SlideShare a Scribd company logo
Karishma Jain
 The VQA task seeks to solve the problem of
automatically generating answers to
questions of images – an important problem
in realizing Artificial Intelligence.
 Images were fed through a CNN, questions
and answers through a RNN to a :
◦ Conditional GAN setting
◦ Co-Attention setting
 Used tensorflow for the implementation.
 Parallelized the serial ADABOOST
classification algorithm to be implemented on
three platforms(Distributed memory, Shared
memory and GPU)
 Evaluated performance, scaling and speedup
on all the three systems.
 Designed an intelligent lane departure
warning and vehicle collision avoidance
system using monocular camera.
 By using Hard Negative Mining precision
improved by 20% and overall accuracy by
32%.
 Designed a convolution Neural Network from scratch to
classify MNIST dataset. Coded each layer in the
architecture
 Tried three different architectures and the one that gave
really good accuracy is described below
 CONV[3 1 3] POOL[2 2] CONV[3 3 8] POOL[2 2] RELU[]
FLATTEN[4] LINEAR[5 5 8] SOFTMAX[]
 Initial Learning Rate: 0.25
 Weight Decay:0.0005
 Batch Size: 128
 450 iteration: Accuracy-95.94%
 900 iteration Accuracy-97%
 1350 iteration Accuracy-97.37%
 1800 Accuracy-97.59%
 2250 iterations Accuracy-97.74%
 Implemented video Motion Segmentation
using GPCA technique for all possible affine
motions in MATLAB.
 Studied the concepts of power factorization,
dimensionality reduction and implemented
them in a unified framework.
 Obtained accurate segmentation results for
different input videos.
 Designed a game 'SPOT-IT' by implementing
Feature Matching and Foreground separation
in MATLAB.

 Implemented Feature matching using Harris
Operator, Histogram of Gradient Descriptors,
and Foreground and Background separation
using SLIC (Simple Linear Iterative Clustering)
and max-flow-min-cut graphing technique.
 Detected Harris Corners and using Histogram of
Gradients, found feature descriptors and matched
them using Euclidean distance. Since Question
mark appears twice in the two images, maximum
number of matched features correspond to it.
Hence, the similar object between the two images
 Now aim is to separate any object from its
background. Using SLIC(Simple Linear Iterative
Clustering), superpixels are found and then using
maxflow/mincut algorithm foreground (cheese) can
be separated from the backgound.
 Implemented Panorama PhotoStitching in MATLAB.
 Features Detected using Harris Corner Detector and
described by using SIFT (Scale Invariant Feature
Transform).
 Used RANSAC to filter the inliers from all the
matched putative matches while computing the
Homography Matrix.
 Imager(millimetre sized camera) in the world's
smallest computer 'The Michigan Micro Mote'
produces noisy low resolution images of size
160x160.
 Implemented the technique of Delaunay
Triangulation to obtain a single high Resolution
Image from multiple low resolution images
produced by multiple Imagers displaced and
oriented by a fixed amount with respect to
each other.
 Results will be available by the end of this
month.
 Implemented Adaptive Filter using LMS (Least Mean
Square) technique on SPARTAN 3 FPGA using
Verilog.
 Used fixed-point arithmetic and techniques of
parallel processing which reduced the complexity
and data loss.
 Compared the results obtained for signals with
different signal-to-noise ratio and tested for
accuracy in MATLAB.
Used 5 tap filter whose weights were updated until the noisy signal
adapts itself to the desired signal. As seen above the training period is
inversely proportional to the added noise in the signal.
Hardware No of Blocks used
Multipliers 10
Adders/Subtractors 12
Counters 4
Flip-Flops 15
Clock Negative Edge Values Updated
1st Input x comes
2nd Y = w*x is calculated
3rd Y from all taps is added
4th Desired signal (d) comes and error
(emu) is generated and d remains
constant for 5 clock cycles
5th To update coefficients (w)
6th New sample of x comes. Till then x
remains constant.
7th Again Y is generated
8th Y from taps are added
9th Again new sample of d comes and
error is generated.
 Implemented Proximity Sensor using cypress
Programmable System on Chip and ARM
mbed FRDM KL25z board during Summer
Industrial Training at Eduvance, Mumbai.
All projects

