Top 30+ Best Artificial Intelligence Project Ideas For FYP

Computer Science Engineering (CSE) and Information and Technology (IT) are technical areas that deal with the production and study of computer applications. Graspcoding offers the broadest collection of Best Artificial Intelligence Project Ideas For FYP and research for CSE and IT students. So, Graspcoding lists the best and most recent groundbreaking Artificial Intelligence project topics for research and development for CSE, IT, and other branches of software engineering. These projects were analyzed and assembled into a list to make it easier for students to pick their preferred project subject for discussion in the final year. Get the most comprehensive collection of projects for IT and CSE students at Graspcoding. Browse our page below to find the artificial intelligence topics for your final year in the engineering and IT field:

1. An Intelligent Autopilot System that Learns Drive

This project helps in getting the steering angle of the self-driving car. The inspiration is taken from Udacity Self driving car module as well the End to End Learning for Self-Driving Cars module from NVIDIA.

  • a. Dataset: Udacity
  • b. Inspiration: Udacity self-driving car and End to End Learning for self-driving cars by Nvidia
  • c. Techniques Used: CNN
  • d. Pixel Size: 2500
  • e. Computer Vision Library: OpenCV
  • f. Regularization Used: Dropout

2. A computer vision based vehicle detection and counting system

In many cities around the world, traffic issues are an important concern. The traffic problem has many big causes. Due to better health care, better education, better job opportunities, and well-built houses people migrate from rural to urban areas. And the number of residents moving to urban areas has increased dramatically, resulting in a drastic rise in the number of vehicles. Due to increasing the number of residents, the capacity of the roadway has become inadequate and has grown relatively slow. In large cities, this causes roads and the number of vehicles to be imbalanced which results in road congestion. Similarly, public transportation causes the same problem. Another factor, due to the lack of real-time traffic information causes inadequate traffic management. So, in an intelligent transportation system, especially for traffic management, vehicle detection and counting system plays an important role.

3. Driver Drowsiness Detection System

According to surveys by the World Health Organization (WHO) on road accidents, about 1.3 million people die every year on road highways in 2018. Also, a survey report and research provided by the National Highway Traffic Safety Association (NHTS) on road accidents, about 795 people die from drowsy-driving and 91,000 people die from motor vehicle crashes involving drowsy driving in 2017. So, the drowsy driver is considered as one of the factors for road accidents. Likewise, the researchers show that after 2 to 3 hours, the driver is exhausted and the steering efficiency is also reduced. Likewise, in the early afternoon, after getting lunch and at midnight, there is a larger risk. So, in simple terms, drowsiness is defined as a disorder in which a person feels asleep during active hours. Thus, in this program i.e. Driver Drowsiness Detection System helped us to research three types of people who are suffering from drowsiness: they are categorized as awake, rapid eye movement (REM), and non-rapid eye movement (NREM). 

4. Play Mario Using NEAT Algorithm

NeuroEvolution will refine and develop the configuration of the neural network and the NEAT algorithm was one of the first to illustrate it as a feasible solution. In order to play Mario using a NEAT algorithm, you just have to run the NEATEvolve.lua.

5. Mix and Match

In this tutorial, we are going to discuss the project named mix and match. The mix and match project is based on a conditional generative model. So, the conditional generative model is used to learn to encode and disentangle background, pose, shape, and texture of objects from real images with minimal supervision for the generation of mixed images. This project is based on FineGAN which is an unconditional generative model. So, the unconditional generative model is used to study the required breakdown and picture generator, and use adversarial mutual picture-code delivery to acquire latent factor encoders. Min and match include bounding boxes to the model background during training but no further monitoring is needed.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Download the formatted CUB Data. (Download Link)
  • c. Extract downloaded CUB data inside the data directory.
  • d. Evaluated the model.
  • e. You can train your own model
  • f. Finally enjoy this program.

6. AI Basketball Analysis

In this tutorial, we’ll build an Artificial Intelligence(AI) application named “AI Basketball Analysis” that is based on the concept of object detection. So, object detection helps to collect the data to analyze the shots of basketball digging. Through merely uploading files to the web app, or sending a POST request to the API, we can get the result.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Install all required libraries and modules on your PC.
  • c. Open the Python script named ‘app.py’
  • d. Run ‘app.py’
  • e. Enjoy AI Basketball analysis.
  • f. Finally enjoy this program.

