Open Hub
Open Hub

 Settings |  Report Duplicate

0
I Use This!
Very Low Activity

Commits : Listings

Analyzed about 24 hours ago. based on code collected 2 days ago.
Oct 21, 2025 — Oct 21, 2026
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
Section 1449 updated
Srinivasan Kannan
More... 7 months ago
ChatGPT analysis of Chennai Metropolitan Area Economy and GDP
Srinivasan Kannan
More... 7 months ago
Section 1658 updated
Srinivasan Kannan
More... 7 months ago
1658. (THEORY and FEATURE) Cybercrime Forensics/Deepfakes/Fraud Analytics - Error Level Analysis(ELA) implementation for identifying fake or tampered images - related to 693,1582 and all sections on Fraud Analytics, Large Scale Visuals, Cybercrime analytics,Social network analysis, Anomaly detection, Deep Learning - Convolution Neural Networks - 26 March 2026
Srinivasan Kannan
More... 7 months ago
-------------------------------------------------------------------------------------------------- 1658. (THEORY and FEATURE) Cybercrime Forensics/Deepfakes/Fraud Analytics - Error Level Analysis(ELA) implementation for identifying fake or tampered images - related to 693,1582 and all sections on Fraud Analytics, Large Scale Visuals, Cybercrime analytics,Social network analysis, Anomaly detection, Deep Learning - Convolution Neural Networks - 26 March 2026 -------------------------------------------------------------------------------------------------- 1658.1 python-src/image_pattern_mining/ImageNet/ImageGraph_Keras_Theano.py has been updated to define new function deepfake_detection_ELA(imagefile,scale=10,quality=95) that implements Error Level Analysis (Paper referenced in 1582.8) for JPEG images. 1658.2 Earlier function (*) reads an image file (*) writes the image into another temporary file with less quality (*) reads the temporary image file of less quality (*) and finds the absolute difrence between original and temporary images. 1658.3 Extent of difference between two images computed by ndarray sum() is the measure of possible tampering/morphing/deepfake in original image. 1658.4 Two images (*) testlogs/ExampleImage_1.jpg (authentic classroom photograph that includes author along with undergraduate batchmates - [BE 95CSE PSG Tech-Coimbatore 1998-99]) and (*) testlogs/ThisPersonDoesNotExist.jpeg of a non-existent imaginary person which is sourced from DeepFake repository URL https://this-person-does-not-exist.com/ are checked by earlier ELA function with similar metrics (scaling of 100 and quality of 50): deepfake_detection_ELA("testlogs/ExampleImage_1.jpg",scale=100,quality=50) deepfake_detection_ELA("testlogs/ThisPersonDoesNotExist.jpeg",scale=100,quality=50) 1658.5 Following are the sum of entries in ELA diff computed for 2 images implying something artificial in second image having high error value (though superficially secon looks perfectly human): deepfake_detection_ELA(): sum diff = 41344160 (Authentic - testlogs/ExampleImage_1.jpg) deepfake_detection_ELA(): sum diff = 328787672 (DeepFake - testlogs/ThisPersonDoesNotExist.jpeg) 1658.6 Error Level Analysis results are often used to train Convolution Neural Networks that map receptive field subsquare in input image to a Convolution Layer (with a stride) followed by Maxpooling Layer. Error Level Analysis is widely used forensic for detecting tampered images having objectionable content.
