{"id":1621,"date":"2020-12-19T07:50:38","date_gmt":"2020-12-19T06:50:38","guid":{"rendered":"http:\/\/blogs.gm.fh-koeln.de\/ciop\/?page_id=1621"},"modified":"2025-01-20T08:52:33","modified_gmt":"2025-01-20T07:52:33","slug":"anomaly-detection","status":"publish","type":"page","link":"https:\/\/blogs.gm.fh-koeln.de\/ciop\/research\/anomaly-detection\/","title":{"rendered":"Anomaly Detection"},"content":{"rendered":"

\"\"<\/a><\/p>\n

For the operation of large machines in companies or other critical systems in society, it is usually necessary to record and monitor specic machine or system health indicators over time. In the past, the recorded time series were often evaluated manually or by simple heuristics (such as threshold values) to detect abnormal behavior. With the more recent advances in the fields of ML (machine learning)<\/strong> and AI (articial intelligence)<\/strong>, ML-based anomaly detection algorithms are becoming increasingly popular for many tasks such as health monitoring or predictive maintenance.<\/p>\n

In our research group we develop new unsupervised<\/strong> anomaly detection approaches. Methods and algorithms that we use are (among others) TCN<\/strong> (Temporal Coherence Networks), LSTM<\/strong> (Long Short-Term Memory) and wavelets<\/strong>.<\/p>\n

Application areas<\/strong>: predictive maintenance, health services, ECG.<\/p>\n

 <\/p>\n

Project members<\/strong><\/p>\n\n\n\n
\n\n\n\n\n\n
\"\"<\/a><\/td>\n<\/tr>\n
<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/td>\nMarkus Thill<\/a>,
\nTH K\u00f6ln<\/td>\n		\"konen-3\"<\/a><\/td>\nProf. Dr. Wolfgang Konen<\/a>,
\nTH K\u00f6ln<\/td>\n<\/tr>\n
<\/td>\n<\/td>\n\n

<\/h2>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n

Honors<\/strong><\/h2>\n