Information Technology Reference
In-Depth Information
information, which is often hidden, about their underlying biological systems [1]. In
manual processes, clinicians often make a diagnosis by looking at signal data but the
level of complexity associated with manual analysis and interpretation of these
biomedical signals is great even for experienced clinicians. So, signal processing to
extract clinically significant information from these biomedical signals is valuable
before the data is used by the clinician. Nilsson et al. [2] classify biomedical signals
i.e. Respiratory Sinus Arrhythmia with CBR. Authors in [6], [7] deal with temporal
abstraction by key sequences representing a pattern of signal changes in the medical
domain. Ölmeza and Dokur [3] have applied artificial neural networks to classify
heart sounds. Wavelet transformation is used in [4], [5] to characterize ECG signals.
Increased stress is a continuing problem today. Negative stress could particularly
cause serious health problems if it remains undiagnosed/misdiagnosed and untreated.
Different treatments and exercises can reduce this stress. Since one of the effects of
stress is reduced bodily awareness, it is easy to miss signals such as high tension in
the muscles, unnatural breathing, blood-sugar fluctuations and cardiovascular func-
tionality etc. It may take many weeks or months to become aware of the increased
stress level, and once it is noticed, the effects and misaligned processes, e.g. of meta-
bolic processes, may need long and active behavioral treatment to revert to a normal
state [8]. For patients with high blood pressure and heart problems high stress levels
may be directly life-endangering. A system determining a person's stress profile and
potential health problems would be valuable both in a clinical environment as a sec-
ond opinion or in the home environment to be used as part of a stress management
program.
During stress the sympathetic nervous system is activated causing a decrease in pe-
ripheral circulation which in turn decreases the skin temperature. However during
relaxation, a reverse effect (i.e. activation of the parasympathetic nervous system)
occurs resulting in the increase of skin temperature. In this way, the finger skin tem-
perature responds to stress [69]. The pattern of variation within a finger temperature
signal could help to determine stress-related disorders. Other conventional methods
for measuring stress such as taking measurements of respiration (e.g. end-tidal carbon
dioxide (ETCO2)), heart rate (e.g. calculating the respiratory sinus arrhythmia (RSA))
and heart rate variability (HRV) is often expensive and requires equipment (using
many sensors) which is not suitable for use in non-clinical environments or without
supervision of experienced clinical staff. Finger temperature measurements on the
other hand can be collected using a sensor which is comparatively low in cost and can
be used as a supplementary and convenient tool by general users to diagnose and
control stress at home or at work. However, the characteristics of finger temperature
(FT) is different for different individuals due to health factors, metabolic activity etc.
In practice, it is difficult and tedious even for an experienced clinician to understand,
interpret and analyze complex, lengthy sequential measurements in order to determine
the stress levels. Since there are significant individual variations when looking at the
FT, this is a worthy challenge to find a computational solution to apply it in a com-
puter-based system.
Therefore, this chapter presents a general paradigm in which a case-based approach
is used as a core technique to facilitate experience reuse based on signals to develop a
computer-based stress diagnosis system that can be used by people who need to
monitor their stress level during everyday situations e.g. at home and work for health
Search WWH ::
Custom Search