Srinivasan Kannan
More... 7 months ago
1657. (THEORY and FEATURE) Social Network Analysis - AI people analytics by OpenAI prompt - related to 14,365,626,711,727,753,876,1127,1128,1129,1130,1204,1263,1269,1427,1442,1452,1532,1534,1547,1555,1571,1592,1605,1645 and all sections on People Analytics, Intrinsic Merit Versus Fame Equilibrium, BKS Conjecture, Stability and Noise Sensitivity of Interview LTF/PTF,Peres Theorem,Unique Identification,Talent Analytics,Code search of opensource repositories,HR Analytics and Automated Recruitment,Question-Answering,Majority Voting,Condorcet Jury Theorem Variants,Margulis-Ruzzo Thresholds,Novelty Detection,Recommender Systems,AI Question-Answering, Partial Ordered Ranking, Fame-Merit equilibrium, Intrinsic Merit as Query Complexity,Software Analytics-Mythical Manmonth-CathedralAndBazaar,Birthday Paradox,Matching in Matrimony-Professional-Personal Social Media Network Profiles,Tree matching - 24 March 2026
Srinivasan Kannan
More... 7 months ago
1657. (THEORY and FEATURE) Social Network Analysis - AI people analytics by OpenAI prompt - related to 14,365,626,711,727,753,876,1127,1128,1129,1130,1204,1263,1269,1427,1442,1452,1532,1534,1547,1555,1571,1592,1605,1645 and all sections on People Analytics, Intrinsic Merit Versus Fame Equilibrium, BKS Conjecture, Stability and Noise Sensitivity of Interview LTF/PTF,Peres Theorem,Unique Identification,Talent Analytics,Code search of opensource repositories,HR Analytics and Automated Recruitment,Question-Answering,Majority Voting,Condorcet Jury Theorem Variants,Margulis-Ruzzo Thresholds,Novelty Detection,Recommender Systems,AI Question-Answering, Partial Ordered Ranking, Fame-Merit equilibrium, Intrinsic Merit as Query Complexity,Software Analytics-Mythical Manmonth-CathedralAndBazaar,Birthday Paradox,Matching in Matrimony-Professional-Personal Social Media Network Profiles,Tree matching - 24 March 2026
Srinivasan Kannan
More... 7 months ago
Section 1621 updated
Srinivasan Kannan
More... 7 months ago
Updated BestPractices.txt
Srinivasan Kannan
More... 7 months ago
Section 1651 updated
Srinivasan Kannan
More... 7 months ago
Section 1651 updated
Srinivasan Kannan
More... 7 months ago
Section 1621 updated
Srinivasan Kannan
More... 8 months ago
Section 1621 updated
Srinivasan Kannan
More... 8 months ago
ChatGPT AI review of Computational Geometric Factoriation algorithm implemented in NeuronRain (Python-Spark and Rust-Rayon)
Srinivasan Kannan
More... 8 months ago
Claude AI code review of NeuronRain repositories - https://claude.ai/chat/82cdd88e-870a-45bf-95d8-bb6f886b32a9
Srinivasan Kannan
More... 8 months ago
Section 1426 updated
Srinivasan Kannan
More... 8 months ago
Section 1435 updated
Srinivasan Kannan
More... 8 months ago
Section 1651 updated
Srinivasan Kannan
More... 8 months ago
Section 1350 updated
Srinivasan Kannan
More... 8 months ago
Updated BestPractices.txt
Srinivasan Kannan
More... 8 months ago
ChatGPT AI Review of https://scholar.google.com/citations?user=eLZY7CIAAAAJ&hl=en&authuser=1
Srinivasan Kannan
More... 8 months ago
Section 1651 updated
Srinivasan Kannan
More... 8 months ago
+1651. (THEORY and FEATURE) Functional Data Analysis(Scikit-FDA) implementation - ClusterPlot graphics for cluster visualization - related to 148,172,313,445,446,463,1165,1171,1176,1266,1289,1316,1318,1327,1358,1359,1360,1361,1364,1367,1368,1388,1404,1455,1456,1463,1479,1480,1515,1526,1527,1528,1548,1558,1561,1562,1567,1581,1590,1631,1638,1650 and all sections on Correlation between gravitational effects of Mined Celestial N-Body Patterns and terrestrial extreme weather events (or Gravitational effects on climate change), Drone natural obstacle avoidance-Drone autonomous online shopping delivery-Drone Electronic Voting Machine, Artificial Intelligence models for Climate Change-Adaptive Fourier Neural Operator-FourCastNet, Astronomical algorithms, Multifractals, Timeseries analysis, Sequence Mining-Class Association Rules, Global warming,Clausius-Clapeyron equation,Navier-Stokes equation, Handwriting recognition, Gait Analysis, Fraud analytics - 18 February 2026