More Related Content

What's hot

Forelasning4
Forelasning4Forelasning4
Forelasning4Memo Love
 
Optimization of graph storage using GoFFish
Optimization of graph storage using GoFFishOptimization of graph storage using GoFFish
Optimization of graph storage using GoFFishAnushree Prasanna Kumar
 
poster-hadoop-MiroslavMihaylov
poster-hadoop-MiroslavMihaylovposter-hadoop-MiroslavMihaylov
poster-hadoop-MiroslavMihaylovMiroslav Mihaylov
 
Automatic calibration of hysteretic models through multiple responses
Automatic calibration of hysteretic models through multiple responsesAutomatic calibration of hysteretic models through multiple responses
Automatic calibration of hysteretic models through multiple responsesopenseesdays
 
IEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time TrackerIEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time Trackerc.choi
 
Summarizing videos with Attention
Summarizing videos with AttentionSummarizing videos with Attention
Summarizing videos with AttentionArithmer Inc.
 
Real-Time Visual Simulation of Smoke
Real-Time Visual Simulation of SmokeReal-Time Visual Simulation of Smoke
Real-Time Visual Simulation of SmokeMuhammad Karim
 
Parallel Algorithms K – means Clustering
Parallel Algorithms K – means ClusteringParallel Algorithms K – means Clustering
Parallel Algorithms K – means ClusteringAndreina Uzcategui
 
PRAM algorithms from deepika
PRAM algorithms from deepikaPRAM algorithms from deepika
PRAM algorithms from deepikaguest1f4fb3
 
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...AILABS Academy
 
Svd filtered temporal usage clustering
Svd filtered temporal usage clusteringSvd filtered temporal usage clustering
Svd filtered temporal usage clusteringLiang Xie, PhD
 
Determining the k in k-means with MapReduce
Determining the k in k-means with MapReduceDetermining the k in k-means with MapReduce
Determining the k in k-means with MapReduceThibault Debatty
 
Soft Shadow Maps for Linear Lights
Soft Shadow Maps for Linear LightsSoft Shadow Maps for Linear Lights
Soft Shadow Maps for Linear Lightsstefan_b
 
Geometry Shader
Geometry ShaderGeometry Shader
Geometry Shaderacbess
 
Advanced Techniques for Mobile Robotics
Advanced Techniques for Mobile RoboticsAdvanced Techniques for Mobile Robotics
Advanced Techniques for Mobile RoboticsPrasanth Jaya
 

What's hot (20)

Forelasning4
Forelasning4Forelasning4
Forelasning4
 
Optimization of graph storage using GoFFish
Optimization of graph storage using GoFFishOptimization of graph storage using GoFFish
Optimization of graph storage using GoFFish
 
poster-hadoop-MiroslavMihaylov
poster-hadoop-MiroslavMihaylovposter-hadoop-MiroslavMihaylov
poster-hadoop-MiroslavMihaylov
 
Automatic calibration of hysteretic models through multiple responses
Automatic calibration of hysteretic models through multiple responsesAutomatic calibration of hysteretic models through multiple responses
Automatic calibration of hysteretic models through multiple responses
 
IEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time TrackerIEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time Tracker
 
Masters Thesis
Masters ThesisMasters Thesis
Masters Thesis
 
Motion analyser using image processing
Motion analyser using image processingMotion analyser using image processing
Motion analyser using image processing
 
SparkNet presentation
SparkNet presentationSparkNet presentation
SparkNet presentation
 
Summarizing videos with Attention
Summarizing videos with AttentionSummarizing videos with Attention
Summarizing videos with Attention
 