7. Virtual Walk in Google Street View

The project is based on Pose Estimation Models along with Long Short Term Memory (LSTM). The PoseNet model was used for pose estimation, while an LSTM model was used to create TensorFlow 2.0 for the behavior detection portion. Thus, with the aid of the Google Street View, virtual walks project is able to mimic walking around the street all around the world.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Install all the dependencies.
  • c. Download and install Firefox and Geckkodriver.
  • d. Run 'execute.py'
  • e. Finally, enjoy virtual walks program.

8. Sudoku Solver

In this tutorial, we’ll build a sudoku solver game using Pygame and OpenCV. Along with OpenCV, we are using a real-time webcam to solve the sudoku problem. So, while opening thee webcam the system searches in the frame for 9*9 sudoku puzzle, extracts it, resolves it, and overlays the solution on the puzzle itself.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Install Pygame in your PC.
  • c. Open the Python script named b>‘guiapp.py’.
  • d. Run ‘guiapp.py’
  • e. Enjoy Sudoku Solver Game

9. FunMirrors

In this project, we’ll build a FunMirrors program based on computer vision. So, the concept of computer vision in this program is used to relate to the computer projection matrix and geometry of the image formation.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Install all required libraries.
  • c. Run the program
  • d. Enjoy with FunMIrrors Program.

10. Drowning Detector

In this project, we’ll build a drowning detector program. We are using YOLO object detection and can detect whether a person is drowning or it’s a normal person. Similarly, a Raspberry Pi Camera should be used for this project, and can then be put into underwater with a suitable case.

Installation Guide

  • a. Download the repository and unzip the file.
  • b. Install all required libraries.
  • c. Open DrownDetect.py and here you go.
  • d. Enjoy drowning detector program.
  • e. Finally, help to make lifeguards in the swimming pool/River.

11. Retrieval Based Chatbot

In this project, we’ll build a retrieval based chatbot. As we all know, chatbot usually works as an assistant to the customer. And the main purpose of the chatbot is to assist business terms in their consumer interaction by providing accuracy, customization, reliability, and scalability. Thus, while building a chatbot we are using Keras which is a Deep Learning Library, Natural Language Processing Toolkit (NLTK), Tkinter, and some other helpful libraries.

Installation Guide

  • a. At first, Import libraries and load the data.
  • b. Pre-processing the data.
  • c. Creating training and testing data.
  • d. Creating GUI to interact with the chatbot.
  • e. Finally, Enjoy the chatbot.

12. Face Recognition and Detection

In this tutorial, we are going to show something real beautiful program. Here, we are using a Python 3.7.3, OpenCV, and some other Python libraries (NumPy, Dlib, CMake, and face_recognition) to build face recognition and detection program. But, the interesting point is that you can use any version of Python and OpenCV to run this script.

Installation Guide

  • a. Install the Python modules which are specified in "requirements.txt"
  • b. Within the root directory, there is the folder named “faces” which includes all the known faces, and that will be how faces of people are recognized and detected by the system.
  • c. Within the root directory, there is the folder named “test” where you can place your own images in which faces are recognized and detected.
  • d. The final step is to run the python script named “face_rec.py”.

13. Car Plane Detection

This tutorial mainly focused on car plane detection based on Convolution Neural Network. We are using Python 3.7.3 and NumPy to build this program. But, you can use any version of Python to run this code. The main aim of this tutorial is to improve our capacity to analyze the operating process and various CNN architecture based on detecting the car and the plane. Also to obtain knowledge on the basic parameter and hyperparameter that make up a complete program.

Installation Guide

  • a. The initial step is to collect the data for car and plane
  • b. Divide the dataset into train, test and validate dataset (Download Dataset)
  • c. Train the CNN architecture to detect the car and the plane from our dataset which we have created.
  • d. The final step is to evaluate the result

14. Toonify Image

In today’s tutorial, we are providing you a code to toonify your image – to make a photo-realistic cartoon model on your own.

