Figure 1: This network was used in the classification process. Dashed backward lines represent target variables, which are compared against predicted ones to perform gradient descent. The discriminator is trained to distinguish between real data-label pairs originating from the training data and fake data, which includes synthetic data created by the generator and unlabelled data with predicted labels. The discriminator serves as adversarial for the other networks, guiding the generator to create more realistic samples and the classifier to predict more accurate labels. A detailed description can be found in Sec. 3.
Wearable devices such as smartphones and smartwatches are widely used and record a significant amount of data. Labelling this data for human activity recognition is a time-consuming task, therefore methods which reduce the amount of labelled data required to train accurate classifiers are important. Generative Adversarial Networks (GANs) can be used to model the implicit distribution of a dataset. Traditional GANs, which only consist of a generator and a discriminator, result in networks able to generate synthetic data and distinguish real from fake samples. This adversarial game can be extended to include a classifier, which allows the training of the classification network to be enhanced with synthetic and unlabelled data. The network architecture presented in this paper is inspired by SenseGAN[1], but instead of generating and classifying sensor-recorded time series data, our approach operates with extracted features, which drastically reduces the amount of stored and processed data and enables deployment on less powerful and potentially wearable devices. We show that this technique can be used to improve the classification performance of a classifier trained to recognise locomotion modes based on recorded acceleration data ant that it reduces the amount of labelled training data necessary to achieve a similar performance compared to a baseline classifier. Specifically, our approach reached the same accuracy as the baseline classifier up to 50% faster and was able to achieve a 10% higher accuracy in the same number of epochs.
This paper describes the use of a genetic algorithm to design a website, according to principles of clarity, symmetry, golden ratio and image size. The website's logo is used to calculate a matching colour scheme. Results indicate that local maxima can be a problem but that with the right weighting of the fitness function, a pleasing design can be achieved.Such a program could be used when designing large numbers of websites; when a website has to be re-designed regularly to match changing content; or to provide a starting point for human website designers or users of interactive genetic algorithms to improve.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.