Learning from Life-Logging Data by Hybrid HMM: A Case Study on Active States Prediction

Ni, Jinfu; Lambrou, Tryphon; Ye, Xujiong

doi:10.2316/p.2016.832-019

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many models have been proposed to solve the imbalanced data classification problem. These models include: k-NN [8] [12], SVM [13], SVM and HMM Hybrids [14]- [15], HMMs [16] [8]- [9], Neural Networks and CNN models [1] [17].…”

Section: Imbalanced Data Classificationmentioning

confidence: 99%

Imbalanced Data Classification Using Auxiliary Classifier Generative Adversarial Networks

Sutedja¹

2020

IJATCSE

View full text Add to dashboard Cite

This paper explores an Auxiliary Classifier Generative Adversarial Networks (AC-GAN) model to address imbalanced data classifications. More specifically, debit card transaction data from a private Indonesian bank were categorized into fraudulent and non-fraudulent transactions. Training and testing datasets were then analyzed. Due to its architectural similarity, this study explores the learning performance of an AC-GAN Discriminator model and compares it with the learning performance of a Convolutional Neural Network (CNN) model, as a baseline model. The experimental results illustrate that the training and testing accuracy of the AC-GAN discriminator model (i.e., 81.1% and 93.0%, respectively) outperformed the CNN model (i.e., 68.1% and 67.7%). Given the similar structures of AC-GAN discriminators and CNN models, it is hypothesized that AC-GAN discriminators can perform better than CNNs. This is because the effect of the adversarial training approach embedded up-sampling techniques into the model-training process.

show abstract

Section: Imbalanced Data Classificationmentioning

confidence: 99%

Imbalanced Data Classification Using Auxiliary Classifier Generative Adversarial Networks

Sutedja¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…In most of these studies, the noise injection is based on the study by [16] where noise injection was used with K-nearest neighbors algorithm in multilayer perceptron training. However, what is noticeable is that noise injection has been used to with wearable sensor data only to balance data ( [17]) but it has not been studied how it can be used to build more general models from a small original data set.…”

Section: Problem Statement and Related Workmentioning

confidence: 99%

Personal models for eHealth - improving user-dependent human activity recognition models using noise injection

Siirtola

Koskimäki

Röning

2016

2016 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

Abstract-In this paper, a noise injection method to improve personal recognition models is presented. The idea of the method is to build more general recognition models for eHealth using a small original data set and by expanding the area covered by training data using noise injection. This way, it is possible to train models that are less vulnerable to changing conditions, and thus more accurate, but still the data gathering phase can be non-burdensome. The proposed method was tested using two classifiers (linear discriminant analysis and quadratic discriminant analysis) and three human activity recognition data sets collected using inertial sensors of a smartphone. Two of these data sets are open data sets. The results show that noise injection improves the true positive recognition rates. With first data set the improvement varies from 1.3 to 2.0 percentage units, with second from 1.4 to 4.5 percentage units, and with third the highest improvement was 2.5 percentage units. Moreover, the results show that the method improves precision and reduces false positive rates. In addition, experiments were made using different training set sizes to show that the improvement in true positive rate is bigger if the original training data set is small. In this study, the method is experimented using human activity data sets but it is not limited to this application area and can be used with any time series data.Index Terms-Activity recognition; eHealth; noise injection; smartphone; inertial sensors; accelerometer; personal models; I. PROBLEM STATEMENT AND RELATED WORKIn eHealth it is often important to recognize what a person is doing or a condition of a person. However, people are different, and therefore, a user-independent recognition model that provides accurate recognition results for one person does not necessary provide as high results for other person. There are many possible reasons for this phenomena. For instance, person's can be different: physical characteristics, health state or gender can have an effect to the recognition results. On the other hand, external factor such as weather, terrain and location can cause problems to recognition models. In addition, in the real-life many other unseen contingencies can happen and the training data set used to train the recognition models cannot include all of these. This means that model that seem to work really well when tested with testing data do not work as well when it is used online, in real-time, real-life applications [1].In the case of human activity recognition, often the recognition is done using user-independent models and good recognition rates have been achieved (for instance [2], [3], [4], [5]). However, it has been shown that user-independent models do not work accurately for instance if trained with healthy study subjects and tested with subjects who have difficulties to move [6]. Personal models could solve this problem. In fact, it has been shown that user-dependent models are more accurate than user-independent ones [7]. However, in [8] it was shown...

show abstract

Learning from Life-Logging Data by Hybrid HMM: A Case Study on Active States Prediction

Cited by 2 publications

References 15 publications

Imbalanced Data Classification Using Auxiliary Classifier Generative Adversarial Networks

Imbalanced Data Classification Using Auxiliary Classifier Generative Adversarial Networks

Personal models for eHealth - improving user-dependent human activity recognition models using noise injection

Contact Info

Product

Resources

About