Sensor Fusion and Smart Sensor in Sports and Biomedical Applications

José Mendes Jr., Mário Vieira, Marcelo Pires, Sergio Stevan Jr.
2016 Sensors  
The following work presents an overview of smart sensors and sensor fusion targeted at biomedical applications and sports areas. In this work, the integration of these areas is demonstrated, promoting a reflection about techniques and applications to collect, quantify and qualify some physical variables associated with the human body. These techniques are presented in various biomedical and sports applications, which cover areas related to diagnostics, rehabilitation, physical monitoring, and
more » ... e development of performance in athletes, among others. Although some applications are described in only one of two fields of study (biomedicine and sports), it is very likely that the same application fits in both, with small peculiarities or adaptations. To illustrate the contemporaneity of applications, an analysis of specialized papers published in the last six years has been made. In this context, the main characteristic of this review is to present the largest quantity of relevant examples of sensor fusion and smart sensors focusing on their utilization and proposals, without deeply addressing one specific system or technique, to the detriment of the others. The sensor fusion concept is increasingly widespread and discussed these days, making it comparable to a Science [1]. Due to a large amount of features involved, it is unlikely that only one signal acquisition can provide a satisfactory compression system or variable analysis [2] . In general, sensor fusion is the combination of different data from sensors that may result in more complex analysis, which are not possible with the use of sensors singularly and/or separately [3] . In addition to data acquisition of different magnitudes, sensor fusion includes management and combination of this data with strategies to provide consistent and effective responses [1] . The development of fusion techniques is driven by the overview of a given system to be analyzed in order to improve the decision-making process into specific actions in the same system. The areas most affected by this technology are in commercial, social, biomedical, environmental, military, sociological, and psychological scopes of effects: in short, often interdisciplinary interaction [1, 2, 4] . When it comes to sensor fusion, there are two situations. During the first, the fusion is done on sensors with different signals [5] ; while the second merges data, which is not necessarily of different magnitudes, but with equivalent sensors in different situations. Traditionally, its structure is composed of three levels, which act sequentially: acquisition and data merger, fusion of characteristics, and merger of decisions [1]. These three levels work with information in different classes, as shown in Figure 1 . The first level (low) is composed of different sensors that collect signals from n variables, which can be physical quantities, chemical, biological or images (pixels). The second rating level (average) refers to handling and processing obtained signals, from which their main information is extracted. Finally, in the third level (high), there are manipulation classes, which create a fusion of symbols (characters, recognized information and strategies), and also where decision algorithms for recognition and transmission information are applied. Sensors 2016, 16, 1569 2 of 31 The sensor fusion concept is increasingly widespread and discussed these days, making it comparable to a Science [1]. Due to a large amount of features involved, it is unlikely that only one signal acquisition can provide a satisfactory compression system or variable analysis [2] . In general, sensor fusion is the combination of different data from sensors that may result in more complex analysis, which are not possible with the use of sensors singularly and/or separately [3] . In addition to data acquisition of different magnitudes, sensor fusion includes management and combination of this data with strategies to provide consistent and effective responses [1] . The development of fusion techniques is driven by the overview of a given system to be analyzed in order to improve the decision-making process into specific actions in the same system. The areas most affected by this technology are in commercial, social, biomedical, environmental, military, sociological, and psychological scopes of effects: in short, often interdisciplinary interaction [1, 2, 4] . When it comes to sensor fusion, there are two situations. During the first, the fusion is done on sensors with different signals [5] ; while the second merges data, which is not necessarily of different magnitudes, but with equivalent sensors in different situations. Traditionally, its structure is composed of three levels, which act sequentially: acquisition and data merger, fusion of characteristics, and merger of decisions [1]. These three levels work with information in different classes, as shown in Figure 1 . The first level (low) is composed of different sensors that collect signals from n variables, which can be physical quantities, chemical, biological or images (pixels). The second rating level (average) refers to handling and processing obtained signals, from which their main information is extracted. Finally, in the third level (high), there are manipulation classes, which create a fusion of symbols (characters, recognized information and strategies), and also where decision algorithms for recognition and transmission information are applied.
doi:10.3390/s16101569 pmid:27669260 pmcid:PMC5087358 fatcat:fankvzg6sffavkx4fcgwthxn2e