Projects

This project is a preliminary part of an ongoing Industrial Employee Attendance Project at Fab Lab, Independent University Bangladesh. I used the simplest "face_recognition" API for python in order to recognize faces in front of the camera. Along with it, I created an Attendance project that will use the webcam to detect faces and record the attendance live in an excel sheet. I also incorporated "datetime" library for recording the real-time when attendances are listed. The project also ensures that there is no overlap of attendance because it keeps track of the existing attendance list whenever a face is recognized.

GitHub: https://github.com/MZayed47/Smart_Attendance_System

This project on inspecting the percentage of each province’s population in Canada that are university or college students and also on showing the location of a number of universities throughout Canada. The aim of the project was to see the geographical spaces among the universities and probable position for new ones.

Among the findings, I found that proportion of students has only modest variations throughout Canada. Each university is represented by a point, and the size of each point corresponds to the number of students enrolled at that university. Inset into the map is a close-up view of Southern Ontario, where there is a high density of universities.

Libraries used: geopandas, plotly, matplotlib, pandas, mpl_toolkits, inset_axes.

This project was based on a data set containing the rank (popularity) and count of baby names in England and Wales from the period 1996 to 2020. This was a re-creation the interactive experience in the “Top baby names” visualization published by the UK Office for National Statistics, which can be found here:

https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/livebirths/bulletins/babynamesenglandandwales/2020

This project was from a landscaping company based in St. John’s, Newfoundland, Canada. The company offers a variety of landscaping services, and accepts work from residential and commercial customers in the St. John’s metropolitan area. The company’s broad goal was to answer the question, “How can our company be improved?”

To answer to the company’s broad goal, I identified two sub-goals within the data that I plan to convey. They are:

1) Is the company providing quality service in all the types of services they are providing? How can the service quality be improved?

2) Does the company has a good combination of work-schedule with the employees throughout a whole month? Can the work-schedule be more balanced and developed?

Libraries used: matplotlib, pandas, ipywidgets, IPython, seaborn. 

This project is a part of my ongoing research work on “Real-Time On-Road Vehicle Detection and Distance Estimation”. For this project, I have used the YOLOv4 algorithm (published in April 2020) which is considered the fastest and most accurate version of YOLO. But unlike the previous project, where I created a YOLOv3 model from scratch, in this project, I loaded the actual YOLOv4 model from its core repository and then converted the darknet model into the TensorFlow model (tf.pb). I also explored tflite.pb which is very lightweight and compatible with android phones and other edge devices. This modified TensorFlow model can detect objects from several angles: car dash camera, human-eye height and live feed from drones or helicopters.

The major improvement in YOLO v4 is, it takes the influence of state of art BoF (bag of freebies) and several BoS (bag of specials). The BoF improves the accuracy of the detector, without increasing the inference time. They only increase the training cost. On the other hand, the BoS increase the inference cost by a small amount however they significantly improve the accuracy of object detection. The further improvement of this project for my research work is to estimate the distance of the on-road vehicles

GitHub: https://github.com/MZayed47/Real_time_OD_webcam_dashcam

Based on a data set containing information about all the athletes that have participated in the Olympics up until the 2016 games. The analysis included several goals, some of which are:

1) Show the top 10 most decorated Olympians. That is, the Olympic athletes that have won the highest total number of medals. Each bar is color coded according to the number of gold, silver and bronze medals won by that athlete.

2) Display the number of athletes that competed in the 2012 (dark blue) and 2016 (light blue) Olympics from a set of different countries. Additionally, show the overlap on the number of athletes that competed in both Olympics, and how many competed in just one of these Olympics.

Based on a Population Database containing population trends of all the countries in the world from 1950 to 2020. The analysis had several goals, some of which are:

1) Yearly population change per continent over the past 60 years.

2) The population of the top 10 most populous countries in 2020.

3) Display the median age and percentage population growth from the year 2019 to 2020 for all the countries of the world by color coding them according to their continents.

This project is a part of my second research work on “Real-Time Detection and Recognition of traffic signs in Bangladesh using YOLOv3 Detector”. Before getting started on that research, I had to learn the basics of computer vision algorithms and how they work. I studied several algorithms and found that YOLOv3 is the latest and faster than any other algorithm till now. So, the primary step I took before conducting the research is building this project to detect objects in images using the YOLOv3 algorithm. I used Keras library to build the YOLOv3 model from scratch and loaded it with a pre-trained weight file. Then I used both Keras and TensorFlow to load the model and detect several classified objects in images.

YOLOv3 is now highly used widely for computer vision projects because of its speed and lightweight model. I have continued my exploration in the field of Computer Vision using YOLOv3. The further improvement of this for my research work is to train the model with my team’s custom-made dataset and then run a test accordingly.

GitHub: https://github.com/MZayed47/Object_Detection_using_YOLOv3

This is the first-ever project I have done using the Python programming language. During the third year of my undergraduate study, I learned the Django framework and became interested in building websites associated with JavaScript. Under the influence of excitement, I built a personal website using Django, where I can create separate profiles, record information, upload personal files, etc. I also used HTML, CSS, JavaScript, bootstrap at different levels of the project.

The introductory page displays all the recorded profiles on the website. Clicking on a specific profile takes the user to the details of that profile. If a user wants to register, he/she can register using a User ID and Password. A registered user can add a profile too. They have to click on the “Add Profile” option on the navigation bar at the top-right which will take them to a form to submit their information. After submitting the form, a new profile will be created and displayed on the front page along with the previous profiles.

GitHub: https://github.com/MZayed47/FirstWebDjango

This project includes some works of functions in C++, files, graphics, and some conditions. It helps students to think about prediction mathematically. There are 100 numbers from 0-99 in a list and if one takes a number in mind from it, my project finds out the exact number in only six steps. It includes graphics work in every step.

GitHub:https://github.com/MZayed47/Mind_Game