Scribd
Upload
43 views2 pages

NO Paper / Year Method/tool Concept Application

This document discusses 7 papers related to applying machine learning and deep learning techniques to big data problems. Paper 1 from 2017 discusses using a Lambda architecture with Hadoop and a big data lake to perform parallel batch and real-time analytics for smart grid and big data eco-systems. Paper 2 from 2017 discusses using machine learning and deep learning for intrusion detection in wired and wireless networks. Paper 3 from 2017 discusses using semi-supervised convolutional neural networks for human activity recognition to train accurate models with limited labeled data and large amounts of unlabeled data.

Uploaded by

mindworkz pro
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
43 views2 pages

NO Paper / Year Method/tool Concept Application

This document discusses 7 papers related to applying machine learning and deep learning techniques to big data problems. Paper 1 from 2017 discusses using a Lambda architecture with Hadoop and a big data lake to perform parallel batch and real-time analytics for smart grid and big data eco-systems. Paper 2 from 2017 discusses using machine learning and deep learning for intrusion detection in wired and wireless networks. Paper 3 from 2017 discusses using semi-supervised convolutional neural networks for human activity recognition to train accurate models with limited labeled data and large amounts of unlabeled data.

Uploaded by

mindworkz pro
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

NO Paper / Method/tool Concept Drawback Application

year
1. Data lake Lamda Architecture Perform Tool complexity smart grid big
lambda parallel Tableau data eco
architecture Hadoop Bigdata lake is batch and Matlab system
for smart grids used to store data, real time Radoop
big data
image, video operations
analytics
on data

2017
2. Machine 1.Machine learning, Applicable to Difficult and Cybersecurity
Learning and perform time-consuming
Deep 2.Deep learning intrusion
Learning detection in
Methods for wired and
Cybersecurity wireless
networks.
2017
3. Semi- 1.Convolutional encoder- train Difficulty in (i) machine
Supervised decoder (CNN-Encoder- accurate and recognizing learning in HAR
and
Convolutional Decoder) generalizable (ii) semi-
Neural DNNs with supervised
Networks for 2.Convolutional ladder limited learning in HAR
Human network (CNN-Ladder) labeled data
Activity and large
Recognition scale
unlabeled
2017 data for HAR
4. Towards Bayesian network detect faults distribute and Map reduce
MapReduce in big data produce
based applications enormous
Bayesian amounts of logs,
Deep i.e., big data
Learning applications
Network for
Monitoring
Big Data
Applications

2017
5. A survey on Hierarchical Perform Processing Pre_training,
deep learning Architecture classification issues on data Fine_tuning
for big data mining and
Most typical deep and pattern information
2017 learning models are recognition processing
used:SAE,DBN,CNN,RNN
6. A FDC_CNN Improve Fault
convolutional (Fault detection and training diagnosis,cannot
neural classification speed and extract
network for convolution neural classification correlations
fault
network) performance among all
classification
sensor variables
and diagnosis
in
semiconductor
manufacturing
processes

2016
7. A deep Long short term Network to Forecasting
learning model memory(LSTM) predicts the problem in big
for air quality future values data
prediction in of air quality
smart cities in a smart city
2017

You might also like