Computer vision technologies have greatly improved in the last few years. Many problems have been solved using deep learning merged with more computational power. Action recognition is one of society's problems that must be addressed. Human Action Recognition (HAR) may be adopted for intelligent video surveillance systems, and the government may use the same for monitoring crimes and security purposes. This paper proposes a deep learning-based HAR model, i.e., a 3-dimensional Convolutional Network with multiplicative LSTM. The suggested model makes it easier to comprehend the tasks that an individual or team of individuals completes. The four-phase proposed model consists of a 3D Convolutional neural network (3DCNN) combined with an LSTM multiplicative recurrent network and Yolov6 for real-time object detection. The four stages of the proposed model are data fusion, feature extraction, object identification, and skeleton articulation approaches. The NTU-RGB-D, KITTI, NTU-RGB-D 120, UCF 101, and Fused datasets are some used to train the model. The suggested model surpasses other cutting-edge models by reaching an accuracy of 98.23%, 97.65%, 98.76%, 95.45%, and 97.65% on the abovementioned datasets. Other state-of-the-art (SOTA) methods compared in this study are traditional CNN, Yolov6, and CNN with BiLSTM. The results verify that actions are classified more accurately by the proposed model that combines all these techniques compared to existing ones.
Automatic detection of a medical disease is a need of the hour as it helps doctors diagnose diseases and provide fast medical reports. COVID-19 is a deadly disease for which an automated detection system may be helpful. This study proposes a unique hybrid deep learning model, COVIDet, based on CNN and the speeded-up robust features (SURF) extraction approach to diagnose COVID-19 using chest x-ray images. SURF is utilized in this work to extract features, and the output is then transferred to a 25-layer CNN for detection using the extracted features. This investigation employed 4623 COVID-19 positive X-ray pictures or 8055 total. The suggested hybrid model also contrasts with the study's VGG19, Resnet50, Inception, Xception, and traditional CNN models. The proposed model had a 98.01% accuracy, a 97.03% F1-score, a 98.65% sensitivity, a 99% precision, and a 95.65% specificity. The proposed model can be further improved when more datasets are available and can help doctors to diagnose patients quickly and efficiently. Using chest X-ray pictures, a secured web application is also developed to identify COVID-19. The user sends the application a chest X-ray image, and in return, it determines whether an individual is COVID-19 positive or not, cutting down on testing time. In Covid times, when people are standing in long queues and waiting for their turns, this application would greatly help. The application uses the pre-trained COVIDet model in the backend.
The transport system manages traffic between cities worldwide. In addition to cities, highways and other locations can also experience traffic congestion. The area’s existing transportation system is unsatisfactory without supervision. The constraints of the present traffic monitoring system in collecting road data and expanding its visual range are improved by using remote sensing data to identify congestion. Since some remote sensing data must be kept private, this issue must be resolved to safeguard the security of remote sensing data while deep learning training is underway. In contrast to the traditional deep learning training method, this work provides a federated learning methodology to detect automobile objects in remote sensing pictures, addressing the data privacy problem in the training stage of remote sensing data. This study uses a finetuned YOLOv6 model to detect different vehicles along with federated learning. This experiment uses real-time remote sensing data as training samples. The training results reach an accuracy of roughly 95.89%, and the estimated processing time is as short as 0.047 s. A method that effectively controls traffic and improves the passing-vehicle ratio at the intersection is also introduced. Using a mathematical process, the dependence of fuel use on trip time and fuel consumption is also determined, which helps reduce vehicle idle time and fuel consumption. To detect congestion, the system will automatically recognize automobiles as objects in a traffic scenario based on the final experimental findings.