Open Hub
Open Hub

 Settings |  Report Duplicate

0
I Use This!
Very Low Activity

Commits : Listings

Analyzed about 4 hours ago. based on code collected 1 day ago.
Nov 05, 2025 — Nov 05, 2026
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
Updated mined class association rule parsing in python-src/MaitreyaEncHoro_RuleSearch.py
Srinivasan Kannan
More... about 9 years ago
Updated NeuronRain_Research_Celestial_Pattern_Mining.txt
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
------------------------------------------------------------------------------------------------------------------------------------------- Celestial Data Pattern Mining - Updates to autogen_classifier_dataset pre-processing and classification of datasets ------------------------------------------------------------------------------------------------------------------------------------------- (*) An 8 year old lurking bug in cpp-src/NaiveBayesClassifier.cpp has been resolved.It was causing a null class to be returned after bayesian argmax() computation. (*) Lot of new articles on earthquakes and hurricanes have been added as training dataset for NaiveBayesian Classifier.These articles also have lot of research information on predicting hurricanes and earthquakes (*) python-src/autogen_classifier_dataset/AsferClassifierPreproc.py has been updated to include new articles in training data for NaiveBayesian (*) words.txt,word-frequency.txt,training-set.txt,topics.txt,test-set.txt have been re-created by executing python-src/autogen_classifier_dataset/AsferClassifierPreproc.py (*) Datasets are classified into python-src/autogen_classifier_dataset/EventClassDataSet_Earthquakes.txt and python-src/autogen_classifier_dataset/EventClassDataSet_Storms.txt by executing asfer_dataset_segregator.sh
Srinivasan Kannan
More... about 9 years ago
Updated NeuronRain_Research_Celestial_Pattern_Mining.txt
Srinivasan Kannan
More... about 9 years ago
------------------------------------------------------------------------------------------------------------------------------------------ Celestial Pattern Mining Update - specific to NeuronRain Research in SourceForge repositories - recreated Sequence Mined Rules ------------------------------------------------------------------------------------------------------------------------------------------ (*) Added a documentation text file asfer-docs/NeuronRain_Research_Celestial_Pattern_Mining.txt describing how astronomical pattern mining is done and code involved therein.
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
------------------------------------------------------------------------------------------------------------------------------------------ Celestial Pattern Mining Update - specific to NeuronRain Research in SourceForge repositories - recreated Sequence Mined Rules ------------------------------------------------------------------------------------------------------------------------------------------ (*) Added a documentation text file asfer-docs/NeuronRain_Research_Celestial_Pattern_Mining.txt describing how astronomical pattern mining is done and code involved therein.
Srinivasan Kannan
More... about 9 years ago
Updated Requirements.txt
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated Requirements.txt
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated Requirements.txt
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... about 9 years ago
-------------------------------------------------------------------------------------------------------------------------------------- Scheduler Analytics Update - Commits - 10 August 2017 -------------------------------------------------------------------------------------------------------------------------------------- (*) There is a problem in defining expected priorities in BackPropagation Neural Network output layer. This is necessary for weight update to happen iteratively and to quantify error between expected and actual neural network output (*) Output layer of BackPropagation is an indicator of process priority learnt by the perceptron. (*) Previously expected priorities were hardcoded. This has been changed as below: (*) Set of processes currently running are clustered and stored in an input JSON file (*) This JSON dictionary has key-value pairs mapping a process class to its apriori expected priority (*) Scheduler Analytics loads this JSON and looks up the expected priority for each process executable by its process class (*) Presently process class is just a substring of the executable name (*) BackPropagation does string match of this process class to executable name and finds the expected priority from JSON dict (*) BackPropagation iteration updates the weights of all 3 layers (*) Defining apriori class of a process is subjective and instead of substring of executable, an independent clustering algorithm having a suitable distance function can be used to write the JSON classification of processes. For example, unix process groups are numerical classes of processes. (*) Previous generation of JSON classes for processes and backpropagation weight update iteration is the first phase of analytics. (*) In the second phase, weight-updated BackPropagation Neural Network takes as input runtime process statistics (CPU, Memory and Context Switches) to predict the actual priority of a process belonging to the apriori class. (*) This is a depth 2 tree evaluation: Static - apriori expected class of a process and BackPropagation iteration Dynamic - fine grained priority of a process within the previous static class by evaluating the multilayer neural network
Srinivasan Kannan
More... about 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... over 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... over 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... over 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
as K.Srinivasan
More... over 9 years ago
Updated AsFer Design Document
Srinivasan Kannan
More... over 9 years ago