1,721,219 research outputs found
Efficient Computation for Localization and Navigation System for a Differential Drive Mobile Robot in Indoor and Outdoor Environments
No full textPredictive Analytics for City Crime Using Machine Learning
No full textThis study delves into the application of machine learning algorithms to predict urban crime, focusing on the dynamic and complex landscape of Los Angeles. Utilising a comprehensive dataset, the research explores the efficacy of various models like LSTM, GRU, SimpleRNN, Prophet, and XGBoost in predicting crime locations and types. The study aims to transition urban safety strategies from reactive to proactive measures by accurately forecasting crime patterns. The models were evaluated based on RMSE, MAE, and R² scores, with the data split into 80:20 and 70:30 ratios for training and testing. Results indicated that while LSTM, GRU, and XGBoost demonstrated high accuracy in spatial predictions, all models faced challenges in accurately predicting crime types, reflecting the multifaceted nature of criminal behaviour. The study highlights the potential of machine learning in enhancing urban safety but also notes the ethical and practical challenges inherent in predictive policing. It underscores the need for further research, especially in improving crime-type predictions and addressing the ethical implications of such predictive technologies. This research contributes significantly to the field of predictive urban crime analytics, offering insights and pathways for future innovations
Service-oriented chatbot for essential oils using natural language processing
Get PDFThis Master’s thesis focuses on the need for a conversational bot for guiding a layman in the
application of essential oils as a medicine in the healthcare domain. Observing the benefits
of Ayurveda, people nowadays are increasingly using essential oils for treating their medical
conditions and their body has been responding well to it compared to any allopathic
treatment. But there is an issue which needs to be solved, for example, if a person wants
more knowledge about essential oils and starts searching on the web then she/he finds a lot
of non-essential and scattered information. This dissertation here aims at the usage of
essential oils for medicinal purposes. According to the questions asked by the user, the
artifact provides information on essential oils and suggests the use of it. With the help of
NLP, chatbot delivers the users’ application of essential oils and also suggests solutions to
their medical sufferings with these oils. The prototype has a safe and stress-reducing
interface for the user to find information and is liked by 70% of the people. This prototype
also increased the knowledge of 60% of the participants. Duckduckgo API and Tensorflow
are used for the advancement of the chatbot
Risk Assessment of Cardiovascular Diseases Utilizing Individual Lifestyle Factors with Machine Learning Techniques
No full textRevamping restaurant billing system through react JS development
No full textThe restaurant industry is always evolving, aiming to improve the dining experience. Beyond great food and service, smooth and efficient payment processes are crucial. This thesis focuses on restaurant billing systems, highlighting the need for modernization in our digital age. Traditionally, restaurants used manual billing, a slow and error-prone process. With complex menus and various orders, accurate billing was challenging. The solution is a tech upgrade, with this research endorsing the React JavaScript Framework. React, known for speed and user-friendliness, promises to revolutionize restaurant billing. The goal is to eliminate manual billing’s inefficiencies and embrace automation. Introducing React streamlines operations, reducing errors. Automation simplifies bill creation, ensuring precise invoices and custom billing systems using React’s modular approach. Ultimately, this journey aims to improve the customer experience by reducing wait times and billing disputes. This thesis blends real-world data and theoretical insights to explore React’s potential in restaurant billing, emphasizing the importance of technology in enhancing operational efficiency
Worldwide opinion on climate change as measured via Twitter
No full textThe last Intergovernmental Panel on Climate Change (IPCC) in 2014
has concluded that the earth is warming and human influence is the main
cause. This has not led to the meaningful action by nations around the
world to address the impacts from the report. One would assume that
with overwhelming scientific consensus supporting anthropogenic climate
change, the time for debate would be over. Yet public opinion on the topic
remains divided. Twitter provides access to publicly available data where
people express their opinion on a wide variety of topics including climate
change. This dissertation explores the differences in public opinion between
geographic regions around the world, as expressed on twitter, with 10,006
tweets collected over five days in March, 2020. It further explores the theme
of the tweets to understand the variation in topics being discussed under
the climate change umbrella in the different geographies. In addition, this
paper also examines a number of machine learning models using differing
techniques to assess their respective performance in opinion classification.
The trends seen point to where future research should focus to expand on
the results found in this paper
Anti-money laundering detection and customer segmentation
No full textIn this project we going to cover best practices of the anti-money laundering techniques and methods, such a customer segmentation based on suspicious behaviour and fraud detection machine learning algorithms. The goal of the project is to define what payment instrument used for the money laundering the most, so financial institution can reinforce their fraud detection process for this specific payment method and work closely with the bank provider. We going to implement and compare different machine learning classification and clustering algorithms and find out what method is more accurate and suits better for crime detection problem on the specific financial instrument
Machine learning chatbot for education search purpose in Dublin
No full textThis dissertation is about an artificial intelligence chatbot which act as a virtual assistant for the students who are looking for education in Dublin. In real-world scenario a student register in a foreign education agency to pursue education in abroad. Many a time it was observed that the education counsellor could not give adequate amount of time in guiding the student either due to shortage of time or lack of knowledge. Consequently, it becomes a hurdle in admission process and for applying student visa. In order to remove this hurdle the dissertation contribute a conversational bot to assist students regarding education search and information related to any institutions or universities in Dublin. The conversational bot was been developed in Python programming language using machine learning algorithm and natural language processing. According to the participants in user evaluation test the voice feature in bot makes more interactive for communication
The cost and security implications in the adoption of cloud computing services by Irish SMEs
No full textThis research was created with the intention of analysing the interrelationship between cost and security in Cloud Computing for Irish SMEs. The main emphasis is placed on analysing the Multi-perspective framework of cloud computing in relation to companies in Ireland. Five segments have been created to makes the research comprehensive. The first section outlines the core aim and objectives of the research and the significance of the study. The next section illustrates the knowledge obtained by reviewing a vast range of articles and journals. The main challenges and benefits of using Cloud-based services were also discussed in this section. In section three, the methods used in the research have been identified, along with the quantitative and qualitative analyses of the primary data. The fourth section interprets the data collated and analysed. The final section wraps up the project with the discussion and analyses of the findings
Diet analysis of diabetes using machine learning
No full textThe latest advancement in health sciences have prompted a need for creation of data, for example, health treatment information, produced in large volumes of health records. Machine learning techniques seems to be increasing every day, like never before, the motivation behind this work is to change all accessible data into significant data. Diabetes mellitus is a type of metabolic problem, creating an impact on human health around the world and the main cause for this is hereditary. Patients should know how much sugar content present in their meal and what provokes the sugar level. The motive of this thesis is to analyze the data and use machine learning to understand regarding 1) how spicy levels and natural sugars impacted sugar levels 2) how can a food impact sugar levels 3) Comparison of results with different classification algorithms. The best accuracy was obtained from SVM to classify the sugar level present in food
- …
