u540's starred repositories
dynamic-graph-papers
Archive of Temporal Knowledge Reasoning in Social Network and Knowledge Graph
GCN_AnomalyDetection
Code for Deep Anomaly Detection on Attributed Networks (SDM2019)
TADDY_pytorch
A Pytorch implement of paper "Anomaly detection in dynamic graphs via transformer" (TADDY).
Graph-Anomaly-Loss
TNNLS: A Synergistic Approach for Graph Anomaly Detection with Pattern Mining and Feature Learning; CIKM'20: Error-bounded Graph Anomaly Loss for GNNs.
sbustreamspot-core
Core streaming heterogeneous graph clustering and anomaly detection code (KDD 2016)
KDD19-AnomRank
Anomaly Detection in Dynamic Graphs
Multi-Scale-One-Class-Recurrent-Neural-Networks
Code for KDD 2021 paper "Multi-Scale One-Class Recurrent Neural Networks \\for Discrete Event Sequence Anomaly Detection"
DeepLog
Anomaly detection is a critical step towards building a secure and trustworthy system. The primary purpose of a system log is to record system states and significant events at various critical points to help debug system failures and perform root cause analysis. Such log data is universally available in nearly all computer systems. Log data is an important and valuable resource for understanding system status and performance issues; therefore, the various system logs are naturally excellent source of information for online monitoring and anomaly detection. We propose DeepLog, a deep neural network model utilizing Long Short-Term Memory (LSTM), to model a system log as a natural language sequence. This allows DeepLog to automatically learn log patterns from normal execution, and detect anomalies when log patterns deviate from the model trained from log data under normal execution.
ABNORMAL-HUMAN-ACTIVITY-DETECTION-SYSTEM
# Abnormal-Human-Activity-Detection With the increase in the amount of anti-social activities taking place in the environment, security has been given the utmost importance lately. Therefore, organizations require a constant monitoring of people and their interactions. Since this constant monitoring of data by humans to judge if the events are abnormal is a near impossible task as it requires a lot of workforce and constant attention. Therefore, the challenge that comes up is the demand for an automatic and intelligent analysis for such video sequences. Our project comes forward as an attempt to provide solution to such a problem as the model developed is a smart surveillance system which can detect unusual or abnormal activity automatically. A method for representing the motion characteristics is described for detection and localization of unusual activities in the crowd scenes on a generalized framework which includes both a local and global range for detection of such activities.
BERT_SequenceTagging
A project finetuing BERT-lieked models for sequence tagging tasks (like Named Entity Recognition, Event Detection). Implemented by huggingface/transformers
build-event-sequence-dataset
Scripts for building datasets in varying formats for sequence detection task
Abnormal-Human-Activity-Detection-System
With the increase in the amount of anti-social activities taking place in the environment, security has been given the utmost importance lately. Therefore, organizations require a constant monitoring of people and their interactions. Since this constant monitoring of data by humans to judge if the events are abnormal is a near impossible task as it requires a lot of workforce and constant attention. Therefore, the challenge that comes up is the demand for an automatic and intelligent analysis for such video sequences. Our project comes forward as an attempt to provide solution to such a problem as the model developed is a smart surveillance system which can detect unusual or abnormal activity automatically. A method for representing the motion characteristics is described for detection and localization of unusual activities in the crowd scenes on a generalized framework which includes both a local and global range for detection of such activities.
Abnormal-Human-Activity-Detection
With the increase in the amount of anti-social activities taking place in the environment, security has been given the utmost importance lately. Therefore, organizations require a constant monitoring of people and their interactions. Since this constant monitoring of data by humans to judge if the events are abnormal is a near impossible task as it requires a lot of workforce and constant attention. Therefore, the challenge that comes up is the demand for an automatic and intelligent analysis for such video sequences. Our project comes forward as an attempt to provide solution to such a problem as the model developed is a smart surveillance system which can detect unusual or abnormal activity automatically. A method for representing the motion characteristics is described for detection and localization of unusual activities in the crowd scenes on a generalized framework which includes both a local and global range for detection of such activities.
python-sequences
Python Sequences: A tool for detecting patterns and overlaps in data streams, from character strings to event sequences, without caching. Ideal for game input detection and sequence testing.