Evaluating different machine learning techniques as surrogate for low voltage grids

Active Low Voltage Grids

Two Different Machine Learning Techniques for Drug-Drug Interaction Extraction

Detection of drug-drug interaction (DDI) is an important task for both patient safety and efficient health care management. In this paper, we explore the combination of two different machine-learning approaches to extract DDI: (i) a feature-based method using a SVM classifier with a set of features extracted from texts, and (ii) a kernelbased method combining 3 different kernels. Experiments co...

LOW VOLTAGE PAs Techniques for Low Voltage Power Amplifier Matching

There is rapid expansion in the use of short range digital wireless systems [1], using the license-free allocations around 915 MHz in the USA and 869 MHz in Europe that permit up to 1 watt output power. These RF systems now use digital signal processing (DSP) for modulation and demodulation so to get better circuit packing density, and take advantage of finer IC process geometries that generall...

Relevance as a Metric for Evaluating Machine Learning Algorithms

In machine learning, the choice of a learning algorithm that is suitable for the application domain is critical. The performance metric used to compare different algorithms must also reflect the concerns of users in the application domain under consideration. In this work, we propose a novel probability-based performance metric called Relevance Score for evaluating supervised learning algorithm...

Telecommunication requirements in low-voltage smart grids