Installation Guide

  • a. Extract faces and align the images
  • b. Project the images (i.e. find the latent code)
  • c. Toonify the images (i.e. use the latent code with the toon model)
  • d. Results will be placed in the stylegan2/generated folder

15. Movie Plot Synopses with Tags: Tags Prediction

Abstract social tagging of movies reveals a wide range of heterogeneous information about movies, like the genre, plot structure, soundtracks, metadata, visual and emotional experiences. Such information can be valuable in building automatic systems to create tags for movies. Automatic tagging systems can help recommendation engines to improve the retrieval of similar movies as well as help viewers to know what to expect from a movie in advance. In this paper, we set out to the task of collecting a corpus of movie plot synopses and tags. We describe a methodology that enabled us to build a fine-grained set of around 70 tags exposing heterogeneous characteristics of movie plots and the multi-label associations of these tags with some 14000 movie plot synopses. We investigate how these tags correlate with movies and the flow of emotions throughout different types of movies. Finally, we use this corpus to explore the feasibility of inferring tags from plot synopses. We expect the corpus will be useful in other tasks where analysis of narratives is relevant.

Installation Guide

  • a. Predict as many tags as possible with high precision and recall
  • b. Incorrect tags could impact customer experience
  • c. TNo strict latency constraints

16. Used Cars Price Estimation

Used cars are priced based on their Brand, Manufacturer, Transmission type and etc etc. This is process is done by a professional who understands the condition and the right pricing scheme of the used cars form his/hers previous experiences. Our goal is to make a Model which can give an estimate of the price that should be intended for the used cars, based on historical data. The data is collected from Craigslist, Craigslist is the world’s largest collection of used vehicles for sale.

ML Modeling

  • a. Linear Regression
  • b. Support Vector Regression
  • c. Linear Support Vector Regression
  • d. MLP Regression
  • e. SGD Regression
  • f. Decision Tree Regression
  • g. XGB Regresion
  • h. Light GBM

17. Corona Detection from X-ray using CNN

Corona virus disease (COVID-19) is an infectious disease caused by a newly discovered corona virus. 465,915 Confirmed cases & 21,031 Confirmed deaths (Updated : 27 March 2020 ) , corona has spread in m ore than 200 countries.

Installation Guide

  • a. X-ray images for patients who have tested positive for COVID-19 are collected
  • b. “Normal” (i.e., not infected) X-ray images from healthy patients are collected
  • c. Divide the dataset in test, train and validate dataset(Download Link)
  • d. Train a CNN to automatically detect COVID-19 in X-ray images via the dataset we created
  • e. Evaluate the results

18. Forensic Sketch to Image Generator using GAN

Welcome to new project details on Forensic sketch to image generator using GAN. Image processing has been a crucial tool for refining the image or we can say, to enhance the image. With the development of machine learning tools, the image processing task has been simplified to great extent. Automatic face sketch-photo generation /synthesis and identification have been always an important topic in computer vision, image processing, and machine learning. As our project falls under the same domain, it takes the help of classes of machine learning algorithms/systems for the transformation of a person’s sketch into the photograph which has the characteristic or feature associated with the sketch. This way, the realistic photograph for any forensic sketch can be obtained easily with precise detail and in less time. The entire process is automated so there is not much human effort while using the system.

Training of Model

To train this network, there are two steps: training the discriminator and training the generator. 

  • a. Training of the Discriminator
  • b. Training of the Generator

19. Credit Card Fraud Detection

One of the big legal problems in the credit card business is a fraud. The key goals of this research are, firstly to recognize the different forms of fraudulent credit cards, secondly, to explore alternative methods utilized in fraud detection. The sub-aim is to evaluate, present, and examine recent results in the identification of credit card fraud. The article sets out terms common in fraud involving credit cards and highlighting figures and key statistics in this field. Various measures such as Logistic Regression, Random Forest, Autoencoder, and SMOTE can be taken and enforced based on the type of fraud faced by the credit card industry or financial institutions. In terms of cost savings and efficiency, the proposals made in this report are likely to have beneficial attributes. The importance of applying these techniques examined here in minimizing credit card fraud. Yet when legitimate credit card users are misclassified as fraudulent there are still ethical issues.

Keywords: Logistic Regression, Random Forest Classifier, Autoencoder, SMOTE

The main aim of this report is to gain the ability to research various machine learning and deep learning algorithms along with its wrong mechanisms based on fraud credit cards and gain knowledge about the techniques which make complete algorithms.

20. Image Captioning using Deep Learning

In the project Image Captioning using deep learning, is the process of generation of textual description of an image and converting into speech using TTS. We introduce a synthesized audio output generator which localize and describe objects, attributes, and relationship in an image, in a natural language form. This also includes high quality rich caption generation with respect to human judgments, out-of-domain data handling, and low latency required in many applications.