Srinivasan Kannan
More... 8 months ago
---------------------------------------------------------------------------------------------------------------------------------------- 1651. (THEORY and FEATURE) Functional Data Analysis(Scikit-FDA) implementation - ClusterPlot graphics for cluster visualization - related to 148,172,313,445,446,463,1165,1171,1176,1266,1289,1316,1318,1327,1358,1359,1360,1361,1364,1367,1368,1388,1404,1455,1456,1463,1479,1480,1515,1526,1527,1528,1548,1558,1561,1562,1567,1581,1590,1631,1638,1650 and all sections on Correlation between gravitational effects of Mined Celestial N-Body Patterns and terrestrial extreme weather events (or Gravitational effects on climate change), Drone natural obstacle avoidance-Drone autonomous online shopping delivery-Drone Electronic Voting Machine, Artificial Intelligence models for Climate Change-Adaptive Fourier Neural Operator-FourCastNet, Astronomical algorithms, Multifractals, Timeseries analysis, Sequence Mining-Class Association Rules, Global warming,Clausius-Clapeyron equation,Navier-Stokes equation, Handwriting recognition, Gait Analysis, Fraud analytics - 18 February 2026 ---------------------------------------------------------------------------------------------------------------------------------------- 1651.1 python-src/FunctionalDataAnalysis.py has been updated to import ClusterPlot and FDataGrid from scikit-fda 1651.2 Cluster data from Scikit-fda Functional KMeans clustering are visualized by ClusterPlot().plot() call: ClusterPlot(fda_kmeans, data).plot() 1651.3 Arbitrary function datasamples are clustered and plotted by instantiation of FDataGrid() object from function samples and gridpoints as per documentation in https://fda.readthedocs.io/en/latest/modules/autosummary/skfda.representation.grid.FDataGrid.html: randomfunction = [[1,2,3],[2,4,8],[5,6,7],[8,9,10]] gridpoints = [3,4,5] randomfunctiondata = FDataGrid(randomfunction,gridpoints) cluster_functions(data=randomfunctiondata) 1651.4 Following are the logs and FDA cluster plots for AEMET Weather,GAIT,HANDWRIT and Random function data: testlogs/FunctionalDataAnalysis.AEMET.18February2026.png testlogs/FunctionalDataAnalysis.GAIT.18February2026.png testlogs/FunctionalDataAnalysis.HANDWRIT.18February2026.png testlogs/FunctionalDataAnalysis.RandomFunction.18February2026.png testlogs/FunctionalDataAnalysis.log.18February2026 1651.5 Functional Data Analysis KMeans clustering is especially useful in Stockmarket timeseries analytics where clustering of ticker timeseries of multiple stocks over a date range is necessary - For example Google Finance timeseries plots comparison for 3 TBTF stock tickers (ICICI,SBI,HDFC) - https://www.google.com/finance/quote/ICICIBANK:NSE?hl=en&comparison=NSE%3ASBIN%2CNSE%3AHDFCBANK&window=6M - over 6 months window shows a clustering trend (ICICI,HDFC performed almost similarly while SBI outperformed both though all 3 belong to same banking sector) which might be best suited for FDA clustering.
Srinivasan Kannan
More... 8 months ago
Section 1650 updated
Srinivasan Kannan
More... 8 months ago
Updated Requirements.txt
Srinivasan Kannan
More... 8 months ago
Section 1649 updated
Srinivasan Kannan
More... 8 months ago
Section 1255 updated
Srinivasan Kannan
More... 8 months ago
Section 624 updated
Srinivasan Kannan
More... 9 months ago
Section 1648 updated
Srinivasan Kannan
More... 9 months ago