M
Muhammad Ali Chattha
Researcher at German Research Centre for Artificial Intelligence
Publications - 9
Citations - 111
Muhammad Ali Chattha is an academic researcher from German Research Centre for Artificial Intelligence. The author has contributed to research in topics: Artificial neural network & Subject-matter expert. The author has an hindex of 3, co-authored 7 publications receiving 62 citations. Previous affiliations of Muhammad Ali Chattha include Kaiserslautern University of Technology.
Papers
More filters
Journal ArticleDOI
FuseAD: Unsupervised Anomaly Detection in Streaming Sensors Data by Fusing Statistical and Deep Learning Models.
TL;DR: A novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion, and the obtained results advocate that this fusion-based technique can obtain the best of both worlds by combining their strengths and complementing their weaknesses.
Proceedings ArticleDOI
A Comparative Analysis of Traditional and Deep Learning-Based Anomaly Detection Methods for Streaming Data
TL;DR: This study compares 13 anomaly detection methods on two commonly used streaming data sets and reveals that the deep learning-based anomalies detection methods are superior to traditionalomaly detection methods.
Proceedings ArticleDOI
PiLoT: A Precise IMU Based Localization Technique for Smart Phone Users
TL;DR: PILoT, a Precise IMU based Localization Technique is proposed and implemented to overcome shortcomings of pedestrian dead reckoning schemes without compromising the accuracy of the system.
Proceedings Article
KINN: Incorporating Expert Knowledge in Neural Networks
Muhammad Ali Chattha,Shoaib Ahmed Siddiqui,Muhammad Imran Malik,Ludger van Elst,Andreas Dengel,Sheraz Ahmed +5 more
TL;DR: In this paper, a framework for incorporating expert knowledge into the network (KINN) is introduced, which can automatically determine the quality of the predictions made by the expert and rectify it accordingly by learning the trends/patterns from data.
Book ChapterDOI
DeepEX: Bridging the Gap Between Knowledge and Data Driven Techniques for Time Series Forecasting
Muhammad Ali Chattha,Shoaib Ahmed Siddiqui,Mohsin Munir,Muhammad Imran Malik,Ludger van Elst,Andreas Dengel,Sheraz Ahmed +6 more
TL;DR: This paper presents a fusion scheme, DeepEX, that combines these seemingly parallel streams of AI, for multi-step time-series forecasting problems and achieves this in a way that merges best of both worlds along with a reduction in the amount of data required to train these models.