50
views
0
recommends
+1 Recommend
0 collections
    4
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Modeling long-term human activeness using recurrent neural networks for biometric data.

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          With the invention of fitness trackers, it has been possible to continuously monitor a user's biometric data such as heart rates, number of footsteps taken, and amount of calories burned. This paper names the time series of these three types of biometric data, the user's "activeness", and investigates the feasibility in modeling and predicting the long-term activeness of the user.

          Related collections

          Most cited references16

          • Record: found
          • Abstract: found
          • Article: not found

          LSTM: A Search Space Odyssey

          Several variants of the long short-term memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful functional ANalysis Of VAriance framework. In total, we summarize the results of 5400 experimental runs ( ≈ 15 years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes.

            Physicians classify patients into those with or without a specific disease. Furthermore, there is often interest in classifying patients according to disease etiology or subtype. Classification trees are frequently used to classify patients according to the presence or absence of a disease. However, classification trees can suffer from limited accuracy. In the data-mining and machine-learning literature, alternate classification schemes have been developed. These include bootstrap aggregation (bagging), boosting, random forests, and support vector machines. We compared the performance of these classification methods with that of conventional classification trees to classify patients with heart failure (HF) according to the following subtypes: HF with preserved ejection fraction (HFPEF) and HF with reduced ejection fraction. We also compared the ability of these methods to predict the probability of the presence of HFPEF with that of conventional logistic regression. We found that modern, flexible tree-based methods from the data-mining literature offer substantial improvement in prediction and classification of HF subtype compared with conventional classification and regression trees. However, conventional logistic regression had superior performance for predicting the probability of the presence of HFPEF compared with the methods proposed in the data-mining literature. The use of tree-based methods offers superior performance over conventional classification and regression trees for predicting and classifying HF subtypes in a population-based sample of patients from Ontario, Canada. However, these methods do not offer substantial improvements over logistic regression for predicting the presence of HFPEF. Copyright © 2013 Elsevier Inc. All rights reserved.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Prediction of energy expenditure from heart rate monitoring during submaximal exercise.

              The aims of this study were to quantify the effects of factors such as mode of exercise, body composition and training on the relationship between heart rate and physical activity energy expenditure (measured in kJ x min(-1)) and to develop prediction equations for energy expenditure from heart rate. Regularly exercising individuals (n = 115; age 18-45 years, body mass 47-120 kg) underwent a test for maximal oxygen uptake (VO2max test), using incremental protocols on either a cycle ergometer or treadmill; VO2max ranged from 27 to 81 ml x kg(-1) x min(-1). The participants then completed three steady-state exercise stages on either the treadmill (10 min) or the cycle ergometer (15 min) at 35%, 62% and 80% of VO2max, corresponding to 57%, 77% and 90% of maximal heart rate. Heart rate and respiratory exchange ratio data were collected during each stage. A mixed-model analysis identified gender, heart rate, weight, V2max and age as factors that best predicted the relationship between heart rate and energy expenditure. The model (with the highest likelihood ratio) was used to estimate energy expenditure. The correlation coefficient (r) between the measured and estimated energy expenditure was 0.913. The model therefore accounted for 83.3% (R2) of the variance in energy expenditure in this sample. Because a measure of fitness, such as VO2max, is not always available, a model without VO2max included was also fitted. The correlation coefficient between the measured energy expenditure and estimates from the mixed model without VO2max was 0.857. It follows that the model without a fitness measure accounted for 73.4% of the variance in energy expenditure in this sample. Based on these results, we conclude that it is possible to estimate physical activity energy expenditure from heart rate in a group of individuals with a great deal of accuracy, after adjusting for age, gender, body mass and fitness.
                Bookmark

                Author and article information

                Journal
                BMC Med Inform Decis Mak
                BMC medical informatics and decision making
                Springer Nature
                1472-6947
                1472-6947
                May 18 2017
                : 17
                : Suppl 1
                Affiliations
                [1 ] School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, South Korea.
                [2 ] Samsung Seoul R&D Campus, Samsung Electronics, 33 Seongchon-gil, Seocho-gu, Seoul, 06765, South Korea.
                [3 ] School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, South Korea. hojinc@kaist.ac.kr.
                Article
                10.1186/s12911-017-0453-1
                10.1186/s12911-017-0453-1
                5444042
                28539116
                63d62e80-9126-4522-b6b3-452c9b9a41bd
                History

                Activeness prediction,Calorie,Footstep,Heart rate,Recurrent neural network,Time series modeling

                Comments

                Comment on this article