Cervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision techniques can be explored to identify potential precancerous and cancerous lesions by analyzing the Pap smear image. The majority of existing work cover binary classification approaches using various classifiers and Convolution Neural Networks. However, they suffer from inherent challenges for minute feature extraction and precise classification. We propose a novel methodology to carry out the multiclass classification of cervical cells from Whole Slide Images (WSI) with optimum feature extraction. The actualization of Conv Net with Transfer Learning technique substantiates meaningful Metamorphic Diagnosis of neoplastic and pre-neoplastic lesions. As the Progressive Resizing technique (an advanced method for training ConvNet) incorporates prior knowledge of the feature hierarchy and can reuse old computations while learning new ones, the model can carry forward the extracted morphological cell features to subsequent Neural Network layers iteratively for elusive learning. The Progressive Resizing technique superimposition in consultation with the Transfer Learning technique while training the Conv Net models has shown a substantial performance increase. The proposed binary and multiclass classification methodology succored in achieving benchmark scores on the Herlev Dataset. We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%), which supersede the scores obtained through principal methodologies. GradCam based feature interpretation extends enhanced assimilation of the generated results, highlighting the pre-malignant and malignant lesions by visual localization in the images.

Unsupervised domain adaptation (UDA) is a transfer learning technique utilized in deep learning. UDA aims to reduce the distribution gap between labeled source and unlabeled target domains by adapting a model through fine-tuning. Typically, UDA approaches assume the same categories in both domains. The effectiveness of transfer learning depends on the degree of similarity between the domains, which determines an efficient fine-tuning strategy. Furthermore, domain-specific tasks generally perform well when the feature distributions of the domains are similar. However, utilizing a trained source model directly in the target domain may not generalize effectively due to domain shift. Domain shift can be caused by intra-class variations, camera sensor variations, background variations, and geographical changes. To address these issues, we design an efficient unsupervised domain adaptation network for image classification and object detection that can learn transferable feature representations and reduce the domain shift problem in a unified network. We propose the guided transfer learning approach to select the layers for fine-tuning the model, which enhances feature transferability and utilizes the JS-Divergence to minimize the domain discrepancy between the domains. We evaluate our proposed approaches using multiple benchmark datasets. Our domain adaptive image classification approach achieves 93.2% accuracy on the Office-31 dataset and 75.3% accuracy on the Office-Home dataset. In addition, our domain adaptive object detection approach achieves 51.1% mAP on the Foggy Cityscapes dataset and 72.7% mAP on the Indian Vehicle dataset. We conduct extensive experiments and ablation studies to demonstrate the effectiveness and efficiency of our work. Experimental results also show that our work significantly outperforms the existing methods.

The traffic congestion and the rise in the number of vehicles have become a grievous issue, and it is focused worldwide. One of the issues with traffic management is that the traffic light’s timer is not dynamic. As a result, one has to remain longer even if there are no or fewer vehicles, on a roadway, causing unnecessary waiting time, fuel consumption and leads to pollution. Prior work on smart traffic management systems repurposes the use of Internet of things, Time Series Forecasting, and Digital Image Processing. Computer Vision-based smart traffic management is an emerging area of research. Therefore a real-time traffic light optimization algorithm that uses Machine Learning and Deep Learning Techniques to predict the optimal time required by the vehicles to clear the lane is presented. This article concentrates on a two-step approach. The first step is to obtain the count of the independent category of the class of vehicles. For this, the You Only Look Once version 4 (YOLOv4) object detection technique is employed. In the second step, an ensemble technique named eXtreme Gradient Boosting (XGBoost) for predicting the optimal time of the green light window is implemented. Furthermore, the different implemented versions of YOLO and different prediction algorithms are compared with the proposed approach. The experimental analysis signifies that YOLOv4 with the XGBoost algorithm produces the most precise outcomes with a balance of accuracy and inference time. The proposed approach elegantly reduces an average of 32.3% of waiting time with usual traffic on the road.