Volume 9 | Issue 6 |

 Abstract

Back in 2014, Ian Goodfellow dreamt up the idea of Generative Adversarial Net-works (GANs), since then a lot of work has been done in the field of Automatic facial image generation. There are already some papers regarding the anime character generation using different GAN algorithms with good results but not so efficient. In this work, we explored the StyleGAN2 for training our clean and well-suited data-set and obtained an efficient and promising result.For public convenience, we built a website that will allow users to obtain required anime character by giving few characteristics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Deep Learning, Generative Model, Anime

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The oral route is the most preferred drug administration path because to its ease of administration, convenience, high patient compliance, flexibility in dosage form design, fewer sterility constraints, and cost effectiveness. Lipid emulsions, lipid solutions, micro emulsions, and dry emulsions are examples of lipid drug delivery systems. Artemether (ARM), a poorly water soluble chemical, presents difficulties in developing pharmaceutical formulations with adequate bioavailability. Capmul MCM was used as the oil, Tween 80 as the surfactant, and PEG 400 as the co-surfactant in various ratios to create four self micro-emulsifying formulations. Using an adsorption method, optimised liquid SMEDDS formulations were converted into free-flowing powder and evaluated for drug content, FTIR, DSC, Globule size analysis, SEM, and in-vitro dissolution study. The results show that decreased crystallinity, altered surface morphology, and smaller globules were responsible for a significant increase in drug dissolving rate from the modified S-SMEDDS formulation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artemether, Poor water solubility, Solid self micro-emulsifying Drug delivery system.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project aims to save energy which is wasted because of human irresponsibility and carelessness in using electricity and effectively control electronic devices using a micro controller (Raspberry Pi). The system here detects the presence of human. If any person found then the appliances will remain on and if no person is detected then the appliances gets turned off. This helps in saving electricity. For detecting humans, the camera will continuously capture the frames and then send these frames to the raspberry pi. From raspberry pi the signal will be sent to the appliances and the system will work accordingly. For detecting humans, the system uses haar cascade algorithm.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Internet of Things, Image processing, Object detection, Haar cascade, Artificial intelligence, Computer vision.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Nowadays plant disease is becoming more and more serious in the agriculture, farmers suffer a lot due to the infection, drastic climate changes and lack of immunity in crops and their yield is also affected due to the lack of detection. This causes large scale demolition of crops, decreases cultivation and eventually leads to financial loss of farmers. Due to rapid growth in variety of diseases and adequate knowledge of farmer, identification and treatment of the disease has become a major challenge. The leaves have texture and visual similarities which attributes for identification of disease type. Hence, computer vision employed with deep learning which provides the way to solve this problem. This paper proposes a deep learning-based CNN model which is trained using plant village dataset containing various images of healthy and diseased leaves. The performance of the proposed model is compared with the existing model and result is presented in the section

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Deep learning, Disease detection, Artificial Neural Network, Convolution Neural Network.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Psychological status of the students is the topic of interest through the world. The whole performance of the student depends on his mental health. Till date there is no proven treatment to manage the Novel corona virus disease. As the rate of spread is increasing day by day, lockdown is the only option available to slowdown the rate of spreading the infection. The examinations were postponed due to the lockdown effect and the actual date of exam is awaited. In this context many students were undergoing mental stress and there is a strong need to consider their mental health status. From this study we found that the effect of lockdown very high on students mantle health . But there are less impact on those students who regular associated with online classes. The internet facility is very big problem in villages and few places. Students are unable to join online classes and their stress and depression level is very high.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Image Deblurring, Non-uniform Motion Blur, Generative Adversarial Network, Keras

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CVD, Machine Learning, Deep Learning, ANN, CNN, RNN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Handwritten Digit Recognition (HDR) is the process of converting images of handwritten digit into digital format. A lot of money is wasted on converting the information that is in paper to digital format. This problem can be solved by using HDR. The heart of our project lies within the ability to develop an efficient algorithm that can recognize the handwritten digits which are scanned and sent as input by the user. The goal of this paper is to observe the variation of different algorithms that can classify the handwritten digits using different hidden layers, various number of epochs and to make a comparison based on the accuracy. This experiment is performed using the Modified National Institute of Standards and Technology (MNIST) dataset.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Handwritten Digit Recognition (HDR), Epochs, Hidden Layers, MNIST dataset

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fly Ash, GGBS, Geopolymer concrete, Strength Parameters.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Aggravated Penetrative Sexual Assault, Aggravated Sexual Assault, Sexual Exploitation, Perverse Mind, Gender Neutral, cataclysms

  License

Creative Commons Attribution 4.0 and The Open Definition