8333 research outputs found
Sort by
Exploring the Effectiveness of Deep Learning Models in Forecasting Commodity Prices: A Case Study on Gold
No full textThis research work presents how efficient deep learning models, such as the Long Short-Term Memory Network (LSTM), have proved in carrying out the forecasting of gold price with high frequency hourly time series data. Compared to other traditional methods, which usually take the input as daily or low resolution data, hourly data may provide finer temporal patterns that will yield more precise predictions.
The key features that will form the basis of the dataset are: Open, High, Low, Close, and Volume. Later, this dataset is augmented further with some external economic indicators like crude oil prices, and volumes to see how this affects the performance of the model. Two models were tested in the experiments: XGBoost is a gradient-boosted decision tree algorithm, while LSTM is a neural network model designed for sequential data. Experiments were conducted in two settings: (1) using the original gold dataset and (2) augmenting the dataset with crude oil features. To have a strict comparison between different models, several metrics such as RMSE, R2, MAE, and sMAPE were adopted. The results prove that LSTM is much better at capturing temporal dependencies and generalises well in all folds, even during volatile market conditions. However, XGBoost has shown variability, especially regarding outliers. The inclusion of crude oil features improved both models, thus confirming the integration of external economic indicators.
This research reveals the potential of high frequency data and deep learning techniques for financial forecasting, thus opening ways for more sophisticated approaches in further studies
Vulnerability Scanner and Reporting Tool: Technical Report
No full textThis report highlights a variety of different aspects to the web application that I have created starting with some expectations and background to the web application such as why I have done this and my reasoning behind it. I will then move onto some of the requirements that are needed to be able to create it following some information about some of the technologies used. Moving on from that you will be presented with a use case of one of the functionalities within the application explaining the process of the task with a result and an alternative example if the user was to make a mistake. Next up you’ll receive a further explained list of requirements such as data requirements, user requirements etc. briefing you on how the application should act. Lastly there is a bit of discussion behind some of the code itself with screenshots and explanations of what certain parts do
Computing Project: Technical Report
No full textThere are two end goals for the project itself. One is to create a game, e.g. something playful, light-hearted and if possible, humorous. The other is to introduce the audience (and me) to some basics of economics, by means of play
The impact of remote work on organizational culture and employee engagement: A case evaluation of Big IT companies of India
No full textAim/Purpose: This research targets to evaluate the influence of remote work on organizational culture and employee engagement within big IT companies in India.
Methodology: Utilizing interpretivism as the research philosophy, this research deploys a mono-qualitative approach, integrating semi-structured interviews and thematic analysis to analyse the complex connection between remote work dynamics, organizational culture, and engagement of employees.
Findings: The findings shows that remote work impacts employee engagement and organizational culture in diverse ways, with elements like communication, work-life balance, and leadership styles playing pivotal roles.
