No abstract

The number of abandoned, homeless and poor people have increased drastically in the recent days. Allotting these people to different shelter home is a very difficult task because volunteers in NGO have to do all the work manually and homeless people don’t have valid documentation regarding their Age and Gender. Volunteers usually estimate the person’s Age and Gender on the basis of naked eye estimation but this estimation or prediction sometimes will not be accurate. This problematic situation can be solved by using Deep Learning algorithm like Convolutional Neural Network (CNN). So in our project, we use CNN algorithm to estimate the Age and Gender from the facial image which proves to be a challenging task for a machine due to the high extent of variability, lighting and other supporting conditions. The system proposes building a model which has multiple convolutional layers along with dropout and maxpooling layers in between. The proposed model has been trained on UTKFace dataset and Fairface dataset. The proposed system aims to produce a high accuracy in allotting the right shelter home for people under various Age and Gender. The web application also accepts donations from the users visiting the website who are willing to help the shelter home residents.

The present work deals with end-to-end network performance andjsis and simulation of hierarchical network formed by htmconnection of wireless local area networks (WLANs) by wavelength-division multiplexed (WDM) optical backbone. The proposed architecture employs a NewDistributed-Coordination Function (New-DCF) [3] media access control (MAC) protocol for WLAN. In the case of WDM optical backbone, slotted-ALOHA and ALOHA are considered a s MAC protocols for control and data channels, respectively. In this presentation, the analysis and simulation results reveal that the probability of inter-WLAN communication and number of WLANs have significant impact on the backbone throughput and also on the end-to-end success probability of a packet in the entire network. Moreover, this presentation d e t e r " the number of users in a WLAN as well as number of WLANs can be accommodated for optimum utilization of the backbone for a required M c .

Stock markets serve as a platform where individuals and institutional investors can come together to buy and sell shares in a public venue and ultimately impact the economy. With the advent of digital technology these markets or exchanges exist as electronic marketplaces. These markets are very volatile thus making the stock market prediction a highly challenging problem. These predictions of stock value offer great profits which serve as a huge motivation for extensive research in this area. Identifying and predicting a stock value beforehand by even a fraction of a second can result in very high profits. Similarly, a near to precise prediction can be extremely profitable in the amortized case. This attractiveness of finding a solution has motivated researchers in both industry and academia to devise techniques despite the complications due to volatility, seasonality and time dependency, economy, and other such factors. Lately, AI/ML techniques like Fuzzy Logic and Support Vector Machines (SVMs) have been used to arrive at different solutions. In this paper, we explore and develop an ensemble predictive system to forecast the market prices using deep learning algorithms. Here we consider the fractional change in stock value and the intra-day high and low values of the stock to train and employ a neural network for obtaining the trading strategy that leads to relatively superior market returns. The focus here is on the use of regression and LSTM based deep learning strategies used to predict stock values. Factors considered are open, close, low, high, and volume.