Real-Time Visual Simulation of Smoke
Real-Time Visual Simulation of SmokeReal-Time Visual Simulation of Smoke
Real-Time Visual Simulation of Smoke
 
Parallel Algorithms K – means Clustering
Parallel Algorithms K – means ClusteringParallel Algorithms K – means Clustering
Parallel Algorithms K – means Clustering
 
PRAM algorithms from deepika
PRAM algorithms from deepikaPRAM algorithms from deepika
PRAM algorithms from deepika
 
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
 
Svd filtered temporal usage clustering
Svd filtered temporal usage clusteringSvd filtered temporal usage clustering
Svd filtered temporal usage clustering
 
Determining the k in k-means with MapReduce
Determining the k in k-means with MapReduceDetermining the k in k-means with MapReduce
Determining the k in k-means with MapReduce
 
Soft Shadow Maps for Linear Lights
Soft Shadow Maps for Linear LightsSoft Shadow Maps for Linear Lights
Soft Shadow Maps for Linear Lights
 
Geometry Shader
Geometry ShaderGeometry Shader
Geometry Shader
 
07 plan agent
07 plan agent07 plan agent
07 plan agent
 
Advanced Techniques for Mobile Robotics
Advanced Techniques for Mobile RoboticsAdvanced Techniques for Mobile Robotics
Advanced Techniques for Mobile Robotics
 
Project
ProjectProject
Project
 

Similar to All projects

Video Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTVideo Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTIRJET Journal
 
EE660_Report_YaxinLiu_8448347171
EE660_Report_YaxinLiu_8448347171EE660_Report_YaxinLiu_8448347171
EE660_Report_YaxinLiu_8448347171Yaxin Liu
 
A multilevel automatic thresholding method based on a genetic algorithm for a...
A multilevel automatic thresholding method based on a genetic algorithm for a...A multilevel automatic thresholding method based on a genetic algorithm for a...
A multilevel automatic thresholding method based on a genetic algorithm for a...Akshit Arora
 
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONMEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONcscpconf
 
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONMEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONcsandit
 
Median based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstructionMedian based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstructioncsandit
 
FPGA Implementation of a GA
FPGA Implementation of a GAFPGA Implementation of a GA
FPGA Implementation of a GAHocine Merabti
 
Two methods for optimising cognitive model parameters
Two methods for optimising cognitive model parametersTwo methods for optimising cognitive model parameters
Two methods for optimising cognitive model parametersUniversity of Huddersfield
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNZihao(Gerald) Zhang
 
Hand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdfHand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdfSwathiSoman5
 
ECG beats classification using multiclass SVMs with ECOC
ECG beats classification using multiclass SVMs with ECOCECG beats classification using multiclass SVMs with ECOC
ECG beats classification using multiclass SVMs with ECOCYomna Mahmoud Ibrahim Hassan
 
An ann approach for network
An ann approach for networkAn ann approach for network
An ann approach for networkIJNSA Journal
 
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...Editor IJMTER
 
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...IOSR Journals
 
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...IJNSA Journal
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System OperationsIRJET Journal
 

Similar to All projects (20)

Video Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTVideo Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFT
 
EE660_Report_YaxinLiu_8448347171
EE660_Report_YaxinLiu_8448347171EE660_Report_YaxinLiu_8448347171
EE660_Report_YaxinLiu_8448347171
 
A multilevel automatic thresholding method based on a genetic algorithm for a...
A multilevel automatic thresholding method based on a genetic algorithm for a...A multilevel automatic thresholding method based on a genetic algorithm for a...
A multilevel automatic thresholding method based on a genetic algorithm for a...
 
