SynSys: A Synthetic Data Generation System for Healthcare Applications

Abstract

Creation of realistic synthetic behavior-based sensor data is an important aspect of testing machine learning techniques for healthcare applications. Many of the existing approaches for generating synthetic data are often limited in terms of complexity and realism. We introduce SynSys, a machine learning-based synthetic data generation method, to improve upon these limitations. We use this method to generate synthetic time series data that is composed of nested sequences using hidden Markov models and regression models which are initially trained on real datasets. We test our synthetic data generation technique on a real annotated smart home dataset. We use time series distance measures as a baseline to determine how realistic the generated data is compared to real data and demonstrate that SynSys produces more realistic data in terms of distance compared to random data generation, data from another home, and data from another time period. Finally, we apply our synthetic data generation technique to the problem of generating data when only a small amount of ground truth data is available. Using semi-supervised learning we demonstrate that SynSys is able to improve activity recognition accuracy compared to using the small amount of real data alone.

CbDGen: Uma ferramenta de geração de dados sintéticos baseada na complexidade

“…O trabalho gera regras de aprendizado com base nos atributos inseridos pelo usuário para construir relacionamentos entre esses atributos, e a técnica utilizada foi aárvore de decisão. Existem também trabalhos que produzem dados para problemas específicos, como (Dahmen and Cook 2019) que escreveram um artigo sobre o sistema de geração de dados para aplicativos de assistência médica, limitando a geração de novos dados apenas para esses casos.…”

Data Augmentation with Suboptimal Warping for Time-Series Classification

“…Krall et al [17], in turn, augmented electroencephalographic data using temporal and spatial or rotational distortions. The importance of time-series augmentation for healthcare applications was considered by Dahmen and Cook [18]. In that work, nested sequences obtained with hidden Markov models and regression models were used.…”

A Review of the Recent Developments in Integrating Machine Learning Models with Sensor Devices in the Smart Buildings Sector with a View to Attaining Enhanced Sensing, Energy Efficiency, and Optimal Building Management

“…Analyzing the papers selected and summarized in Table S13, it can be observed that 78% of them exclusively analyze smart homes, 16% take into consideration smart buildings in general, 3% analyze both smart homes and buildings, while the remaining 3% of the selected papers refer to smart workplace environments. The authors of these scientific articles make use of different types of sensors in their analyses, including wireless sensor networks [70,115,[119][120][121][122][123][124]; passive infrared motion sensors [82,97,117,118,122,125,126]; motion sensors [25,70,81,118,120,127,128]; environmental sensors [10,25,81,82,[116][117][118]123,[127][128][129][130][131][132]; temperature sensors [116,118,120,123,125,[131][132][133]; humidity sensors…”

“…The performance metrics that chosen by the authors of the scientific papers using the Hidden Markov Model integrated with sensor devices in smart buildings included: Accuracy [3,10,25,33,70,115,117,120,122,123,125,127,131,133,136,138]; Precision [25,118,128,133,135,137]; Recall [25,118,128,135]; F-Measure [25,81,121,130,133]; Sensitivity and Specificity [25,33,133]; F1 Score [116,133]; Confusion Matrix [116,127,129]; and Correctness [97,118]. In addition to the above-mentioned performance metrics, other methods that were used to assess the performance of the developed methods by the authors of the scientific papers selected and summarized in Table S13 included: a numerical case study highlighting the efficiency of the developed model [134]; thread latency [119]; evaluation of energy savings…”

“…In [117], Dahmen et al analyzed methods for "testing machine learning techniques for healthcare applications", aiming to overcome the limitations related to the complexity and lack of applicability of many actual approaches. To this end, the authors developed a synthetic data generation method based on Machine Learning techniques, SynSys.…”