Technical Committee News

The PhysioNet/Computing in Cardiology Challenge 2015 is now open! This year's challenge is 'Reducing False Arrhythmia Alarms in the ICU'. False alarms in the ICU can lead to a disruption of care, impacting both the patient and the clinical staff through noise disturbances, desensitization to warnings and slowing of response times, leading to decreased quality of care. False alarm rates can be as high as 90% or more. To address this issue we have developed an expert-labelled data set of 1250 life-threatening arrhythmia alarms with five minutes of electrophysiological and pulsatile waveform data leading up to each alarm event. Competitors are challenged to devise a method of processing all the available data to reduce false alarms with minimal or no effect on true (vital) alarms.

Deep learning is becoming an important AI paradigm for pattern recognition, image/video processing and fraud detection applications in finance. The computational complexity of a deep learning network dictates need for a distributed realization. The big data lab at Impetus, led by Dr. Vijay Srinivas Agneeswaran, has built the first prototype of the distributed deep learning network over Apache Spark. They have parallelized the training phase of the network and consequently reduced training time.

Three years after its launch, the AASP TC Challenges series has achieved its goal of stimulating ground-breaking approaches to hot topics in Audio and Acoustic Signal Processing. The challenges run so far have been great successes, leading to unprecedented participation, new publicly available datasets, and highly attended special sessions and workshops

Software defined radio (SDR) is an architecture for designing more flexibility and generalized hardware for communication systems, radar, sonar or remote sensing systems making more intelligent and multi-function radio systems possible. In the January 2015 issue of the Proceedings of the IEEE , two articles present surveys in the fields of software defined networking (SDN) and the spectrum management for radar systems which is one of the key techniques for radar and wireless communication.