Loading...
Search for:
linear-discriminant-analyses--lda
0.008 seconds
A fusion-based gender recognition method using facial images
, Article 26th Iranian Conference on Electrical Engineering, ICEE 2018, 8 May 2018 through 10 May 2018 ; 2018 , Pages 1493-1498 ; 9781538649169 (ISBN) ; Bagheri Shouraki, S ; Mohammadzade, H ; Iranmehr, E ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2018
Abstract
This paper proposes a fusion-based gender recognition method which uses facial images as input. Firstly, this paper utilizes pre-processing and a landmark detection method in order to find the important landmarks of faces. Thereafter, four different frameworks are proposed which are inspired by state-of-the-art gender recognition systems. The first framework extracts features using Local Binary Pattern (LBP) and Principal Component Analysis (PCA) and uses back propagation neural network. The second framework uses Gabor filters, PCA, and kernel Support Vector Machine (SVM). The third framework uses lower part of faces as input and classifies them using kernel SVM. The fourth framework uses...
Label-free detection of β-amyloid peptides (Aβ40 and Aβ42): a colorimetric sensor array for plasma monitoring of alzheimer's disease
, Article Nanoscale ; Volume 10, Issue 14 , 2018 , Pages 6361-6368 ; 20403364 (ISSN) ; Hormozi Nezhad, M. R ; Mahmoudi, M ; Sharif University of Technology
Royal Society of Chemistry
2018
Abstract
Monitoring the ratio of 40- and 42-residue amyloid β peptides (i.e., Aβ40 and Aβ42) in human plasma is considered one of the hallmarks of detection of the early stage of Alzheimer's disease (AD). Therefore, development of a specific, yet non-antibody-based method for simultaneous detection of Aβ40 and Aβ42 may have considerable clinical applications. Here, we developed a 'nanoparticle-based colorimetric sensor array' utilizing label-free gold and silver nanoparticles for visual detection of Aβ42 and Aβ40. Different aggregation behaviors of nanoparticles through their conjugation with Aβ42 and Aβ40 followed by the coordination of Aβ42 and Aβ40 with Cu(ii) led to diverse spectral and color...
Fisherposes for human action recognition using kinect sensor data
, Article IEEE Sensors Journal ; Volume 18, Issue 4 , 2018 , Pages 1612-1627 ; 1530437X (ISSN) ; Mohammadzade, H ; Mokari, M ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2018
Abstract
This paper proposes a new method for view-invariant action recognition that utilizes the temporal position of skeletal joints obtained by Kinect sensor. In this method, the actions are represented as sequences of several pre-defined poses. After pre-processing, which includes skeleton alignment and scaling, the appropriate feature vectors are obtained for recognizing and discriminating the pose of every frame by the proposed Fisherposes method. The proposed regularized Mahalanobis distance metric is used in order to recognize both the involuntary and highly made-up actions at the same time. Hidden Markov model (HMM) is then used to classify the action related to an input sequence of poses....
Chemiluminometric fingerprints for identification of plasmonic nanoparticles
, Article Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy ; Volume 209 , 2019 , Pages 85-94 ; 13861425 (ISSN) ; Hormozi Nezhad, M. R ; Sharif University of Technology
Elsevier B.V
2019
Abstract
Development of a convenient and inexpensive method for identification and detection of nanoparticles (NPs) is of great interest. In this work, we have developed a novel and simple chemiluminescence based sensor array, with its sensing mechanism mimicking that of olfactory and gustatory systems for discriminating a set of NPs. The proposed method is based on the enhancement effect of NPs on luminol–oxidant CL intensity by their catalytic effect. Three kinds of oxidant including H2O2, AgNO3, and K3Fe(CN)6 were used as sensor elements and NPs exhibited diverse enhancing responses to different oxidant-luminol CL systems producing unique response patterns that were identified through heat map and...