Parallel Computing

• 64 Recognizing neurological disease on MRI image using CNN trained in cloud

Spec: Build, train & validate deep network to classify images. It is done in cloud.

Language: Python (Keras-Tensorflow), Matlab (Deep Learning & Neural Networks Toolbox, Computer Vision Toolbox).

• 12 Computing velocities of sonar targets using parfor-loop & SPMD

Spec: Benchmark CPU vs multi-CPU using various parallel techniques.

Language: Matlab (Signal Processing Toolbox, Parallel Computing Toolbox).

• 13 Detecting maternal heart rate & uterine activity using parallel function evaluation

Spec: Build multi-threaded version of application from single-threaded one.

Language: Matlab (Signal Processing Toolbox, Parallel Computing Toolbox).

Big Data

• 113 Finding maximum element in big file using datastores, tall arrays, mapreduce

Spec: Find maximum departure delay in big file of airline flights using various big data techniques.

Language: Matlab (Big Data functions).

• 14 Evaluating dependency between pollution and health of tree using tall array

Spec: Extract data from big file using tall array.

Language: Matlab (Signal Processing Toolbox, Big Data functions).

• 15 Computing mean length of sonar target using mapreduce

Spec: Extract data from big file using mapreduce.

Language: Matlab (Signal Processing Toolbox, Big Data functions).

System Identification

• 23 Compressing fetal signal using time-series ARMAX (autoregressive-moving-average) model

Spec: Fit ARMAX model to compress data.

Language: Matlab (System Identification Toolbox).

• 21 Adaptive cancellation of uterine-activity artifact in fetal heart signal

Spec: First sensor provides mixture of wanted signal and unwanted noise1. Second sensor provides noise2 correlated with noise1. Extract wanted signal.

Language: Matlab (Signal Processing Toolbox, Embedded/DSP System Toolbox, System Identification Toolbox).

• 24 Detecting system fault using data measured on system inputs & outputs

Spec: Build & train a model of system. Run the model in parallel with the system to predict its failure.

Language: Matlab (System Identification Toolbox).

Statistics

• 25 Fitting distribution to sample data using non-parametric technique

Spec: Fit probability distribution to sample data.

Language: Matlab (Statistics Toolbox).

• 26 Benchmarking two fetal monitors using ANOVA (analysis of variance)

Spec: Benchmark new device vs existing prototype using ANOVA.

Language: Matlab (Statistics Toolbox).

• 27 Estimating accuracy of neonatal ventilator designed using Six Sigma

Spec: Estimate main parameter of device manufactured to meet Six Sigma requirements.

Language: Matlab (Statistics Toolbox).

• 28 Investigating time of clinical process using survival analysis

Spec: Compute survival & hazard functions of clinical process.

Language: Matlab (Statistics Toolbox).

IoT (Internet of Things)

• 29 Complete IoT system - fetal monitor based on smart multicore sensor

Spec: Integrate projects with numbers 03, 06, 08, 09, 13, 16, 17, 21, 23, 25, 26, and 28 to design a compact low-cost device.

Language: Matlab (Deep Learning & Neural Networks Toolbox, Machine Learning Toolbox, Signal Processing Toolbox, Embedded/DSP System Toolbox, Parallel Computing Toolbox, Statistics Toolbox).

• 23 Compressing fetal signal using time-series ARMAX model

Spec: Fit ARMAX model to compress data.

Language: Matlab (System Identification Toolbox).

• 24 Detecting system fault using data measured on system inputs & outputs

Spec: Build & train a model of system. Run the model in parallel with the system to predict its failure.

Language: Matlab (System Identification Toolbox).

• 39 Compressing image using 2-D DCT

Spec: Investigate 2-D DCT for image compression.

Language: C++ (OpenCV), Matlab (Image Processing Toolbox).

• 97 Reducing JPEG compression artifacts in image using CNN

Spec: Improve quality of JPEG decompression using deep learning.

Language: Matlab (Deep Learning & Neural Networks Toolbox, Image Processing Toolbox).

Copyright © 2017-2019 Serguei Kabakov. All Rights Reserved.