Conclusion and Recommendations: Effective communication channels, initiatives promoting work-life balance, and opportunities for skill enhancement are recommended to foster a favorable or positive remote work culture and optimize employee performance and well-being
Advanced Google Scholar Scraper: A Content-Based Filtering Approach for Literature Recommendation Using BERT
No full textAdvanced Google Scholar Scraper is a complex recommendation system for reading materials. It employs various techniques including web scraping, natural language processing, and content-based filtering. It uses Selenium, Beautiful Soup, and the Hugging Face Transformers library (with a focus on BERT) to make literature referrals more accurate and relevant. The scraper was developed to provide researchers, students, and practitioners with a simple but flexible tool that will allow them to find relevant articles across all fields. Domains include Natural Language Processing (NLP), Machine Learning (ML), and BERT Models. Trying to provide contextually and semantically accurate recommendations, the system is based on BERT embeddings and cosine similarity metrics. An assessment of the scraper verifies its capacity to collect articles from specific domains and offers examples of successful applications for natural language processing methods and web scraping functions. The results show high similarity scores in different fields of research and are timely. The results are that the Advanced Google Scholar Scraper succeeds in getting over these obstacles for dynamic Web scraping, error handling, and user interface design. This is one solution appropriate to all the applications of literature suggestions. The scraper’s adaptability, real-time progress monitoring, and error tolerance make it an extremely useful tool in many research environments
A comprehensive security approach to mitigate Replay and MITM attacks in LoRaWAN protocol
No full textThe development of numerous new Internet of Things (IoT) applications have been made possible by low-power, long range wide-area technology (LoRaWAN), which provides energy and cost-efficient wireless connectivity for large deployments of autonomous sensors. The security of LoRaWAN operating in the license-free frequency band, has received somewhat limited attention and numerous investigations have identified security flaws that makes it susceptible to network attacks such as Replay, Man in the Middle (MiTM) and bit-flipping attack. Current research has identified that LoRaWAN in its present form lacks synchronization between communicating parties, has a vulnerable key management and encryption process. The research has proposed an improvement in the form of dual encryption and time stamp-based synchronization check, which tends to negate these network attacks. This approach neither tampers with the core of the LoRaWAN nor the recommendations of the LoRa Alliance. The approach will lead to enhanced attack detection and mitigation capability of the protocol and make it robust for critical nodes and applications
Evaluate the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) to bridge the gap between security policies and employees in large enterprises
No full textSecurity policies are crucial for establishing the security posture of an enterprise, with significant number of research papers attributing a reduced level of compliance to those enterprises where there is not sufficient dissemination, communication, understanding and clarity of ask.
The factors contributing to a reduced level of compliance are by and large thought to be people problems, rather than technical ones. Despite significant research into these factors, the key challenge which persists is bridging the gap between the security policies of the enterprise and the employees who need to comply with them. The importance of having a securely educated workforce cannot be underestimated. A 2020 research paper from Stanford University found that approximately 88% of all data breaches are caused by employee mistakes, in many cases attributed to a lack of security policy knowledge, with 45% of employees attributing distraction as the top reason for falling for security threats such as phishing. The study went on to conclude that employees report they are primarily focused on the job they have been hired to do, rather than having the time to find, read, understand, and comply with security policies. [1]
An opportunity to bridge this gap requires the simplification of the process for employees to find security policy information and avoid having to read through pages and pages of “security speak” to attempt to decipher an answer to their problem.
This research paper evaluated the potential for the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) to bridge the gap by carrying out a full literature review on both the factors affecting successful security policy adoption, and the state of the art in Chatbots. A technical model for an enterprise specific security policy Chatbot was designed, implemented, and trained on a limited set of ISO27001 policies. The Chatbot: PolicyPal, was also fine tuned during an iterative set of phases to continuously improve the quality and accuracy of the answers provided by the Chatbot. At the end of the fine-tuning phase, the PolicyPal was able to answer 72% of test cases effectively, with the remaining 28% being partially effective
The Role of AI Tools in Promoting Innovation and Creativity in Small Businesses in Nigeria
No full textAI (Artificial Intelligence) is rapidly changing the world and AI technologies continue to advance and permeate various sectors including among small businesses in Nigeria. AI has emerged as a disruptive force, revolutionizing sectors, and transforming the way businesses operate. There has been a growing discourse surrounding the potential negative impact of AI and since AI is an inevitable part of our future, it is crucial to understand its positive impact on entrepreneurial endeavours, especially amongst SMEs (Small and Medium Enterprises), and the potential they hold in driving innovation. This research aims to provide valuable insights into the transformative power of AI in promoting innovation and inspiring creative thinking among small business owners in Nigeria, ultimately offering recommendations for small business owners on harnessing AI’s potential for driving sustainable entrepreneurial growth. Through a comprehensive analysis of existing literature and semi-structured virtual interviews with ten (10) business owners across industries, five (5) prominent themes emerged – (i) idea generation; (ii) alternate and efficient ways to carry out tasks; (iii) improved business operations; (iv) positive impact on decision-making and problem-solving; (v) optimism for the future.
