288
S. Titi et al.
and food, because they adopt conventional approaches such as classical ontology
and fuzzy logic. The combination of ontologies and fuzzy-logic approaches can
effectively resolve the problem of uncertainty of data related to diabetic patients
and thus ameliorate the accuracy of system when performing decisions related
to the current health condition and recommendations. This paper introduces a
fuzzy-ontology-based healthcare system integrating IoT technologies. The system provides certain and precise diabetes-related decisions that allow patients to
maintain a lifestyle in which the diet is coordinated with exercise and activities.
The remainder of this paper is organized as follows. Section 2 presents related
works. Section 3 then describes the architecture of the proposed system and the
knowledge construction mechanism. Next, Sect. 4 introduces the fuzzy-ontology
generating model. Section 5 describes the semantic fuzzy decision-making process for diabetes system and summarizes the evaluation results. Conclusions and
perspectives are finally drawn in Sect. 6.
2 Related Works
The increasing number of chronically ill aged people worldwide has drawn the
attention of a diverse array of fields including Internet of Things (IoT) and
Artificial Intelligence (IA), explaining why IoT based healthcare systems using
ontology and fuzzy-logic have been adopted for continues real-time monitoring.
For instance, Mumtaj et al. [10] proposed an IoT-based system combining ANN
and fuzzy logic and aims to ensure the monitoring of elderly and supports caregivers to diagnose diseases by sending alerts in case of any abnormalities. Huang
et al. [6] introduced predictive symptom checker system based fuzzy logic that
helps the elderly to decisively determine the most appropriate illness and any
health-related threats. Another system presented in [11] aims to evaluate the
likelihood of developing heart diseases in patients. Another work presented in [3]
introduced an expert fuzzy system for heart disease diagnosis. IoT allows users
to share information everywhere and every time. However, the huge exploitation of the connected objects becomes a source of a mass of heterogeneous data.
Ontologies play an important role to deal with the huge quantity of data by
offering a semantic representation of the domain knowledge. Recently, different ontologies related to IoT based healthcare are proposed. For instance, [12]
describes an ontology-based framework using the semantic IoT that provides
continuous monitoring of patient status. Another work in [14] presents an IoT
based system where an ontology is introduced to provide semantic interoperability among heterogeneous devices and users to ensure remote control of patient
affected by chronic diseases. In [2], the authors proposed a context management
system for smart environments that uses an ontology to model the uncertainty
and vagueness of the contextual information collected to reach a richer inference
process. Authors in [9], propose an ontology-based context management system
that allows the monitoring of the elderly citizens’ behavior and the detection of
risks related to mild cognitive impairments and frailty. The work proposed in
[8] describes a decision support system aiming to ensure the treatment and care
S. Titi et al.
and food, because they adopt conventional approaches such as classical ontology
and fuzzy logic. The combination of ontologies and fuzzy-logic approaches can
effectively resolve the problem of uncertainty of data related to diabetic patients
and thus ameliorate the accuracy of system when performing decisions related
to the current health condition and recommendations. This paper introduces a
fuzzy-ontology-based healthcare system integrating IoT technologies. The system provides certain and precise diabetes-related decisions that allow patients to
maintain a lifestyle in which the diet is coordinated with exercise and activities.
The remainder of this paper is organized as follows. Section 2 presents related
works. Section 3 then describes the architecture of the proposed system and the
knowledge construction mechanism. Next, Sect. 4 introduces the fuzzy-ontology
generating model. Section 5 describes the semantic fuzzy decision-making process for diabetes system and summarizes the evaluation results. Conclusions and
perspectives are finally drawn in Sect. 6.
2 Related Works
The increasing number of chronically ill aged people worldwide has drawn the
attention of a diverse array of fields including Internet of Things (IoT) and
Artificial Intelligence (IA), explaining why IoT based healthcare systems using
ontology and fuzzy-logic have been adopted for continues real-time monitoring.
For instance, Mumtaj et al. [10] proposed an IoT-based system combining ANN
and fuzzy logic and aims to ensure the monitoring of elderly and supports caregivers to diagnose diseases by sending alerts in case of any abnormalities. Huang
et al. [6] introduced predictive symptom checker system based fuzzy logic that
helps the elderly to decisively determine the most appropriate illness and any
health-related threats. Another system presented in [11] aims to evaluate the
likelihood of developing heart diseases in patients. Another work presented in [3]
introduced an expert fuzzy system for heart disease diagnosis. IoT allows users
to share information everywhere and every time. However, the huge exploitation of the connected objects becomes a source of a mass of heterogeneous data.
Ontologies play an important role to deal with the huge quantity of data by
offering a semantic representation of the domain knowledge. Recently, different ontologies related to IoT based healthcare are proposed. For instance, [12]
describes an ontology-based framework using the semantic IoT that provides
continuous monitoring of patient status. Another work in [14] presents an IoT
based system where an ontology is introduced to provide semantic interoperability among heterogeneous devices and users to ensure remote control of patient
affected by chronic diseases. In [2], the authors proposed a context management
system for smart environments that uses an ontology to model the uncertainty
and vagueness of the contextual information collected to reach a richer inference
process. Authors in [9], propose an ontology-based context management system
that allows the monitoring of the elderly citizens’ behavior and the detection of
risks related to mild cognitive impairments and frailty. The work proposed in
[8] describes a decision support system aiming to ensure the treatment and care