Paper Title

VIRTUAL ASSISTANT FOR WINDOWS USING PYTHON

Abstract

In this modern era, day to day life became smarter and interlinked with technology. We already know some voice assistance like Google, Siri, etc. Virtual Personal Assistant is one of the most successful results of Artificial Intelligence, which has given a new way for the human to have its work done from a machine. This project gives a brief survey on the methodologies and concepts used in making of a Virtual Personal Assistant and thereby going on to use it in different software applications. Speech Recognition Systems, also known as Automatic Speech Recognition, plays an important role in virtual assistants in order to help user have a conversation with the system. In this project, we are trying to make a Voice based personal assistant which will include the important features that could help in assisting ones\' needs. As the world is mostly being automated, we have heard some of the Virtual Assistants for windows like Alexa, Cortana, etc. Amazon hasn\'t added any features so that Alexa can control or access Windows specifically. Developing a Voice- Based Personal Assistant for Windows OS with the below main features. Opening any application that we installed in the system. Artificial Neural Networks (ANN) to build an interactive assistant.
KEYWORDS : Desktop Assistant, Pesonal Assistant, Voice Assistant, Speech Recognition, Python, Machine Learning, Virtual Assistant, Text to Speech, Speech to Text, Language Processing, Voice Recognition, Artificial Intelligence, Virtual Assistant.

Paper Title

A SMART APPROACH TO ORPHANAGE DONATION MANAGEMENT

Abstract

The growing problem of orphans is a result of urbanization and industrialization. Each orphanage has different needs such as food, clothing, and medicine. While many people want to help, they may not know how to go about it. Our proposed solution is to create a central hub for connecting orphanages and old age homes in need of aid with individuals who are willing to help. Transparency and audit ability in all transactions helps build confidence with stakeholders and funders while also protecting against fraud and unwanted access. Also, the conditions of contribution agreements may be automated and enforced by \"smart contracts\" that is Block chain-based code executables. Like smart contracts may include features like as minimum price levels, automatic contribution verification, and predetermined procedures for money transfers. However, there are many privileged people in any society who are capable of satisfying their needs and some who don’t. In such environments, there are people who are willing to aid (donors) and people who are longing to accept the help (donees). Both parties required a trustworthy platform to facilitate their needs. In this research, the main focus is to analyze the government schools in provincially. Surveys are conducted to analyze data and to aid to arrive at conclusions.
KEYWORDS : Orphanage, Stakeholders, automatic contribution, donors, \"Smart contracts\", Block chain, Analyze data.

Paper Title

MACHINE LEARNING MODELS FOR TIMELY DEPRESSION DETECTION IN SOCIAL MEDIA

Abstract

Depression is one of the leading causes of suicide worldwide. However, a large percentage of cases of depression go undiagnosed and, thus, untreated. Previous studies have found that messages posted by individuals with major depressive disorder on social media platforms can be analyzed to predict if they are suffering, or likely to suffer, from depression. With a growth in the use of the social media, we have witnessed a positive connection between the demonstration of Suicidal ideation on social networking sites (such as Twitter) and the suicidal cases. One of the most admired and extensively used online social network sites is Twitter. Twitter becomes the mean where every individual can share their emotions whether the emotions are positive negative or neutral. The aim of this study is to design a model for individuals that run the higher risk of committing suicide. This study aims to determine whether machine learning could be effectively used to detect signs of depression in social media users by analyzing their social media posts—especially when those messages do not explicitly contain specific keywords such as ‘depression’ or ‘diagnosis’. To this end, we investigate several text preprocessing and textual-based featuring methods along with machine learning classifiers, including single and ensemble models, to propose a generalized approach for depression detection using social media texts.
KEYWORDS : machine learning, social media platforms, social network, committing suicide, social media texts