KrishArul26's repositories
Motorbike-Helmet_detection-using-YOLOV3
This project related to road safety. We have to wear a helmet according to road safety rules when riding a motorcycle. Therefore, these rules are monitored by the police. Also, Due to the invention of high-quality cameras and the development of the state of art in AI, the surveillance system willing to use AI system to detect whether passengers are wearing helmets or not. In this category I have built a model, first, it can be able to detect the motorcycle, then it will find out who is riding the bike. Finally, it will determine whether the person is wearing a helmet or not. To that end, I trained the pre-trained model SSD-MobileNet-V1 to detect motorcycles and humans.
Air-Quality-Index-prediction_with_deployment
India is one of the countries with the highest air pollution country. Generally, air pollution is assessed by PM value or air quality index value. For my further analysis, I have selected PM-2.5 value to determine the air quality prediction and the India-Bangalore region. Also, the data was collected through web scraping with the help of Beautiful Soup.
Text-Classification-DBpedia-ontology-classes-Using-LSTM
Text classification is the task of assigning a set of predefined categories to free text. Text classifiers can be used to organize, structure, and categorize pretty much anything. For example, new articles can be organized by topics, support tickets can be organized by urgency, chat conversations can be organized by language, brand mentions can be organized by sentiment, and so on.
Autonomous-Vehicle-Running-with-Line-Navigation-and-Object-Detection-Using-OpenCV-and-AI-Techniques-
Mobility on a wide scale is moving towards complete automation. Though the technology for automating the vehicles already exists, these technologies must be optimised to fit the current environment. This project would be a scaled-down model of the Autonomous Car. By running these scaled-down models in the live streaming line detection using OpenCV.
Defect-detection-in-Air-Pressure-system-APS-of-a-truck-using-ML
The dataset consists of data collected from heavy Scania trucks in everyday usage. The system in focus is the Air Pressure system (APS) which generates pressurised air that is utilized in various functions in a truck, such as braking and gear changes. The dataset’s positive class consists of component failures for a specific component of the APS system. The negative class consists of trucks with failures for components not related to the APS. So, I created a model where It can able to detect whether the APS is going to fail or Not.
Live-Face-Mask-Detection-Using-Faster_rcnn
Due to the COVID-19 regulation, people have to wear masks to protect themselves. Also, you need to create a system to find out if a person is wearing a mask or not. Also, this system should give a warning or sound when people are not wearing masks. So, I created the model with the help of Fast-R-CNN
Impact-Resistance-Testing-Instrument-for-Ceramic-Floor-Tiles
impact resistance properties of tiles are important property to be identified, for that purpose impact testing instrument was fabricated according to Sri Lanka industry specification
Improvement-Of-Seat-Belt-Detection-Via-Instance-Segmentation-Using-YOLACT-
Wearing a seat belts can reduce the risk of serious injuries by 50%, reduce accidents by up to 45%, and save an average of 15,000 lives each year. This compulsion can be emphasized by monitoring and punishing the wear of seat belts by drivers. In that sense, the detection of seatbelt in the roads is crucial. Although several studies were focused on seat belt detection, some limitations and restrictions have not yet been resolved. Therefore, this study aims to detect the seat belt using instant segmentation approach with YOLACT ++ algorithm. Also, this study intends to detect the seat belt from the real-time video.
IoT-Based-Remote-Sensor-Data-Monitoring-and-Actuator-Control
As the current housing systems are moving towards automation, the focus on the systems used within the house is given more focus than the customer requirement. The systems available in the current market are complex and expensive. The objective of the “IoT based remote sensor data monitoring and actuator control” project is to create a partial open-source monitoring system that can be customized based on the individual requirements of the customer which is cheaper than the available market alternatives and user-friendly.
Smart-Way-Gate-Monitoring-System-for-Supermarket-Due-to-the-Covid-19-Period-using-AI--Live-Streaming
This project is related to whether the person is carrying a rolling basket as well as wearing a mask with them into entering the supermarket or else. The system will generate an alert in terms of sound as well as text.
Bank-Customer-Churn-Prediction-using-DNN-with-Hyperparameter-Tuning
How to Started With ANN using TensorFlow 2.0, Feature selection, Different type of optimizer and activation function, Sampling techniques
Bitcoin-Price-prediction-using-Tensorflow
Live straming forecasting is the biggest challenges into the ML. Here, I applied LSTM, Bi-LSTM, and CNN Deep Learning model to forecast the price of bitcoin.
Cars_Counting-Detection-using-haar-Cacade
Cars detecting and counting using OpenCV
Ecommerce-Sales-Analysis-PowerBI
As an internet revolution now people use online purchasing rather than directly go shopping. So, E-commerce data have to analysis and find the use full information about the business and make decisions accordingly. So, Here I used, Ecommerce data it contains various features like region, product type, sales and price etc. So, This data was queried by Power-Bi and Finally, Dashboard was created.
Image_classification-CNN-
So, Image classification techniques are the basic of object detection So, In this Repository only contain the Image Classification problems and Transfer learning Network frame Work
KrishArul26
Kirsnaragavan portfolio
Password-Strength-Prediction-Deployment
This repository, focus on password strength prediction. I have created an SVM model to classify whether password strength or medium or weak. After training the model, It has deployed on the Heroku platform.
Semantic-Text-Similarity-
Semantic Text Similarity can able to calculate using cosine similarity and Levenshtein distance
Sentiments-Classifier-using-BERT
The process of computationally identifying and categorizing opinions expressed in a piece of text, especially to determine whether the writer's attitude towards a particular topic, product, etc. is positive, negative, or neutral. Understanding people’s emotions is essential for businesses since customers are able to express their thoughts and feelings more openly than ever before. By automatically analysing customer feedback, from survey responses to social media conversations, brands are able to listen attentively to their customers, and tailor products and services to meet their needs.
Smart-Car-Parking-System-using-Camera-and-Ultrasonic-Sensor-with-Computer-Vision-Techniques
Home Vehicle parking system is one of the most important factors to reduce traffic and satisfy drivers. Moreover, when parking vehicles in the apartment parking place, the driver has to open the door. So, the driver has to get out of the vehicle and open it. In this project, we have created a system for an automated vehicle parking system using computer vision techniques and a Raspberry-Pi camera module and an ultrasonic sensor.
Spam-Mail-Classification-Using-ML
Spam Mail detection Jupyter-Notebook
Speech-To-Text-Using-AI
Speech Recognition is an important feature in several applications used such as home automation, artificial intelligence, etc. This article aims to provide an introduction on how to make use of the SpeechRecognition library of Python. This is useful as it can be used on micro controllers such as Raspberry Pis with the help of an external microphone.
TensorFlow_Certificate_Exam-Prepration
This is repo is in development. It is used to keep resources, course references, and code examples while preparing for the TensorFlow Developer Certification exam. If the work here helps you in some way please feel free to share, fork, or star.
Text-Generation-using-GPT2
GPT-2 is a pre-trained language model that can be used for various NLP tasks such as text generation, data summarization, and translation. Language models are statistical tools to predict/generate the next word(s) in a sequence based on the preceding word(s). The GPT-2 architecture is based on the Transformers concept. The Transformer provides a mechanism based on encoder-decoders to detect input-output dependencies. At every stage, the model takes the previously generated data as additional input when generating the next output. GPT-2 has outperformed other language models when it comes to generating articles based on small input content.
VGG-16-Inception-V3-Cotton-Disease-Prediction
Cotton disease prediction using CNN frameworks such as VGG-16, Inception-V3 and Inception-Resnet-v2.