Individuals generally try not to purchase apparel online chiefly on the grounds that it’s difficult to decide regardless of whether it will look great on them. We chose to construct a cloth try-on system, to tackle this issue. In our web application the users can try most of the upper body clothes provided by them in real-time and it will resize according to the user’s body structure. The user can provide an image of cloth from any shopping website. The cloth is extracted from the image and it’s then sent for real-time try-on. This project is implemented using Flask and OpenCV.

Convolutional Neural Networks (CNN’s) are widely being used for various image processing applications such as denoising, classification, de-hazing and super-resolution. In this paper, CNN image classifier to classify the digits is designed with the convolutional units, batch normalization units and the rectified linear units. The classification accuracy variation by changing different CNN parameters such as learning rate, convolutional filters, convolutional layers and training images is being analyzed. The accuracy saturates or degrades with the increment in number of convolutional layers. Selection of number of filters and learning rate are important hyper parameters impacting classifier accuracy.

Over the years, many researchers have sought to use Deep Learning techniques to detect the malaria-infected cells in blood sample images. Although extremely dangerous, the spread of malaria can be restricted when treated in the early stages. This serves as an impetus for implementing an accurate solution for the detection of malaria that can replace the traditional manual process. The manual process consists of visually examining the blood samples and counting the parasitized and non-parasitized red blood cells. This process is extremely time-consuming, requires the presence of trained medical personnel, and is susceptible to human errors. With these aspects in mind, we aimed to develop a solution that could be used by medical staff with minimal training, thereby saving on time and labour. Having studied various research papers related to the use of Deep Learning techniques for the detection of malaria, we have proposed a model that addresses the gaps we identified in these systems while not compromising on the accuracy of the results. Our proposed model comprises a pre-processing module, the frozen Encoder of an Autoencoder model, a few dense CNN layers, and the classifier (Softmax).

The LLC resonant converters are widely used in various sectors of the electronics-based industries due to their advantages of high efficiency, high energy density, electrical isolation, low electromagnetic interference (EMI),wide output ranges and high operation frequency. A Good power factor for the LLC resonant tank is required to achieve high efficiency over a wide input voltage range. A unity voltage gain can be accomplished over the whole loading conditions by having switching frequency equal to resonant tank frequency in LLC converter, however it is not suited for constant current – constant voltage (CC-CV) battery applications. The use of a buck converter at the output of an LLC resonant converter to regulate the charging current and voltage for battery charging applications is proposed in this paper. The use of a buck converter allows the output voltage of the LLC converter to be varied, ensuring CCCV charging. The proposed system is analyzed and studied in MATLAB/Simulink.

The increase in demand of electricity consumption and concerns towards environmental issues has led the concept of hybrid renewable energy microgrids to meet both the needs simultaneously. Therefore, in this paper, the study and simulation of such microgrid is carried out along with consideration of the net present cost, capital expenditure, operating expenditure, annual energy cost and the emission of carbon dioxide of the system. For this purpose, the site and load profile of an institute is considered located in New Delhi. The optimization is carried out using HOMER PRO software. The most suitable system topology is considered which is able to meet the set objective function in paper. Sensitivity analysis is also performed on the proposed system. Furthermore, the proposed system configuration i.e., solar PV-battery microgrid is compared to traditional grid-only supply system.

Most banking sectors and government entities depend on a centralised mechanism to perform various operations. This mechanism is often slow, inefficient, and unreliable. The Government levies Goods and Service Tax (GST) on the supply of goods and services. GST is a complex multistage indirect tax law applied from manufacturing to the end-user. The current GST implementation has a few loopholes where a seller can easily evade tax payments. Similarly, a Letter of Credit (LC) is a trade process mediated by banking partners. This process is often manual for sharing and validating documents between traders with or within countries for commerce. This paper explores the possibility of implementing GST and LC processes using blockchain technology and aims to address some of the issues faced in the current system. This paper proposes a decentralised application (DApp) to ease the operation logic of GST or e-way bills using smart contracts. The paper also explores a decentralised finance (DeFi) system using blockchain technology to simplify the LC process. This paper also discusses the implementation of the proposed smart contracts on a private blockchain network.

