We applied Deep Learning algorithm known as Generative Adversarial Networks (GANs) to perform sol... more We applied Deep Learning algorithm known as Generative Adversarial Networks (GANs) to perform solar image-to-image translation. That is, from Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager(HMI) line of sight magnetogram images to SDO/Atmospheric Imaging Assembly(AIA) 0304-Å images. The Ultraviolet(UV)/Extreme Ultraviolet(EUV) observations like the SDO/AIA0304-Å images were only made available to scientists in the late 1990s even though the magenetic field observations like the SDO/HMI have been available since the 1970s. Therefore by leveraging Deep Learning algorithms like GANs we can give scientists access to complete datasets for analysis. For generating high resolution solar images we use the Pix2PixHD and Pix2Pix algorithms. The Pix2PixHD algorithm was specifically designed for high resolution image generation tasks, and the Pix2Pix algorithm is by far the most widely used image to image translation algorithm. For training and testing we used the data for the...
In-cylinder combustion behavior of diesel engines has been enigmatic on many accounts for researc... more In-cylinder combustion behavior of diesel engines has been enigmatic on many accounts for researchers, but they are significant harbinger of various performance, durability and emission characteristics. With the advent of biodiesel as an alternative fuel for diesel engines, the interest of comparative combustion study of neat diesel (D100) and biodiesel (B100) operation is gaining attention. In this context, a comprehensive experimental trial was envisaged on an unmodified diesel engine to determine and compare several combustion characteristics when operating on neat diesel and neat biodiesel separately. Biodiesel was prepared from locally available “Calophyllum Inophyllum” vegetable oil using transesterification process. The results at full load indicated that in-cylinder pressure data for 51 consecutive cycles showed the cycle to cycle variability among 51 consecutive cycle to be 2.68 bar at 4 crank angle degrees after TDC for D100 operation and 7.47 bars at 3 crank angle degrees...
The late stage of the free fall of homogeneous and heterogeneous cones in a quiescent water mediu... more The late stage of the free fall of homogeneous and heterogeneous cones in a quiescent water medium and the induced flow are experimentally inspected using three-dimensional particle tracking velocimetry and volumetric particle image velocimetry. The structures shared the same geometry but had different combined specific gravity SG ∈ [1.2, 8]. Results showed four distinct free-fall patterns, which were modulated by the degree of heterogeneity and SG. They included (i) straight fall, (ii) regular sinusoidal-like trajectories with a maximum angle of oscillation with respect to the vertical, θ max < π/2, (iii) motions characterized by inclined translations and large rotations with θ max > π/2, and (iv) tumbling followed by an irregular motion. The straight fall occurred in cones with SG 6 regardless of the mass distribution. The sinusoidal motions arose in the homogeneous cones with SG < 3. The large rotations occurred with heterogeneous cones of SG < 3, whereas the tumbling with irregular motions occurred in the heterogeneous cone with the highest ratio between the center of mass and geometrical centroid. Inspection of the linear and angular components of the velocities and accelerations reveal the distinct patterns and the linkage with the surrounding flow.
We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a n... more We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a number of sectors. GANs combine two neural networks that compete against one another using zero-sum game theory, allowing them to create much crisper and discrete outputs. GANs can be used to perform image processing, video generation and prediction, among other computer vision applications. GANs can also be utilised for a variety of science-related activities, including protein engineering, astronomical data processing, remote sensing image dehazing, and crystal structure synthesis. Other notable fields where GANs have made gains include finance, marketing, fashion design, sports, and music. Therefore in this article we provide a comprehensive overview of the applications of GANs in a wide variety of disciplines. We first cover the theory supporting GAN, GAN variants, and the metrics to evaluate GANs. Then we present how GAN and its variants can be applied in twelve domains, ranging from...
Uploads
Papers by Ankan Dash