Our applicationdeveloped in Flutter captures image frames from the live video stream or simply an image from the device and describe the context of the objects in the image with their description in Devanagari and deliver the audio output.

Keywords : Text to speech, Image Captioning, AI vision camera

Objective

The objective of this system is to develop an offline mobile application that generates synthesized audio output of the image description.



21. Hand Gesture Classification

Welcome to project tutorial on Hand Gesture Classification. The goal of this project is to train a Machine Learning algorithm capable of classifying images of different hand gestures, such as a fist, palm, showing the thumb, and others. This classification can be useful for Gesture Navigation, for example.

Installation Guide

  • a. Import a few python packages which will be needed to work with images and arrays
  • b. Collect Data
  • c. Load Data
  • d. Use PCA to explain the variance-covariance structure of a set of variables through Linear Combination
  • e. Normalize the data to make sure different features take on similar range of values
  • f. Evaluate the results

22. Artificially Intelligent Targeting System (AITS)

Artificially Intelligent Targeting System (AITS) system detects human infiltration near borders, terrorist activities and shot them down after force command from the center alerted by our system or on its own if there is no response from the center. It also detects small movements near borders which can also be alerted to the state by the system which can call backup from the nearby state authorities for further investigation.

Working Modes

  • a. Mode 1: Human Infiltration
  • b. Mode 2: Motion Detection
  • c. Mode 2: FireArm Detection
  • d. Mode 4: Infrared Detection

23. Ghum Gham: The Journey of Full Information

The intrusion of technology has penetrated deeper into people’s lives in the twenty first century. Smartphones and other mobile devices have found greater use in many spheres of life. Various applications have been invented to be installed in smartphones to assist in various works and goals. Despite the increasing use of smartphones, there is a great scope to use data stored on the devices for wide applications. This leaves room to use smart applications that can provide value to our collected data. As technology is evolving for the ease, simplicity, and convenience, our project to assist people to have information about the places they would be visiting.

As we are at the peak of the information age, we prefer to get information from the data we feed to our system of smart-phones. We all want the value of our data, as we are heading towards the age of Artificial Intelligence and Blockchain. The main idea of this project is to design a system that will run on most of the smartphones and will be helpful for getting information about the popular tourist destinations by feeding the pictures through the system. We resolve to provide every possible information of a particular place to our user in their palm. The system is processed by the image recognition as a part of Artificial intelligence and information is provided as recognized by the system.

Application

  • a. To provide reliable information about various travel destination throughout the country.
  • b. To act as a PaaS system for the tourism industry.
  • c. To bridge the information gap between travellers and tourism places

24. Real Time Number Plate Recognition System

Real Time Number Plate Recognition System is an image processing technology which uses number (license) plate to identify the vehicle. The objective is to design an efficient automatic authorized vehicle identification system by using the vehicle number plate. Number plate recognition (NPR) can be used in various fields such as vehicle tracking, traffic monitoring, automatic payment of tolls on highways or bridges, surveillance systems, tolls collection points, and parking management systems. The developed system first detects the vehicle and then captures the vehicle image. Vehicle number plate region is localized using Neural Network then image segmentation is done on the image. Character recognition technique is used for the character extraction from the plate. The resulting data is then stored in a database along with the time-stamp. The system is implemented and simulated in python, and its performance is tested on real image.

25. Stock Prediction

Stock price forecasting is a popular and important topic in financial and academic studies. Share Market is an untidy place for predicting since there are no significant rules to estimate or predict the price of share in stock market. Many methods like technical analysis, fundamental analysis and statistical analysis etc. are all used to attempt to predict the stock price in the share market but none of these methods are proved as a consistently acceptable prediction/forecasting tool.

Scope

  • a. Saving of time
  • b. Relief from processor problem
  • c. Work on several numbers of data

26. Weather Prediction

Weather is an important aspect of a person’s life as it can help us to know when it’ll rain and when it’ll be sunny. Weather forecasting is the attempt by meteorologists to predict the weather conditions at some future time and the weather conditions that may be expected. The climatic condition parameters are based on the temperature, pressure, humidity, dew-point, rainfall, precipitation, wind speed and size of dataset. Here, the parameters temperature, pressure, humidity, dew-point, precipitation, rainfall is only considered for experimental analysis.

