We present a highly effective algorithm for image dehazing that leverages the valuable information within the hazy image to guide the haze removal process. Our proposed algorithm begins by employing a neural network that has been trained to establish a mapping between hazy images and their corresponding clear versions. This network learns to identify the shared structural elements and patterns between hazy and clear images through the training process. To enhance the utilization of guidance information from the generated reference image, we introduce a progressive feature fusion module that combines the features extracted from the hazy image and the reference image. Our proposed algorithm is an effective solution for image dehazing, as it capitalizes on the guidance information in the hazy appearance. By combining the strengths of deep learning, progressive feature fusion, and end-to-end training, we achieve impressive results in restoring clear images from hazy counterparts. The practical applicability of our algorithm is further validated by its success on benchmark data sets and real-world SEM and TEM images.

This research paper explores the performance of electrorheological fluids, widely known as smart fluids, which are popular because they experience immediate changes in their characteristics when applied to exterior magnetic or electric field. On application of high voltage, the ER fluid alters its form to semisolid from viscous liquid within a few milliseconds, which is reversible. The reversible nature of ER fluid was employed to absorb vibrations during hard machining. In this research, the consequence of the application of electric field to the ER characteristics of numerous non‐Newtonian fluids with an accumulation of TiO₂ and Al₂O₃ nano elements are investigated. The purpose of this research is to discover the ER sample, which has the highest viscosity, highest breakdown voltage, but less sedimentation. So the selected sample can be used in ER dampers for the purpose of shock absorption. The ER fluid behaves as a mainspring with nonlinear vibration features that are managed by an arrangement of ER fluid, the structure of plunger, and the constraints of applied electric field. In this research, we have employed steel metallic specimens made from EN24T of 302BHN and the machining experiments are conducted to attain the shape parameters that can reduce the tool vibration and help improve the process of cutting at the time of machining with minimum application of fluid utilizing hard metal inserts. In this work, cutting tool parameters were analyzed like cutting force, tool wear, tool vibration amplitude, and surface roughness. It was observed that ER damper has shown its better performance at 5KV. At 5KV, cutting force was the least, tool wear was the least, tool vibration amplitude was the least, and surface roughness was the least. The use of an ER fluid damper decreases tool vibrations and successfully enhances machining performance. The machining industry will be benefited with commercialization of this technique.