Browsing by Author "Iqra Khalid"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Metropolis Violation Detector Using Deep Neural Network
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Iqra Khalid; FA19-RCS-014; LHR TP 7298; Dr. Zeeshan Gillani
    Anomaly discovery on road traffic is a significant assignment because of its extraordinary potential in metropolitan traffic the board and street wellbeing. It's anything but an extremely difficult assignment since the strange occasion happens seldom and shows various practices. In this work, we present a model to recognize abnormality in street traffic by gaining from the vehicle movement designs in two particular yet connected modes, i.e., the static mode and the powerful mode, of the vehicles. The static mode investigation of the vehicles is gained from the foundation demonstrating followed by vehicle identification technique to find the unusual vehicles that keep still out and about. The unique mode investigation of the vehicles is gained from identified and followed vehicle directions to find the strange direction which is atypical from the predominant movement designs. The outcomes from the double mode investigations are finally melded by driven a re identification model to acquire the final abnormality. This study was based on three classes of anomalies (car crash, car stall and lane change). It was divided into a two class problem with 63 anomaly folders and 86 no anomaly folders. Dataset was provided by NVIDIA AI city challenge track 4 containing 100 train and 100 test videos. Firstly videos were annotated according to anomaly event time. The anomaly time was converted into seconds and then specific frames were cropped. Then 30 frames per video were selected to fed into ResNet18 for high feature extraction. Then LSTM architecture and 3D-CNN was trained and results were evaluated on accuracy evaluation measure. Satisfying results was obtained from both architectures i-e; 80 % accuracy of 3D-CNN and 83 % accuracy of ResNet with LSTM. As it is an on-growing field many work can be done in future by using advanced models for the improvements
  • No Thumbnail Available
    Item
    Synthesis and Characterization of NiFe2O4/CS Nanocomposites and its application towards Choline Biosensing
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Iqra Khalid; CIIT/SP20-RPH-031/LHR; Dr. Akbar Ali; LHR TP 7715
    A non-enzymatic choline biosensor was demonstrated with chitosan (CS) supported NiFe2O4 modified on carbon paste electrode (CPE). The NiFe2O4 was synthesized via hydrothermal method to study the choline chloride (ChCl) behaviour towards the distinctive performance of choline. The prepared sample presented cost-effective choline sensing as emerged with CS formed NiFe2O4/CS and immersed with CPE. The synthesized NiFe2O4 was examined with different characterization technique to confirm the formation of specified material. X-ray diffraction (XRD), Fourier- Transmission Infrared spectroscopy (FTIR) and Raman Spectroscopy used to optimize and evaluate the various properties of prepared material. XRD confirmed the cubic inverse spinel crystal structure of NiFe2O4 with crystallite size of 14nm, while FTIR spectra revealed the stretching and bending vibration over the IR frequency range and modes confirmed through Raman spectra frequency range. The modified electrode of NiFe2O4/CS/CPE was used to perform electrochemical studies by voltammogram and evaluated through Cyclic voltammetry (CV). The CV curves taken at different working range (5-15μL) of potential 0.0-+1.0 V and quantified the analyte signal of LoD (0.002μM) considering the S/N=3 across the current system with the linear regression (R2) of 0.99. The prepared electrode showed the low (LoD) at the smaller range of the choline chloride and demonstrated good response