It has always been difficult for a visually impaired individual to navigate around without assistance. Even for them, a constant need arises of having all the relevant functions bundled up together in an application for their ease. Hence, the objective of this paper focuses on providing a multipurpose android application for the visually impaired to aid them via an intelligent and convenient, handheld device i.e smartphone. This app is an integration of several technologies, which starts with a key function - object detection to detect the presence of objects around the user concurrently communicating them through the device speaker/headphone.It further implements Speech recognition and synthesis, TexttoSpeech conversion and alerting the user and their relations when the device battery is low.

In this paper design and implementation of a textile patch antenna will be discuss for military application. The antennas used for military application must be light weight and are needed to work in rough environments surroundings such as rain, heat, snow etc. The antenna design should be thin, lightweight, low cost of maintenance, easily integration into garments and its performance should not get affect by any activity of wearer. Operating frequency of antenna is 2.4 GHz which lies in ISM frequency band. Substrate material used is Jeans fabric with dielectric constant of 1.76 and thickness of substrate is 3mm. Copper is used as conducting material for ground and patch. The antenna is of compact size as compared to calculation based on frequency and dielectric constant. The antenna proposed in this paper is fabricated and results of it are analyzed which are mentioned below. Software used for designing and simulation of antenna is High-Frequency Structure Simulator (HFSS).

The alarming increase in the number of people affected by Obstructive sleep apnea is a point of concern for the medical experts as well as the whole populace. The discontinuous breathing due to upper airway blocking may lead to various cardiovascular and neurological complications such as hypertension and stroke. Polysomnography and manual scanning of ECG signals are time-consuming and expensive techniques. Thus, a need arises for exploring the alternatives to these techniques. The existing literature highlights the efficacy of machine learning and deep learning techniques in the detection of sleep apnea using ECG signals. The comparison of 2-Dimensional and 1-Dimensional convolution neural network-based models stipulate that 2-Dimensional models are better in efficacy, whereas of 1-Dimensional models are more adaptive and compact. Therefore, in this study, the authors looked for a trade-off and designed a novel 1-Dimensional architecture ’1-D Channel Attention Convolution Neural Network’ for the detection of sleep apnea. This compact architecture achieves better accuracy than other 1-Dimensional models with a limited number of parameters. First, it uses the Savitzky-Golay filter for noise suppression, thereafter it uses the smoothened signals for classification. The model utilizes channel attention layers to refine the intermediate feature descriptors before passing them deeper into the network. Thus, simultaneously reducing the need of implementing a deep neural network. The 1-D Channel Attention Convolution Neural Network reports the highest average accuracy of 93.01%, specificity of 93.10%, and sensitivity of 92.93% for sleep apnea detection. The results obtained prove that the proposed model outperforms other state-of-the-art 1-D convolution neural network architectures.

Malware detection models are being built primarily focusing on signature or behavior type detection. In this paper, anti-forensic techniques are used to hide the malware from malware scanners using various approaches and making different changes to the source code of malware to prevent its detection. In this paper I have worked on two models with interchanging payloads and code segments for analysis to check the performance in each case. In this experiment many samples of malware from the recent attacks covering different malware families and intended attack areas have been used to check detection rates as well as new payloads have been created and merged with the existing malware to understand the behavior and combination of the payloads for multi system attacks and calculate the detection rates making the use of VirusTotal to check the detection. The use of different obfuscation techniques which include encoding the payload, code splitting, adding encryption, backdooring the file, Code injection Payload and finally making the use of different steganographic methods to carry the payload to maintain signature evasion have been used as a technique of payload delivery. The technique of manual unpacking has been used in this paper to unpack the malware and deliver the final attack and a framework of automated deployment methods have been laid for further work.