Please use this identifier to cite or link to this item:
Title: Cognitive companion for elderly
Authors: Tay, Han Yi
Keywords: Engineering::Computer science and engineering::Computer applications::Life and medical sciences
Issue Date: 2020
Publisher: Nanyang Technological University
Project: SCSE 19-0548
Abstract: The world today is fraught with many problems – climate change, food and water security and lack of employment to name a few. Another such issue is the rapid increase of the aging population. The process of aging is natural, but it also brings about the declination of various faculties of the body. Elderly tend to experience less agility in their bodies, resulting in slower movements in their limbs. They might also struggle with the deterioration of their cognitive functions which can lead to other issues such as dementia and depression. Dementia, being the slowing down of ability to process, can be mitigated by mitigated using therapy that engages the cognitive abilities of mental calculation, decision making and learning capabilities. One such researched therapy is called the Individual Cognitive Stimulating Therapy (ICST). Therapy should be easily available to those who need it. Therefore, this project aims to deliver ICST to elderly with dementia via a chatbot. In order to mimic a person conducting the therapy session with the elderly, the chatbot will be imbued with human-like characteristics. These characteristics have been defined as the self-awareness aspects of a conversational agent. Through this project, a chatbot has been designed with considerations done based on researching on other intelligent agents, literary readings on self-awareness and readings about the therapy. This project has produced a system architecture design, conversation algorithm flow, database design and a chatbot platform for users to interact with. In this project, issues and challenges faced were having to implement a memory model and chatbot from scratch with no prior reference code. Other challenges include getting users to develop attachment to the chatbot, engaging the users with an active and natural conversation, having to mimic a human like conversation. This project is completed using Python 3 for the conversation algorithm, MongoDB for the two databases, Wit Ai as the natural language processing framework and Django to create the website platform. The basic chatbot created can be used as a steppingstone for the next project to improve on and create a more complete and user friendly chatbot.
Schools: School of Computer Science and Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
3.26 MBAdobe PDFView/Open

Page view(s)

Updated on Jul 14, 2024

Download(s) 50

Updated on Jul 14, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.