Ay33292297
Ay33292297Ay33292297
Ay33292297
 
Ay33292297
Ay33292297Ay33292297
Ay33292297
 
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONMEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
 
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONMEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
 
Median based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstructionMedian based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstruction
 
Kq3518291832
Kq3518291832Kq3518291832
Kq3518291832
 
FPGA Implementation of a GA
FPGA Implementation of a GAFPGA Implementation of a GA
FPGA Implementation of a GA
 
Two methods for optimising cognitive model parameters
Two methods for optimising cognitive model parametersTwo methods for optimising cognitive model parameters
Two methods for optimising cognitive model parameters
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
 
Hand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdfHand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdf
 
ECG beats classification using multiclass SVMs with ECOC
ECG beats classification using multiclass SVMs with ECOCECG beats classification using multiclass SVMs with ECOC
ECG beats classification using multiclass SVMs with ECOC
 
An ann approach for network
An ann approach for networkAn ann approach for network
An ann approach for network
 
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...
Computer aided classification of Bascal cell carcinoma using adaptive Neuro-f...
 
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...
Hardware Implementation of Low Cost Inertial Navigation System Using Mems Ine...
 
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
 
Y34147151
Y34147151Y34147151
Y34147151
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System Operations
 

Recently uploaded

İTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopİTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopEmre Günaydın
 
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringDr. Radhey Shyam
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdfKamal Acharya
 
Halogenation process of chemical process industries
Halogenation process of chemical process industriesHalogenation process of chemical process industries
Halogenation process of chemical process industriesMuhammadTufail242431
 
Arduino based vehicle speed tracker project
Arduino based vehicle speed tracker projectArduino based vehicle speed tracker project
Arduino based vehicle speed tracker projectRased Khan
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsAtif Razi
 
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdfONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdfKamal Acharya
 
Fruit shop management system project report.pdf
Fruit shop management system project report.pdfFruit shop management system project report.pdf
Fruit shop management system project report.pdfKamal Acharya
 
Top 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering ScientistTop 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering Scientistgettygaming1
 
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data AnalysisIT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data AnalysisDr. Radhey Shyam
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...Amil baba
 
ASME IX(9) 2007 Full Version .pdf
ASME IX(9)  2007 Full Version       .pdfASME IX(9)  2007 Full Version       .pdf
ASME IX(9) 2007 Full Version .pdfAhmedHussein950959
 
fundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projectionfundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projectionjeevanprasad8
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdfKamal Acharya
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
 
The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfPipe Restoration Solutions
 
Explosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdfExplosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdf884710SadaqatAli
 
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data StreamKIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data StreamDr. Radhey Shyam
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdfKamal Acharya
 

Recently uploaded (20)

İTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopİTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering Workshop
 
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdf
 
Halogenation process of chemical process industries
Halogenation process of chemical process industriesHalogenation process of chemical process industries
Halogenation process of chemical process industries
 
Arduino based vehicle speed tracker project
Arduino based vehicle speed tracker projectArduino based vehicle speed tracker project
Arduino based vehicle speed tracker project
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
 
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdfONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
 
Fruit shop management system project report.pdf
Fruit shop management system project report.pdfFruit shop management system project report.pdf
Fruit shop management system project report.pdf
 
Top 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering ScientistTop 13 Famous Civil Engineering Scientist
Top 13 Famous Civil Engineering Scientist
 
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data AnalysisIT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
 
ASME IX(9) 2007 Full Version .pdf
ASME IX(9)  2007 Full Version       .pdfASME IX(9)  2007 Full Version       .pdf
ASME IX(9) 2007 Full Version .pdf
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
fundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projectionfundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projection
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
 
The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdf
 
Explosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdfExplosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdf
 
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data StreamKIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
 

