Lab of Advanced Analytics for Intelligent Manufacturing and Systems
Photo Credit: Freepik
In-situ Process Monitoring
Layer-wise Spatial Modeling of Porosity in Additive Manufacturing
The objective of this work is to model and quantify the layer-wise spatial evolution of porosity in parts made using additive manufacturing (AM) processes. An augmented layer-wise spatial log Gaussian Cox process (ALS-LGCP) model is proposed. The ALS-LGCP approach quantifies the spatial distribution of pores within each layer of the AM part and tracks their sequential evolution across layers.
Machine learning–driven in situ process monitoring with vibration frequency spectra
Frequency spectra representation of the microelectromechanical systems (MEMS) vibration sensor signals during subtle process changes is investigated, and the signal patterns uncovered by frequency spectra are utilized to formulate a machine learning–driven in situ process monitoring approach to detect process anomalies in CMP.
Wafer quality monitoring using spatial Dirichlet process based mixed-eﬀect proﬁle modeling scheme
A mixed eﬀect proﬁle monitoring (MEPM) scheme is proposed. The MEPM scheme adaptively groups proﬁle data into clusters and models the inter-cluster variations, consequently, enabling a robust statistical process control scheme for detecting deviant proﬁle data. Capturing the clustering information of the proﬁle data leads to a deep understanding and an accurate modeling of the spatial data.
Deep Convolutional Neural Network-Based Epileptic Electroencephalogram (EEG) Signal Classification
A new deep learning-based classiﬁcation methodology, namely epileptic EEG signal classiﬁcation (EESC), is proposed in this paper. This methodology ﬁrst transforms epileptic EEG signals to power spectrum density energy diagrams (PSDEDs), then applies deep convolutional neural networks (DCNNs) and transfer learning to automatically extract features from the PSDED, and ﬁnally classiﬁes four categories of epileptic states (interictal, preictal duration to 30 min, preictal duration to 10 min, and seizure).
Get in Touch.
We are looking for self-motivated, fast-learning, collaborative, and hard-working students to join us. Research topics include data analytics, machine learning, and artificial intelligence in advance manufacturing, sensor application design, robotics control, etc. Students from statistics, computer science, mathematics, industrial and systems engineering, electrical engineering are encouraged to apply. We will offer full scholarship opportunities.
1. Data analytics skills: statistics, machine learning, and signal processing.
2. Sufficient coding skills: C, Matlab, Python, or R.
3. Sensing and data acquisition: select the suitable sensors to measure physical phenomena and collect the sensor data.
Preference will be given to applicants who have research experience. Applicants must satisfy the requirements from Auburn University and ISE department.
Please send your resume, transcript, GRE/TOEFL scores, and self introduction including why you are interested to firstname.lastname@example.org. The matched applicants will be given a one-and-a-half hour interview with me. Due to the large amount of application emails, I will not reply to the applicants whom I think may not match well. Please accept my appreciation for your interest and best wishes to your application.
Samuel Ginn College of Engineering 3301G Shelby Center,
Auburn, AL 36849 USA