No abstract

No abstract

Actigraphs for personalized health and fitness monitoring is a trending niche market and fit aptly in the Internet of Medical Things (IoMT) paradigm. Conventionally, actigraphy is acquired and digitized using standard low pass filtering and quantization techniques. High sampling frequencies and quantization resolution of various actigraphs can lead to memory leakage and unwanted battery usage. Our systematic investigation on different types of actigraphy signals yields that lower levels of quantization are sufficient for acquiring and storing vital movement information while ensuring an increase in SNR, higher space savings, and in faster time. The objective of this study is to propose a low-level signal encoding method which could improve data acquisition and storage in actigraphs, as well as enhance signal clarity for pattern classification. To further verify this study, we have used a machine learning approach which suggests that signal encoding also improves pattern recognition accuracy. Our experiments indicate that signal encoding at the source results in an increase in SNR (signal-to-noise ratio) by at least 50–90%, coupled with a bit rate reduction by 50–80%, and an overall space savings in the range of 68–92%, depending on the type of actigraph and application used in our study. Consistent improvements by lowering the quantization factor also indicates that a 3-bit encoding of actigraphy data retains most prominent movement information, and also results in an increase of the pattern recognition accuracy by at least 10%.

SUMMARYActigraphy can assist in the detection of periodic limb movements in sleep. Although several actigraphs have been previously reported to accurately detect periodic limb movements, many are no longer available; of the existing actigraphs, most sample too infrequently to accurately detect periodic limb movements. The purpose of this study was to use advanced signal analysis to validate a readily available actigraph that has the capability of sampling at relatively high frequencies. We simultaneously recorded polysomnography and bilateral ankle actigraphy in 96 consecutive patients presenting to our sleep laboratory. After pre-processing and conditioning, the bilateral ankle actigraphy signals were then analysed for 14 simple time, frequency and morphology-based features. These features reduced the signal dimensionality and aided in better representation of the periodic limb movement activity in the actigraph signals. These features were then processed by a Na€ ıve-Bayes binary classifier for distinguishing between normal and abnormal periodic limb movement indices. We trained the Na€ ıve-Bayes classifier using a training set, and subsequently tested its classification accuracy using a testing set. From our experiments, using a periodic limb movement index cut-off of 5, we found that the Na€ ıve-Bayes classifier had a correct classification rate of 78.9%, with a sensitivity of 80.3% and a specificity of 73.7%. The algorithm developed in this study has the potential of facilitating identification of periodic limb movements across a wide spectrum of patient populations via the use of bilateral ankle actigraphy.

The intention of this study is to gauge the performance of Fisher kernels for dimension simplification and classification of time-series signals. Our research work has indicated that Fisher kernels have shown substantial improvement in signal classification by enabling clearer pattern visualization in three-dimensional space. In this paper, we will exhibit the performance of Fisher kernels for two domains: financial and biomedical. The financial domain study involves identifying the possibility of collapse or survival of a company trading in the stock market. For assessing the fate of each company, we have collected financial time-series composed of weekly closing stock prices in a common time frame, using Thomson Datastream software. The biomedical domain study involves knee signals collected using the vibration arthrometry technique. This study uses the severity of cartilage degeneration for classifying normal and abnormal knee joints. In both studies, we apply Fisher Kernels incorporated with a Gaussian mixture model (GMM) for dimension transformation into feature space, which is created as a three-dimensional plot for visualization and for further classification using support vector machines. From our experiments we observe that Fisher Kernel usage fits really well for both kinds of signals, with low classification error rates.