“Ayesha is an expert in the field of machine learning / analytical models. She is able to design and develop new solutions requiring multiple algorithms and software development / implementations to address complex problems. Ayesha is a team player, not afraid to make commitments, and works hard to meet scheduling requirements. I highly recommend Ayesha, she is an asset for any technical development team. ”
About
Currently working in Azure Compute (OS of cloud) - Building capabilities for Spot Virtual…
Activity
-
When I started learning data science, AI did not exist 👇🏽 You wanted to learn something? You figured it out the hard way: - You found a book. -…
When I started learning data science, AI did not exist 👇🏽 You wanted to learn something? You figured it out the hard way: - You found a book. -…
Liked by Ayesha Gurnani
-
Last week, I had a unique opportunity to reinforce Azure’s leadership in AI innovation during my visit to our European hubs in Bucharest, Romania…
Last week, I had a unique opportunity to reinforce Azure’s leadership in AI innovation during my visit to our European hubs in Bucharest, Romania…
Liked by Ayesha Gurnani
-
Started my journey at One New Zealand(Vodafone NZ previously) in 2022. Almost after 3 and half years it comes to an end. It was a great experience…
Started my journey at One New Zealand(Vodafone NZ previously) in 2022. Almost after 3 and half years it comes to an end. It was a great experience…
Liked by Ayesha Gurnani
Experience & Education
-
Microsoft
View Ayesha’s full experience
See their title, tenure and more.
or
Volunteer Experience
-
Event Manager
GTU Techfest
- 2 months
Education
-
Event Coordinator
Lakshya 2015
- Present 11 years 5 months
Education
-
Reviewer
Women in Machine Learning
- Present 8 years 10 months
Science and Technology
-
Mentor
Women Mentoring Women in Engineering at UT Dallas
- Present 7 years 6 months
Education
I mentor women in engineering at UTDallas to find their passion and help them for interview preparation for the job in the tech industry.
Publications
-
A novel approach for Image Segmentation using Histograms and Hue-Data Value
Internation Journal of Scientific Research Development
We developed a new method for segmenting an image which is the most important part of any Computer Vision problem.
Other authors -
-
Flower Categorization using Deep Convolutional Neural Networks
arXiv:1708.03763
We have developed a deep learning network for classification of different flowers. For this, we have used Visual Geometry Group's 102 category flower dataset having 8189 images of 102 different flowers from University of Oxford. The method is basically divided into two parts; Image segmentation and classification. We have compared the performance of two different Convolutional Neural Network architectures GoogLeNet and AlexNet for classification purpose. By keeping the hyper parameters same for…
We have developed a deep learning network for classification of different flowers. For this, we have used Visual Geometry Group's 102 category flower dataset having 8189 images of 102 different flowers from University of Oxford. The method is basically divided into two parts; Image segmentation and classification. We have compared the performance of two different Convolutional Neural Network architectures GoogLeNet and AlexNet for classification purpose. By keeping the hyper parameters same for both architectures, we have found that the top 1 and top 5 accuracies of GoogLeNet are 47.15% and 69.17% respectively whereas the top 1 and top 5 accuracies of AlexNet are 43.39% and 68.68% respectively. These results are extremely good when compared to random classification accuracy of 0.98%. This method for classification of flowers can be implemented in real time applications and can be used to help botanists for their research as well as camping enthusiasts.
Other authors -
-
Human Detection and Tracking for Video Surveillance A Cognitive Science Approach
arXiv
With crimes on the rise all around the world, video surveillance is becoming more important day by day. Due to the lack of human resources to monitor this increasing number of cameras manually new computer vision algorithms to perform lower and higher level tasks are being developed. We have developed a new method incorporating the most acclaimed Histograms of Oriented Gradients the theory of Visual Saliency and the saliency prediction model Deep Multi Level Network to detect human beings in…
With crimes on the rise all around the world, video surveillance is becoming more important day by day. Due to the lack of human resources to monitor this increasing number of cameras manually new computer vision algorithms to perform lower and higher level tasks are being developed. We have developed a new method incorporating the most acclaimed Histograms of Oriented Gradients the theory of Visual Saliency and the saliency prediction model Deep Multi Level Network to detect human beings in video sequences. Furthermore we implemented the k Means algorithm to cluster the HOG feature vectors of the positively detected windows and determined the path followed by a person in the video. We achieved a detection precision of 83.11% and a recall of 41.27%. We obtained these results 76.866 times faster than classification on normal images.
Other authors -
Courses
-
Advanced Microprocessor
216102
-
Digital Signal Processing
-
-
Image Processing
-
-
Microcontroller Interfacing
2151001
-
Microprocessor Interfacing
2141001
-
Signals and System
-
-
VLSI
2161101
Projects
-
Real time Object Detection on Raspberry Pi
- Present
-
Person Re-identification
- Present
Detecting the face of person going through a gate and coming out of the gate for security purposes.
-
Crowd Motion Analysis
- Present
We are developing Computer Vision algorithms for detecting the number of people in densely crowded images.
-
Object Detection on Synthetic data using Convolutional Nueral Networks
- Present
Generally, the problem with machine learning is that it needs a lot of data. So we are making Synthetic data and then apply Convolutional Nueral Networks to it. Using transfer learning, we applied this to real data set.
-
Real time gesture control game
We used "Haar Cascade" classifiers for fist detection. After detecting the fist, we made a game gesture controlled.
-
Flower Species Classification
- Present
We are trying to classify flower species from the flower's picture using Machine Learning algorithms
Other creators -
-
Real time Color filtering for videos using OpenCV
I filtered out a particular color from the picture frame being recorded i.e. making the desired color white and the rest of the image black. This can be used for object detection on the basis of color.
Other creators -
-
Fetching data from Internet
Here, the underlying concept was of Internet of Things wherein we used ESP8266 i.e. WiFi module. This can be further used to fetch any information from the web and any operations can be done henceforth.
Other creators -
-
Line Follower Robot using PID Control
We used Arduino as the controlling element to implement a PID based control system for the robot. We used the L298N as the motor driver.
Other creators -
-
Range Finder using Ultrasonic Sensor
-
The ultrasonic sensor was interfaced with AVR. Using the sensor, we were able to get the signals which when put in the formula gives us the distance of object from the sensor. Some other modules like LCD was also interfaced so that the processed data can be seen.
Other creators -
-
Sending data from mobile to microcontroller over Bluetooth
-
As the name suggests, data was fetched from mobile and given to the microntroller. We used bluetooth module to fetch data from mobile phone. This fetched data was then given to the AVR serially using USART.
Honors & Awards
-
100% Travel Grant to attend Society of Women Engineering Conference, Minneapolis, Minnesota, 2018
Socciety of Women Engineering
-
Travel Grant to attend Women in Machine Learning Conference, Long Beach, California, 2017
Women in Machine Learning
Test Scores
-
TOEFL
Score: 95
-
GRE
Score: 310
Languages
-
English
Professional working proficiency
-
Hindi
Professional working proficiency
-
Gujarati
Native or bilingual proficiency
-
Sindhi
Native or bilingual proficiency
Recommendations received
1 person has recommended Ayesha
Join now to viewMore activity by Ayesha
-
Although they are infrequent, last Week’s AWS outage took down half the internet. Netflix kept streaming. This wasn't luck. We learned this lesson…
Although they are infrequent, last Week’s AWS outage took down half the internet. Netflix kept streaming. This wasn't luck. We learned this lesson…
Liked by Ayesha Gurnani
Other similar profiles
Explore more posts
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top content