Fire and Smoke Detection Using Object Detection Techniques on Hikvision HEOP IP Cameras

iThermAI• 2024 - now

Detection of Sitting and Working Postures in the Workplace and Industry using Computer Vision and YOLO

IPM• 2023

Crack Detection in Concrete Images using Image Processing and Deep Convolutional Neural Networks

SUT• 2023

Diagnosing Human Body Abnormalities using Image Processing and Pose Estimation Algorithms

ViraSetAI• 2022

Signature Similarity Measurement using Deep Few-shot Learning

Central Bank• 2021

2D Teeth Image Semantic Segmentation using U-NET and Detectron2 Mask RCNN for Smile Design with Generative Adversarial Networks (GANs)

ISAA Project• 2021

Tumor Segmentation in Brain MRI Images using DeepMedic on the BraTS dataset and developing a dual-platform Windows/Linux software service [Project Link]

MarcoPacs Project• 2021

Mapping 3D CBCT Images to 2D Panoramic OPG Dental Images using Image Processing Algorithms

A Clinical Project• 2020

Diagnosis of Pulmonary Diseases using Image Processing and Deep Learning

Massih Daneshvari hospital• 2019

Human Complex Activity Recognition in Video Images using Deep Neural Networks

MS. Thesis• 2018

Q1 Journal: Advanced techniques for wind energy production forecasting: Leveraging multi-layer Perceptron + Bayesian optimization, ensemble learning, and CNN-LSTM models [Link]

Case Studies in Chemical and Environmental Engineering, Volume 10• December 2024

Due to the shortage of fossil fuels in many countries, power plants that rely on fossil fuels will be phased out in favor of wind turbines as the primary source of energy generation. These fossil fuel plants wreak havoc on the natural world, making humans and other life forms susceptible to illness. The production potential of wind turbines was investigated. Consequently, methods such as XGBOOST, Multi-Layer Perceptron with Bayesian Optimization (MLP + BO), Gradient Boosting Regression Tree (GBDT), Ensemble (gradient boosting and xgboost), and CNN Long Short-Term Memory (CNN-LSTM) have been utilized. A mean square error (MSE) of 7.2 in 45 seconds was achieved using the Ensemble technique, and an MSE of 6.8 in 450 seconds was obtained with the CNN-LSTM method. Wind power is readily available and straightforward to acquire globally, indicating its potential as a reliable and sustainable energy source.

Conference: Artificial Intelligence as a way of Overcoming Visual Disorders: Damages Related to Visual Cortex, Optic Nerves and Eyes [Link]

16th International Conference on Distributed Computing and Artificial Intelligence (DCAI), Ávila (Spain)• June 2019

Blindness is a disability in which the person got interference with the visual system. In this paper, we studied 18 different diseases. Then categorize the different types of damages to the visual system into three categories which are the brain damages, damages to the eyes and the damages occur to the sensory neurons carrying data. Then suggest possible engineering solutions for each one. Using deep neural networks in order to do the almost same process as the brain does, the developed devices that can be replaced by the vision of the eyes, and also making artificial new connections to cover the attenuation of the sensory neurons carrying data from the eyes to the brain. We are looking forward to overcoming this disability using artificial intelligence apart from medical care. However, we are not denying the importance of medical science but suggesting that new engineering technologies can push up the limits and open new doors to the dead ends. In order to make this dream come true, we need to do lots of studies and will face many more challenges. Some of them are listed in this paper.