Hafidz Daud's repositories
cdsw-demo-env
Install scripts of Cloudera Data Science Workbench (CDSW) with CDH secure cluster on cloud
SafeHaven
SafeHaven - Submission for AWS DeepLens Challenge (the “Hackathon”) #AWSDeepLensChallenge
OneEyeFaceDetection
OneEye is a face recognition software running on AWS DeepLens that can detect and identifies faces
spark-netflow
NetFlow data source for Spark SQL and DataFrames
MyMQTT_Dioty_Connection_JSON_ESP8266_WiFiESP_library
MQTT connection using ESP8266 Cytron WiFi Shield to Dioty MQTT broker
ComposeNet
Implementation of modular composition network from https://arxiv.org/pdf/1711.11289.pdf
Scala-for-Machine-Learning-Second-Edition
Scala for Machine Learning - Second Edition, published by Packt
Frank-Kanes-Taming-Big-Data-with-Apache-Spark-and-Python
Frank Kane's Taming Big Data with Apache Spark and Python, published by Packt
deep_q_learning
This is the Code for "Deep Q Learning - The Math of Intelligence #9" By Siraj Raval on Youtube
Stream-Analytics-with-Microsoft-Azure
Stream Analytics with Microsoft Azure, published by Packt
Hive-XML-SerDe
XML Serializer/Deserializer for Apache Hive
deep-learning-models
Implementations of popular deep learning models in Theano+Lasagne
hadoop-overview
Hands on Hadoop, services, installation
ProductionScheduling
Solving an item production scheduling problem with the help of mathematical optimization.
Applied-Predictive-Modeling-with-Python
A collection of notebook to learn the Applied Predictive Modeling using Python.
progfun1
My solutions to the Functional Programming Principles in Scala course: https://www.coursera.org/learn/progfun1/home/welcome
Anomaly-Detection-by-Netflow-and-DNS-Analysis-of-Alexa-1M-websites
The Domain Name System is a fundamental component of the internet since it maps the easy-to-remember domain names to IP addresses. Therefore, it is usually the primary target for most of the malicious attacks such as DNS Poisoning and Rogue DNS servers. With the help of 0x20 bit encoding, the problem of DNS Poisoning is mitigated to quite a large extent. Although, it has a minor requirement that the authoritative nameserver should be able to preserve the case of the DNS query. It is usually difficult to detect the rogue DNS server above the stub resolver. We propose an anomaly detection system which would be able to raise a red flag in case of DNS Poisoning and malicious DNS authority by passive DNS analysis of domain names and then comparing them with the 0th day cluster of the database. We perform the passive DNS analysis for 27 days by querying the whois server of CYMRU, compare the network profiles of the domain names crawled with the 0th day cluster and categorize the domain names as static, benign anomaly and malicious anomaly depending upon the cluster a domain name shifted. In the process, we also create a WHOIS repository for Alexa domain names which is faster to query than the WHOIS server.
opensoc-streaming
Extensible set of Storm topologies and topology attributes for streaming, enriching, indexing, and storing telemetry in Hadoop.