3830 research outputs found
Sort by
Predicting football match outcomes with ensemble machine learning models
No full textThe study performed here focused on the prediction of the results of football matches using machine learning models. The machine learning models considered in the study were Random Forest (RF), Decision Tree (DT) and the Gradient Boosting classifier and these models were used to build an ensemble model which was the model that performed prediction based on voting. The data associated with football matches was used for training the ensemble model. The best 20 features from the data were selected using the Chi-square technique and the class imbalance in the dataset was solved using Synthetic Minority Oversampling Technique (SMOTE). The results of the study showed that the ensemble model showed an accuracy of 99.5% in predicting the results of football matches. The model was implemented as a desktop application that predicted if the outcome of the football match was a win, lose or draw for the home team
Impact of E-Banking Service Quality on Customer Satisfaction and Loyalty
No full textThis quantitative study explores the impact of E-Banking Service Quality on customer satisfaction and loyalty in the realm of internet banking. With a diverse sample of 120 active electronic banking users, the research aims to evaluate different dimensions of E-Banking Service Quality, measure its influence on customer satisfaction, and investigate its relationship with customer loyalty. The study employs a robust research design, utilizing a quantitative survey strategy with closed-ended questions distributed online. Demographic analysis reveals a balanced representation of gender, a predominant reliance on electronic banking among the 18-35 age group, and diverse occupational and educational backgrounds. Results indicate a significant positive correlation between E-Banking Service Quality, customer satisfaction, and loyalty. Regression analyses highlight the critical roles of user-friendliness and customer support in influencing satisfaction and loyalty. The findings contribute actionable insights for financial institutions to enhance their digital offerings, ensuring competitiveness and building lasting customer relationships in the evolving landscape of digital banking
Competitive and non-competitive behaviours in male and female runners
No full textThis quantitative between groups design study, by means of survey form, examined various aspects of competitiveness and non-competitiveness in running club members, examining gender differences. It assessed if male runners were more competitive than female runners, if competitive male runners have higher affect scores than non-competitive male runners and if competitive female runners have higher affect scores than non-competitive female runners. It also considered if there was a difference between the genders on other aspects of competitiveness, such as goal orientation competitiveness and personal enhancement competitiveness. Participants were (n=184) with roughly an even male/female ratio. Participants were sourced through Irish running clubs. Females were found to be more competitive than their male counterparts, while both genders were found to benefit from positive wellbeing affect when running competitively. Males were found to have lower psychological distress when running non-competitively and increased fatigue when running competitively
Real-time vehicle litter tracking using deep learning: A case study of noTrash.ai 2.0
No full textA city longing to get tagged as smart city should always aim at the health and public safety of the citizens. Every initiative carried out by the city needs to confine itself with a boundary of safety. The boundary of safety can be defined with the aid of the artificial intelligence. In a broad view, clean and hygienic environment can be achieved by tagging the requirements with Machine Learning in every single application criterion. Cleanliness of city streets has an important impact on city environment and public health. Conventional street cleaning methods involve street sweepers going to many spots and manually confirming if the street needs to clean. However, this method takes a substantial amount of manual operations for detection and assessment of street's cleanliness which leads to a high cost for cities. To overcome this vulnerability, Real-Time Vehicle Litter Tracking Using Deep Learning: A Case Study of noTrash.ai 2.0 uses Machine Learning to stop further littering by monitoring the litters thrown from the vehicle and employs cost benefit analysis to showcase the possible profitability of implementing the proposed methodology
Machine learning based prediction model for building energy ratings in Ireland
No full textEnergy can be defined as the driving force behind our modern society. Building energy consumption has emerged as one of the prime contributors to the total energy consumption, due to urbanisation and a colossal increase in the world population. It has been reported that buildings consume 40% of the global energy consumption, and release 38% of Carbon dioxide (CO2). Governments and policymakers are on the lookout for uncovering advanced methods to prepare nations to control climate change and move towards a more sustainable world [1].
Building Energy Ratings have been in the limelight in this regard, as cities have basically turned into blocks of commercial and residential buildings that require energy to fully function. Researchers have proposed the active use of machine learning and technology to support in the agenda. This study has used an official dataset for Irish Building Energy Ratings and emphasises on commissioning the advantages of machine learning to predict energy ratings in Ireland. This study has applied multiclass classification using Logistic Regression, Random Forest Classifier, XGBoost (XGB), Support Vector Classifier and K Nearest Neighbour to train the model to accurately predict building energy ratings. [2]. After the model was applied, it was observed that the Random Forest Classifier and XGBoost were the most efficient models for the purpose of this study. Results from this study can lay a foundation for future studies in the field on building energy ratings in residential and non-residential areas. Energy upgrades have become increasingly common in Ireland and those effected by a better energy certificate have been keen on delving deeper into the possibilities that the Government has offered in this regard.
