DATA SCIENTIST

PROJECT BRIEF

DATA SET

Project Brief:

Several research on the factors influencing life expectancy have been conducted in the past, taking into account demographic demographics, income composition, and mortality rates but, It was discovered that the impact of vaccinations and the human development index had not previously been taken into consideration. Additionally, a number of earlier studies used data from all the countries collected over the course of one year and multiple linear regression. This provides incentive to develop a regression model based on a mixed-effects model and multiple linear regression while taking data from a period of 2000 to 2015 for all the countries, in order to address both of the previously mentioned problems. Hepatitis B, polio, and diphtheria vaccinations are also important to consider. In essence, this study will concentrate on elements connected to immunisation, mortality, the economy, society, and other aspects of health. A country will find it easier to identify the predicting factor causing a lower value of life expectancy as the observations in this dataset are based on multiple countries. This will assist in recommending to a nation which region should be prioritised in order to effectively raise the population's life expectancy.

Project Brief:

Georgia country becomes one of the top travel destinations in recent years. Understanding the characteristics of the time series representing international visits to the country provides valuable insights for business. In this project, the number of visitors that would probably turn up in coming years is calculated using SARIMA, Winters and XGBOOST models. The outcome is used in budgeting and revenue planning for one of the local hotels. Some of the most effective forecasting methods in time series analysis include SARIMA and WINTERS Exponential Smoothing . The Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Square Error are used to measure the accuracy of the fitted models (MAE)

Project Brief:

Fire detection is an essential aspect of fire safety systems, and the development of technology has made it possible to create advanced systems that can detect fires with greater accuracy and efficiency. One such technology is the YOLOv5 object detection algorithm, which is a deep learning-based approach used to detect objects in images and videos. In this project, YOLOv5 is utilized to detect fires in real-time using a camera connected to a computer. To make the system more practical, an Arduino Uno board is used for the real-time triggering of output devices such as a buzzer, LED, and an LCD display. A serial connection is established between the YOLOv5 model running on a PC and the Arduino board, enabling communication between the two. The system triggers the output devices whenever a fire is detected, making it a reliable tool for early fire detection and prevention. This project provides an efficient solution to enhance fire safety systems, ensuring that appropriate action is taken promptly to minimize the damage caused by fires.

Project Brief:

In the wake of the novel corona virus, lots of disciplinary actions are imposed by the government of many countries to slow down the transmission of the deadly virus. With the enhancing usage of modern technology in the period of pandemics to smoothen up the operations and functionality of the numerous organizations. Among these, with the interpretation of AI, facemask detection technology is used to monitor social distancing and even to identify the usage of face masks.

Project Brief:

With the advancements in computer vision and deep learning, it is now possible to develop highly accurate animal identification systems. One such system is the cat and dog identification system using YOLOv5, which is an object detection algorithm used to identify and localize objects in images and videos. This project aims to develop a system that can accurately distinguish between cats and dogs in images and videos. The YOLOv5 algorithm is trained on a large dataset of cat and dog images, enabling it to detect and identify these animals with high accuracy. The system can be used for various applications, such as identifying the presence of cats and dogs in animal shelters, monitoring animal populations in the wild, and even for pet owners to keep track of their pets. This project provides an efficient and reliable solution for animal identification, which has significant applications in the field of animal welfare and behavior studies.

Project Brief:

The "Intelligent Door Access System with Facial Recognition and Voice Control" is a project that aims to create a smart door system that can automatically recognize the face of a person and allow them access to a building or a room. The system is equipped with a camera that captures the face of a person when they ring the doorbell, and a facial recognition algorithm that identifies the person based on their unique facial features.In addition, the system is integrated with Alexa, a voice-controlled virtual assistant, which enables the user to interact with the system using voice commands. Through Alexa, the user can identify the person at the door and command the door to open or close, providing an added layer of security and convenience.