All projects

  • 2.  The VQA task seeks to solve the problem of automatically generating answers to questions of images – an important problem in realizing Artificial Intelligence.  Images were fed through a CNN, questions and answers through a RNN to a : ◦ Conditional GAN setting ◦ Co-Attention setting  Used tensorflow for the implementation.
  • 3.
  • 4.  Parallelized the serial ADABOOST classification algorithm to be implemented on three platforms(Distributed memory, Shared memory and GPU)  Evaluated performance, scaling and speedup on all the three systems.
  • 5.  Designed an intelligent lane departure warning and vehicle collision avoidance system using monocular camera.  By using Hard Negative Mining precision improved by 20% and overall accuracy by 32%.
  • 6.
  • 7.
  • 8.  Designed a convolution Neural Network from scratch to classify MNIST dataset. Coded each layer in the architecture  Tried three different architectures and the one that gave really good accuracy is described below  CONV[3 1 3] POOL[2 2] CONV[3 3 8] POOL[2 2] RELU[] FLATTEN[4] LINEAR[5 5 8] SOFTMAX[]  Initial Learning Rate: 0.25  Weight Decay:0.0005  Batch Size: 128  450 iteration: Accuracy-95.94%  900 iteration Accuracy-97%  1350 iteration Accuracy-97.37%  1800 Accuracy-97.59%  2250 iterations Accuracy-97.74%
  • 9.  Implemented video Motion Segmentation using GPCA technique for all possible affine motions in MATLAB.  Studied the concepts of power factorization, dimensionality reduction and implemented them in a unified framework.  Obtained accurate segmentation results for different input videos.
  • 10.
  • 11.  Designed a game 'SPOT-IT' by implementing Feature Matching and Foreground separation in MATLAB.   Implemented Feature matching using Harris Operator, Histogram of Gradient Descriptors, and Foreground and Background separation using SLIC (Simple Linear Iterative Clustering) and max-flow-min-cut graphing technique.
  • 12.  Detected Harris Corners and using Histogram of Gradients, found feature descriptors and matched them using Euclidean distance. Since Question mark appears twice in the two images, maximum number of matched features correspond to it. Hence, the similar object between the two images
  • 13.  Now aim is to separate any object from its background. Using SLIC(Simple Linear Iterative Clustering), superpixels are found and then using maxflow/mincut algorithm foreground (cheese) can be separated from the backgound.
  • 14.  Implemented Panorama PhotoStitching in MATLAB.  Features Detected using Harris Corner Detector and described by using SIFT (Scale Invariant Feature Transform).  Used RANSAC to filter the inliers from all the matched putative matches while computing the Homography Matrix.
  • 15.
  • 16.
  • 17.  Imager(millimetre sized camera) in the world's smallest computer 'The Michigan Micro Mote' produces noisy low resolution images of size 160x160.  Implemented the technique of Delaunay Triangulation to obtain a single high Resolution Image from multiple low resolution images produced by multiple Imagers displaced and oriented by a fixed amount with respect to each other.  Results will be available by the end of this month.
  • 18.  Implemented Adaptive Filter using LMS (Least Mean Square) technique on SPARTAN 3 FPGA using Verilog.  Used fixed-point arithmetic and techniques of parallel processing which reduced the complexity and data loss.  Compared the results obtained for signals with different signal-to-noise ratio and tested for accuracy in MATLAB.
  • 19. Used 5 tap filter whose weights were updated until the noisy signal adapts itself to the desired signal. As seen above the training period is inversely proportional to the added noise in the signal.
  • 20. Hardware No of Blocks used Multipliers 10 Adders/Subtractors 12 Counters 4 Flip-Flops 15
  • 21. Clock Negative Edge Values Updated 1st Input x comes 2nd Y = w*x is calculated 3rd Y from all taps is added 4th Desired signal (d) comes and error (emu) is generated and d remains constant for 5 clock cycles 5th To update coefficients (w) 6th New sample of x comes. Till then x remains constant. 7th Again Y is generated 8th Y from taps are added 9th Again new sample of d comes and error is generated.
  • 22.  Implemented Proximity Sensor using cypress Programmable System on Chip and ARM mbed FRDM KL25z board during Summer Industrial Training at Eduvance, Mumbai.