Incentives and grants are offered to homeowners and landlords for working towards improving the energy ratings of their respective dwellings. The machine learning model implemented in this study can help individuals gauge the energy ratings of their buildings by plugging in the details and features. It would also give individuals a chance to contribute towards sustainability and efficiently utilising scare energy resources of the planet. This would also save time in assessing the Building Energy Ratings (BER) as it is a detailed process and has a number of formalities before a final rating is reached a
Comparative Study of Techniques for Extracting Customer Needs from Hiking Backpack online Reviews
Full text linkIdentifying customer needs has always been a significant factor that contributes to company’s ongoing success (Wang and Ji, 2010, p. 173). However, the traditional ways of identifying customer are expensive and time-consuming in addition to many other problems (Timoshenko and Hauser, 2019, p. 4). This is why there is a new approach to identify customer needs using User Generated Content (UGC) as a source of data (Kühl et al., 2020, p. 2). The main challenge is about vectorizing the data and extracting only the relevant information. In this project, the steps of this new method will be explained using customer reviews of the product “Hiking Backpack” on Amazon, Etsy and Walmart. Also, twenty combinations of different vectorization methods and supervised machine learning classification algorithms will be compared regarding both accuracy and recall scores
Clustering Analysis in Football
No full textNowadays data is everywhere in sport, there are sports like basketball in the US that are famous to be focus on individual statistics. Football has some tendencies to go in the same direction. Statistics are often used to highlight individual performances more than the collective behaviour of a team.
Smith, R. (2022) wrote about the history of how data arrive in football and write this sentence:
“Football has always measured success by what you win, but only in the last twenty years have clubs started to think about how you win”.
With the number of data extracted from each game, there is a possibility to exploit these data in a better way to find patterns regarding the collective behaviour of the teams
Investigating the impact of business analytics on consumer experience and loyalty in the supermarket industry of Ireland
No full textThe goal of this research is to explore the effect of business analytics on the improvement of the customer experience and loyalty in the supermarket industry in Ireland. It indicates that such an analysis helps to individualize the interactions with a particular customer that in turn leads to an increase in customer loyalty and competitiveness. Nevertheless, there are data integration problems, privacy rights concerns, and the need for qualified workers hurdles to a greater extent. Some impediments to success are addressed by the well-established supermarkets by implementing robust technological infrastructure and data-driven culture of decision making. Data generated in this study depends mostly on larger supermarkets that will limit its use to the small retailers. The investigation shows the process-driving capabilities of business analytics for supplier sector that may need to be covered in future research more extensively and qualitativel
Identifying the knowledge gap: implementing sustainable green building materials in Qatar
No full textThis study aims to identify the benefits, barriers, and economic implications of implementing sustainable green building materials in Qatar, highlighting the knowledge gap within the industry. Utilizing a qualitative research approach, data were gathered from 8 participants aged 25-50 years, all of whom had over two years of experience as project managers or employees in the construction sector. Findings reveal that green building materials significantly contribute to environmental sustainability by reducing energy consumption and improving indoor air quality, leading to long-term savings and increased property values. However, barriers such as high initial costs, a lack of clear regulatory guidelines, and a significant knowledge gap limit their adoption. The hypothesis testing confirmed that the knowledge gap significantly impacts the implementation of these materials, thus rejecting the null hypothesis and supporting the alternative hypothesis. The study concludes that bridging this knowledge gap, along with providing clear guidelines, financial incentives, and high-quality materials, is crucial for promoting the adoption of sustainable building practices in Qatar
Attacking and Defending Kubernetes
No full textThe growing adoption of containers and their orchestration in on-premises and cloud systems highlights the urgent security problems (Hill, 2023). Among these options, Kubernetes is the most advanced for implementing containerised workloads when used in conjunction with Docker. This article summarises painstaking process, showing how to set up and configure a local Kubernetes infrastructure using an Ubuntu OS virtual machine. The inclusion of many penetration testing tools, like Burp Suite and Zmap, together with essential open-source scanners like Trivy and Kubescape, strengthens this ecosystem even further. These tools help to highlight security flaws in the Docker container and Kubernetes ecosystem. Two key planes are used by Kubernetes to function: the control plane, which manages the cluster state, and the data plane, which carries out essential tasks. In order to specify the desired cluster state, its structure mostly depends on a variety of elements. In this article, targeted attacks on a Kubernetes cluster (Akula, n.d.) was conducted, which categorise into four main areas: (a) Attacks against the core Kubernetes engine and its components; (b) Kubernetes network layer exploits; (c) Container breaches, which include malicious code injections and vulnerabilities in containers; and (d) Using Infrastructure as Code (IaC) vulnerabilities. Simultaneously, research uses open-source scanners like Trivy, Kubescape, and others to thoroughly examine Docker as well as container images. This all-inclusive method makes it easier to compare security results produced by various scanning programmes. Additionally, analysis explores known attack vectors, such as the OWASP Top 10, ensuring that results are consistentwith the MITRE methodology for methodical issue classification. Together with these investigative steps, a comprehensive set of countermeasures and defences that are suited to each layer that is vulnerable to these threats was provided. Using the knowledge obtained from thorough investigation, this all-encompassing approach aims to strengthen the security architecture of Kubernetes settings