Mehrdad Nourani

Mehrdad Nourani

Auto-generated profile, based on publicly available information

Mehrdad Nourani

Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2017 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
JBJavad Birjandtalab
Javad Birjandtalab
MPMaziyar Baran Pouyan
Maziyar Baran Pouyan
DCDiana Cogan
Diana Cogan
MNMehrdad Nourani
Mehrdad Nourani
JHJay Harvey
Jay Harvey

1 October 2016 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
MHMehrdad Heydarzadeh
Mehrdad Heydarzadeh
MNMehrdad Nourani
Mehrdad Nourani

6 July 2020 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
HMHafez Eslami Manoochehri
Hafez Eslami Manoochehri
MNMehrdad Nourani
Mehrdad Nourani
Background: Identifying drug-target interaction is a key element in drug discovery. In silico prediction of drug-target interaction can speed up the process of identifying unknown interactions between drugs and target proteins. In recent studies, handcrafted features, similarity metrics and machine learning methods have been proposed for predicting drug-target interactions. However, these methods cannot fully learn the underlying relations between drugs and targets. In this paper, we propose anew framework for drug-target interaction prediction that learns latent features from drug-target interaction network.Results: We present a framework to utilize the network topology and identify interacting and non-interacting drug-target pairs. We model the problem as a semi-bipartite graph in which we are able to use drug-drug and protein-protein similarity in a drug-protein network. We have then used a graph labeling method for vertex ordering in our graph embedding process. Finally, we employed deep neural network to learn the complex pattern of interacting pairs from embedded graphs. We show our approach is able to learn sophisticated drug-target topological features and outperforms other state-of-the-art approaches.Conclusions: The proposed learning model on semi-bipartite graph model, can integrate drug-drug and protein-protein similarities which are semantically different than drug-protein information in a drug-target interaction network. We show our model can determine interaction likelihood for each drug-target pair and outperform other heuristics.

9 August 2018 in IEEE Transactions on Energy Conversion
Verified
Journal Article
Closed access
MHMehrdad Heydarzadeh
Mehrdad Heydarzadeh
MZMohsen Zafarani
Mohsen Zafarani
MNMehrdad Nourani
Mehrdad Nourani
BABilal Akin
Bilal Akin
This paper presents a generic analytical tool to diagnose and classify faults in permanent magnet synchronous motors (PMSM). The proposed method deploys wavelet transform to extract features for fault diagnosis which provides a framework for studying non-stationary trends. Analyzing the stator current with wavelet raises a challenge since the energy of fundamental component spreads over different scales in the decomposition. An adaptive filter is used to estimate and remove the fundamental component in stator current. This filter predicts the main harmonic by processing the measured current data in real-time without any speed feedback. The proposed filter designed in a way that it does not affect or suppress fault related harmonics. The estimation accuracy and convergence rate of this filter is tested and reported by error bounds which exhibit an acceptable robustness. The validity of the proposed fault diagnosis approach is verified by finite element (FE) simulations and experimental results. The effectiveness of this algorithm is tested using two case studies including broken magnet and eccentricity faults. An average accuracy above %96 is obtained using experimental and simulation data. It is proven that the filtering scheme increases the overall accuracy of fault diagnosis.

8 November 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
GPGenchang Peng
Genchang Peng
MNMehrdad Nourani
Mehrdad Nourani
HDHina Dave
Hina Dave
JHJay Harvey
Jay Harvey

17 November 2015 in IEEE Design & Test
Verified
Journal Article
Closed access
SASenthil Arasu
Senthil Arasu
MNMehrdad Nourani
Mehrdad Nourani
JCJohn M. Carulli
John M. Carulli
VRVijay K. Reddy
Vijay K. Reddy
Circuits wear out (age) over time, especially with shrinking feature sizes. This article focuses on an aging mechanism called bias-temperature instability. The authors investigate how far related performance degradation can be contained.