recent trends and challenges
2013 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 13, no 12, p. 17472-17500Article in journal (Refereed) Published
Abstract [en]

The past few years have witnessed an increase in the development of wearable sensors for health monitoring systems. This increase has been due to several factors such as development in sensor technology as well as directed efforts on political and stakeholder levels to promote projects which address the need for providing new methods for care given increasing challenges with an aging population. An important aspect of study in such system is how the data is treated and processed. This paper provides a recent review of the latest methods and algorithms used to analyze data from wearable sensors used for physiological monitoring of vital signs in healthcare services. In particular, the paper outlines the more common data mining tasks that have been applied such as anomaly detection, prediction and decision making when considering in particular continuous time series measurements. Moreover, the paper further details the suitability of particular data mining and machine learning methods used to process the physiological data and provides an overview of the properties of the data sets used in experimental validation. Finally, based on this literature review, a number of key challenges have been outlined for data mining methods in health monitoring systems

Place, publisher, year, edition, pages
Basel: MDPI, 2013
Keywords
data mining; wearable sensors; healthcare; physiological sensors; health monitoring system; machine learning technique; vital signs; medical informatics
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-32866 (URN)10.3390/s131217472 (DOI)000330220600086 ()
Note

Funding Agencies:

SAAPHO (Secure Active Aging: Participation and Health for the Old)

Vinnova Sweden's Innovation Funding Agency

Available from: 2013-12-22 Created: 2013-12-22 Last updated: 2018-01-11Bibliographically approved
Ahmed, M. U., Banaee, H. & Loutfi, A. (2013). Health monitoring for elderly: an application using case-based reasoning and cluster analysis. ISRN Artificial Intelligence, 2013(2013), 1-11
Open this publication in new window or tab >>Health monitoring for elderly: an application using case-based reasoning and cluster analysis
2013 (English)In: ISRN Artificial Intelligence, ISSN 2090-7435, E-ISSN 2090-7443, Vol. 2013, no 2013, p. 1-11Article in journal (Refereed) Published
Abstract [en]

This paper presents a framework to process and analyze data from a pulse oximeter which measures pulse rate and blood oxygen saturation from a set of individuals remotely. Using case-based reasoning (CBR) as the backbone to the framework, records are analyzed and categorized according to how well they are similar. Record collection has been performed using a personalized health profiling approach where participants wore a pulse oximeter sensor for a fixed period of time and performed specific activities for pre-determined intervals. Using a variety of feature extraction in time, frequency and time-frequency domains, and data processing techniques, the data is fed into a CBR system which retrieves most similar cases and generates alarm and flag according to the case outcomes. The system has been compared with an expert's classification and 90% match is achieved between the expert's and CBR classification. Again, considering the clustered measurements the CBR approach classifies 93% correctly both for the pulse rate and oxygen saturation. Along with the proposed methodology, this paper provides a basis for which the system can be used in analysis of continuous health monitoring and be used as a suitable method as in home/remote monitoring systems.

Keywords
Health Monitoring, Elderly, Case-Based Reasoning, Cluster Analysis
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-28738 (URN)10.1155/2013/380239 (DOI)
Projects
SAAPHOREMOTE
Funder
EU, FP7, Seventh Framework Programme
Available from: 2013-04-20 Created: 2013-04-20 Last updated: 2017-12-06Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-9607-9504

Search in DiVA

Show all publications