International Business Machines Corporation

Gciniwe Dlamini

Darlington Shingirirai Mapiye

James Junior Mashiyane

Stephanie Julia Muller

Mpho Mokoatle

Dineo Andronicah Makoro

In an approach to automatically downsampling DNA sequence data using variational autoencoders and preserving genomic integrity of an original file embodiments execute, by an encoder, bootstrapping on genomic sequence data to produce resamples. Furthermore, embodiments assess, by the encoder, unrepresentativeness and self-inconsistency of the resamples and selecting a representative resample according to the assessment, and build, by a modified encoder, vector representations from genotype likelihoods based on the selected representative sample. Additionally, embodiments integrate, by an analytics engine, mapping positional information and the genotype likelihoods to identify an optimum vector representation of a resample, and decode, by a modified decoder, the identified optimum vector representation of the resample to obtain a down-sampled read file that resembles and maintains the genomic integrity of the original file.

Downsampling genomic sequence data

A method for non-invasive detection of ingested medication which provide for one or more processors to receive images of medications designated for a user prior to ingestion of the medications by the user. The one or more processors capture an ultrasound image during ingestion by the user by an ultrasound device removably adhered to a throat area of the user. The one or more processors determine whether contents of the ingestion by the user includes one or more of the medications designated for the user, and responsive to determining the contents of the ingestion by the user includes one or more of the medications designated for the user, the one or more processors generate a confirmation that includes identification of the detected medications ingested by the user.

Non-invasive detection of ingested medications

A computer-implemented method for monitoring disease vectors is disclosed. A vector sensor obtains vector data relating to disease vectors in a monitored area. An environmental data obtaining component obtains environmental data relating to the monitored area. Based on at least one of the vector data and the environmental data, a population characteristic component may estimate or determine a vector population characteristic associated with the monitored area. A structural data obtaining component may obtain structural data relating to the monitored area. A vector travel estimation component may estimate or determine a vector travel characteristic. The vector characteristic may be indicative of predicted disease vector movement from outdoors to indoors in the monitored area and may allow for or facilitate a vector control action based at least partially on the vector travel characteristic. A device and a system for monitoring disease vectors are also disclosed.

Growing community of inventors

Johannesburg, South Africa

Gciniwe Dlamini