The steps involved in preprocessing are:

  • a. Features selection
  • b. Normalization
  • c. Machine Learning

27. Blood Cancer Detection

The purpose of our project is to develop a system that can automatically detect cancer from the blood cell images. This system uses a convolution network that inputs a blood cell images and outputs whether the cell is infected with cancer or not. The appearance of cancer in blood cell images is often vague, can overlap with other diagnoses, and can mimic many other benign abnormalities. These discrepancies cause considerable variability among medical personnel in the diagnosis of cancer. Automated detection of cancer from blood cell images at the level of expert medical personnel would not only have tremendous benefit in clinical settings, it would also be invaluable in delivery of health care to populations with inadequate access to diagnostic imaging specialists.

  • a. The initial step is to collect the data for normal and cancer patient
  • b. Divide the dataset into train, test and validate dataset
  • c. Train the CNN architecture to detect the normal and the cancer patient from our dataset which we have created.
  • d. The final step is to evaluate the result

28. Real Estate Web Application with Recommendation System

This web application is an online real estate management through which individual agents or buyer can maintain their property document keeping and managing property registration and also access its information and manage all the adding, updating, deleting and some of its tasks. The Admin user can inform their agents for regarding to property and update the information regarding property and cancel the property of buyer’s choice.

29. Handwriting Recognition using CNN

Machine Learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. It can also be defined as the scientific study of algorithms and statistical models that computer systems use to effectively perform a specific task without using explicit human intervention, relying on patterns and inference instead. Similarly, a mathematical equation is a statement that defines the equality of two expressions which can be used to define almost all the remaining mathematical theorems and science theories.

30. Movie Recommendation System

Our project entitled “Movie Recommendation System” aims to suggest or recommend the various users, the movie they might like, by intake of their ratings, comments, and history. The system proposed is a kind of collaborative-based filtering system that finally recommends the likable movie to the users using K-means clustering. This will extract vital information and recommend the users according to the user’s preferences, interests, or history about movies. Our system is to use dataset which is to be thoroughly filtered in order to gain user’s idea for movies. This system is to be implemented with web services (on the server-side) and desktop applications (on the client-side). This filtering method matches content resources to user characteristics, base their predictions on the user’s information. It relies heavily on the ratings of different users.



31. Image Encryption and Decryption

This is the proposal for the design and development of software named as “Secure Image Encryption Using Algorithm Based On Rubik’s Cube Principle”. It applies special mathematical algorithm and keys to transform digital image into chiper code before they are transmitted and decrypts using application of mathematical algorithms and keys to get back the original data from the chiper code. The goal is to provide authentication of users and integrity, accuracy and safety of data resources.

Objective

The main objective of our project is to provide security of the image-based data with the help of suitable key and protect the image from illegal copying and distribution.


32. Intrusion Detection System

An Intrusion Detection System is a software application that monitors a network or system for malicious activity or policy violations. A host-based intrusion detection system (HIDS) is an intrusion detection system that is capable of monitoring and analyzing the internals of a computing system as well as the network packets on its network interfaces. A HIDS analyzes the traffic to and from the specific computer on which the intrusion detection software is installed. A host-based system also has the ability to monitor key system files and any attempt to overwrite these files.

Objective

To compare and analyze the accuracy of different algorithms for intrusion detection.

33. Image Colorization using CNN

This application is related to image processing based on CNN (Convolution Neural Network). The basic idea behind this project is to convert black and white images to colored image. We are using Convolution Neural Network capable of coloring black and white images. Image colorization is the process of taking an input grayscale (black and white) image and then producing an output colorized image that represents the semantic colors tones of the input.

The main concept behind colorization is:

  • a. Convert all training images from the RGB color space to the lab color space
  • b. Use the L channel as the input to the network and train the network to predict the AB channel
  • c. Combine the input L channel with the predicated AB channels
  • d. Convert the LAB image back to RGB


The development of full artificial intelligence could spell the end of the human race….It would take off on its own, and re-design itself at an ever-increasing rate. Humans, who are limited by slow biological evolution, couldn’t compete, and would be superseded.

Stephen Hawking, BBC

☺ Thanks for your time ☺

What do you think of this Best Artificial Intelligence Project Ideas For FYP? Let us know by leaving a comment below. (Appreciation, Suggestions, and Questions are highly appreciated).

4 thoughts on “Top 30+ Best Artificial Intelligence Project Ideas For FYP

Leave a Reply

Your email address will not be published. Required fields are marked *