Project Brief:

Imagine a world where you don't need to lift a finger to control the ambiance of your home. With the help of cutting-edge technology, this dream is now a reality. Introducing "Smarter Alexa with ChatGPT for Controlling LED Lights," a project that revolutionizes the way we interact with our smart homes. This project combines the power of Amazon's Alexa and ChatGPT, a state-of-the-art language model, to create a seamless and intuitive experience for controlling LED lights. By using natural language processing, this project allows users to simply speak their commands to Alexa, who then communicates with ChatGPT to accurately interpret and execute the desired actions.

To implement this project, a Raspberry Pi 4 is used as a server to communicate with the Alexa Skill Set. The Raspberry Pi 4 is a powerful microcomputer capable of running multiple programs simultaneously, making it an ideal choice for handling the complex communication between Alexa and ChatGPT. Additionally, the project utilizes the Wiznet-EVB-PICO-5100s board, which is connected to both the LED lights and an 8*8 dot matrix. This board acts as a bridge between the Raspberry Pi and the LED lights, allowing for easy control and manipulation of the light's color and intensity. With the Wiznet-EVB-PICO-5100s board, the LED lights can be synced to music, set to change color depending on the time of day, or even programmed to display scrolling messages on the dot matrix.

Project Brief:

Introducing the project, "INTELLIGENT NOTICE PANEL WITH ALEXA". With this state-of-the-art technology, you can effortlessly control your display with the power of your voice. Whether you need to turn the display on or off or change the text to display precisely what you need, this system provides a hands-free solution to all your display needs.The beauty of this project lies in its simplicity. By utilizing the power of Alexa, you can seamlessly integrate your display into your smart home network and easily manage it with just a few simple voice commands. No more fumbling for remotes or struggling with confusing menus - with "Smarter Display using Alexa," you can easily take control of your display.

Whether you're looking to improve your office productivity or want a more streamlined experience at home, this project is the perfect solution. With its intuitive design and user-friendly interface, it's always been challenging to manage your display and ensure you always have the information you need. So why wait? Experience the convenience and efficiency of "INTELLIGENT NOTICE PANEL WITH ALEXA" today, and take the first step towards a smarter, more connected future.

Project Brief:

Create an IoT setup to send messages to the end client upon triggering. As mentioned earlier, the triggering activity will be a button similar to a doorbell. From the end client, the user should be able to send his response back to the IoT device, which will display the message in an 8*8 dot matrix led panel. The time for reconnecting and sending messages should be ideal. The end client chosen was a telegram bot.

Project Brief:

A number of methods have been proposed to automatically extract collocations, i.e., conventionalized lexical combinations, from text corpora. However, the attempts to evaluate and compare them with a specific application in mind lag behind. This paper compares three end-to-end resources for collocation learning, all of which used the same corpus but different methods. Adopting a goldstandard evaluation method, the results show that the method of dependency parsing outperforms regex-over-pos in collocation identification. The lexical association measures (AMs) used for collocation ranking perform about the same overall but differently for individual collocation types. Further analysis has also revealed that there are considerable differences between other commonly used AMs.

Project Brief:

Document/Text classification is an important task that has use cases in many real-world problems. Assigning topics to documents like news article, books, webpages, social media post has many applications like spam filtering, sentiment analysis, tagging customer queries, fake news detection etc. Natural language's vastly large size, unrestrictive nature, and ambiguity led to two problems when using standard parsing approaches that relied purely on symbolic, hand-crafted rules: unmanageable numerous rules and inability to understand ungrammatical text something which is human comprehensible easily. A problem statement apt for machine learning. NLP is a branch of data science that consists of systematic processes for analyzing, understanding, and deriving information from the text data in a smart and efficient manner. By utilizing NLP and its components, one can organize the massive chunks of text data, perform numerous automated tasks and solve a wide range of problems such as – automatic summarization, machine translation, named entity recognition, relationship extraction, sentiment analysis, speech recognition, and topic segmentation etc.