These themes encompass AI’s pivotal role in content creation, idea generation, problem-solving, decision-making, and enhancing productivity among small businesses. These findings are particularly significant in today's competitive landscape, where small businesses strive to maintain their competitive edge and grow
An Investigation into the Role of Remittances in Supporting the Growth of Small and Medium sized Enterprises in Uganda
No full textThis study examines the role that remittances play in the growth of small and medium sized enterprises (SMEs) in Uganda. It also suggests future policies that impact remittances in Uganda.
Purpose: This research investigates the impact of remittances on SMEs’ growth in Uganda, and the relationship that strategic policies and the collaboration between government institutions and financial organizations play in this regard.
Motivation: The contribution of remittances to the economic growth of Uganda and to expound their impact on SMEs. To have policies that target development implemented by the government, to encourage investment and funds inflows. This is because remittances have helped reduce poverty in Uganda, improved the economy by creating more jobs in form of SMEs, and the education of children.
Research Aims/Objectives: To investigate the role that remittances play on SMEs growth in Uganda. The impact that government policies, the role of financial players and other organisations have on the growth of remittances and SMEs in Uganda. To suggest future policies that facilitate the growth of remittances and SMEs in Uganda.
Literature Review: Official documents were used to gather insights on the SMEs’ growth in Uganda. These included academic journals, articles, textbooks, and online sources on the impact of remittances on Uganda and other developing countries in Africa.
Methodology/Design/Approach: The research was done using a qualitative approach, adopting in-depth interviews with four SME owners and three government officials in addition to three key players in telecoms, banks, and charities in Uganda. Data was analysed using thematic coding and random stratification.
Findings and Analysis: It was found that remittances play a crucial role in the economic development of Uganda. Factors that limit remittances growth include, high costs of the transfer fees, illiteracy of recipients, and government policies.
Conclusion: The study confirms that remittances contribute to the growth of SMEs, lead to investments by migrants, and the economic development of Uganda. It is recommended that further studies on the role of government policies in boosting investment and remittances should be done in the future for development to occur in Uganda
Assessment and Applications of Emotional Intelligence: Dublin Retail Managers Case Study
No full textThis study investigates the Emotional Intelligence of Dublin retail managers, by quantitatively assessing it using a psychological research instrument and illuminating its
applications day-to-day in the workplace, and suggestions regarding it to the teams working under them. Building upon the original works by Weschler, Caruso, Salovey, Bradberry, and others, the research delves into the manager’s Emotional intelligence assessment. It also encompasses manager’s perspectives regarding their use and advice concerning Emotional Intelligence.
Acting as a case study, the retail sector of Dublin showing growth and the retail environment demanding Emotional Intelligence, the significance of Emotional Intelligence in managers cannot be understated. This has universal applications.
Drawing on a mixed-model approach, the Quantitative and Qualitative approach is appropriate for this study as it provides a comprehensive approach to the Dublin retail manager’s point of view. Using Trait Meta-Mood Scale 24 and in-depth interview, a sample of 8 managers is gathered to assess managers’ Emotional Intelligence and its applications and recommendations to the teams working with them.
Findings suggest Dublin retail managers are ‘Fairly’ emotionally aware, ‘Fairly to Very’ emotionally clear, and ‘Very to Extremely’ good at emotional repair. The applications range from stress management to nurturing relationships and many more.
The findings of this study are useful to the field of emotional intelligence, especially in the retail industry. It helps bridge the gap between the existing knowledge and the real application of knowledge coming from the people in question. It brings out their lived experiences, their on ground knowledge, and practical know-how to simplify uses of Emotional intelligence. This ensures the fostering of applications in day-to-day work in retail and gives others a point of view of the real experiences and knowledge of retail managers