arXiv subjects

Martin Weiss

Publications and source records attributed to Martin Weiss.

21 records · Page 2Linked to original sources

arXiv2018

A Survey of Mobile Computing for the Visually Impaired

The number of visually impaired or blind (VIB) people in the world is estimated at several hundred million. Based on a series of interviews with the VIB and developers of assistive technology, this paper provides a survey of machine-learning based mobile applications and identifies the most relevant applications. We discuss the functionality of these apps, how they align with the needs and requirements of the VIB users, and how they can be improved with techniques such as federated learning and model compression. As a result of this study we identify promising future directions of research in mobile perception, micro-navigation, and content-summarization.

cs.HC↗

arXiv2018

Towards Gene Expression Convolutions using Gene Interaction Graphs

We study the challenges of applying deep learning to gene expression data. We find experimentally that there exists non-linear signal in the data, however is it not discovered automatically given the noise and low numbers of samples used in most research. We discuss how gene interaction graphs (same pathway, protein-protein, co-expression, or research paper text association) can be used to impose a bias on a deep model similar to the spatial bias imposed by convolutions on an image. We explore the usage of Graph Convolutional Neural Networks coupled with dropout and gene embeddings to utilize the graph information. We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used. We conclude that more work should be done in this direction. We design experiments that show why existing methods fail to capture signal that is present in the data when features are added which clearly isolates the problem that needs to be addressed.

q-bio.GN↗

arXiv2012

Cognitive Radio Networks: Realistic or Not?

A large volume of research has been conducted in the cognitive radio (CR) area the last decade. However, the deployment of a commercial CR network is yet to emerge. A large portion of the existing literature does not build on real world scenarios, hence, neglecting various important interactions of the research with commercial telecommunication networks. For instance, a lot of attention has been paid to spectrum sensing as the front line functionality that needs to be completed in an efficient and accurate manner to enable an opportunistic CR network architecture. This is necessary to detect the existence of spectrum holes without which no other procedure can be fulfilled. However, simply sensing (cooperatively or not) the energy received from a primary transmitter cannot enable correct dynamic spectrum access. For example, the low strength of a primary transmitter's signal does not assure that there will be no interference to a nearby primary receiver. In addition, the presence of a primary transmitter's signal does not mean that CR network users cannot access the spectrum since there might not be any primary receiver in the vicinity. Despite the existing elegant and clever solutions to the DSA problem no robust, implementable scheme has emerged. In this paper, we challenge the basic premises of the proposed schemes. We further argue that addressing the technical challenges we face in deploying robust CR networks can only be achieved if we radically change the way we design their basic functionalities. In support of our argument, we present a set of real-world scenarios, inspired by realistic settings in commercial telecommunications networks, focusing on spectrum sensing as a basic and critical functionality in the deployment of CRs. We use these scenarios to show why existing DSA paradigms are not amenable to realistic deployment in complex wireless environments.

cs.NI↗