Informatica

Proliferation of wearable healthcare devices has created the need to deliver artificial intelligence applications for these resource-constrained devices to achieve faster, localized decision-making, by bringing computation closer to the data sources, for improved responsiveness and privacy. This contribution presents the results of an experimental evaluation of artificial neural network compression techniques, including quantization, structured pruning, and knowledge distillation, applied to multi-label classification of electrocardiogram (ECG) signals. The experiments were carried out on the PTB-XL dataset using three deep learning models, i.e. an LSTM-based recurrent neural network, a 1D convolutional neural network, and a 1D residual neural network. The results show how the compression methods impact model quality and highlight opportunities to reduce model size and accelerate inference, thereby enabling effective deployment on resource-constrained, edge devices.

Vector Product Format (VPF) based databases store geographical data in a relational framework, where individual VPF files are arranged hierarchically in a directory tree structure. Access and update of the VPF data can become difficult due to fragmentation of data among multiple tables. This paper presents an object-oriented model for the management of a VPF database, which provides easy access and automatic update for the VPF data, and is compatible with ESRI ArcView. This model has been successfully implemented in Java, for Digital Nautical Charts (DNC).