3830 research outputs found
Sort by
Innovative mobile application, Weather Wear: Where wardrobe meets the weather conditions.
No full textThe "Weather Wear" application represents a groundbreaking fusion of real-time weather forecasting and digital wardrobe management. This innovative app utilises cutting-edge technologies such as Expo, React JS, and Firebase, alongside a complimentary Weather API, to deliver a user-centric and intuitive experience. Key features include an organised digital wardrobe, tailored clothing recommendations based on current weather conditions, and an easy-to-use UI. The report describes the development process, technological infrastructure, and the app's unique features. It focuses on the app's cross-platform interoperability and smart algorithm for outfit recommendation. Future improvements, such as geolocation capabilities, configurable user profiles, and a social networking component, are being discussed. The application uniquely addresses the everyday challenge of selecting suitable attire in fluctuating weather scenarios, exemplifying a creative merger of technology and daily life conveniences
The effects of Neobanks on the Irish consumer and barriers to adoption
No full textThe impact felt because of Ulster Bank’s and KBC withdrawal from the Irish market has left nearly a million Irish customers looking for a new bank and switching their accounts. With fewer options in the market, Irish consumer choice has been further constrained and limited to essentially the two pillar banks. On the face of things, the impending departures would appear to consolidate AIB, BOI and Permanent TSB’s position. Though the trajectory of banking in Ireland is changing, high street banks disappearing from streets in towns, akin to the dot com bubble, neo banks such as Revolut have increased in popularity and are expected to soar in signups, especially amongst the younger generations and are portraying themselves as the future of financial services, with cutting edge digital solutions. Traditional banks are confronting a powerful competitor in the rapid changing world of finance. The shift from traditional banks to neo banks from physical locations to app-based banking has perhaps been advantageous to the younger generation but may be argued it has put the older generation at a disadvantage and hence where the barriers to adoption piece is systemically important to explore. Recent research has uncovered several technology risks and challenges impacting the adoption of technology by the elderly. Approximately 32% of the elderly reported a lack of ICT knowledge as a reason for not using the internet. Additionally, some elderly clients reported that web-based electronic banking is not user-friendly. As a result, technology design should undoubtedly be modified further to accommodate the needs of
elderly users.
An air of superstition and hesitation to change amongst consumers is still seen in the market with neo banks particularly amongst the older cohort, with mounting concerns of neobanks being more susceptible to online fraud and use by criminals to launder money being highlighted by media in recent times. Announcements from key players like Revolut publicly admitting to the discovery of criminal money laundering activity, critiques of their automated compliance
were quick to cite for lack of regulation. The above sets the landscape to review the effects neo banks have on the Irish consumer and potential barriers to adoption. This study employs a quantitative research approach and is underpinned by a review of literature on the topic and research conducted through survey analysis to get to the core of the subject matter and to answer the primary research question. The research uncovered a fragmented market with the 50+ year olds reluctant to utilise the services of neo banks due to technology barriers, where loyalty to traditional banks exists, along with concerns of safety and regulation. The 18+ age cohort are embracing neo banks due to greater flexibility for payments and a view of the pillar banks being antiquated which may be a theme derived from the fall of the so-called Celtic Tiger economy and relaxed regulations and speculative investments. The findings showed a changing and evolving banking system and highlighted the barriers to adoption between age populations and how further work must be carried out by neo banks to not silo certain age groups if further market share is to be gained.
In conclusion the research acts as a barometer for appetite for neo banks in Ireland and indications of future trends which showcases these banks as versatile and playing a role in shaping Irelands banking future
Enhancing Early Detection of Heart Disease through Machine Learning: Accuracy, Challenges, and Implications for Healthcare
No full textHeart diseases are common in patients these days and heart disease are among the leading causes of deaths globally. By tracking the various health parameters, it is possible that the heart disease among patients can be detected earlier. This research is focused on use of machine learning techniques to predict heart disease at an early stage, using comprehensive dataset that includes health parameters. This research is conducted and completed by using the CRISP-DM framework that encompasses phase from business understanding to deployment of models.
The dataset used in this study comprise of 14 attributes demonstrating the different health features of patients related to heart health. Some of the attributes are resting blood pressure,
chest pain type, maximum heart rate, age, cholesterol level etc. This report includes the initial exploration of the dataset following the EDA approaches to better understand the data. The data imbalance issue is handled by implementing the SMOTE technique. There are total of five ML models have been created for detection of the heart disease. These models are logistic regression, SVM, KNN, Random Forest and ensemble model.
For the evaluation of the constructed model, common performance metrics such as accuracy, precision, recall, F1-Score and AUC score have been used. All the models are fine-tuned by using the GridSearchCV to maximize their capability and performance. After evaluation, it is found that the most effective and efficient model for prediction of the heart disease is the ensemble model with an overall accuracy of 87.91%. This model is also reliable as the recall of this model is 93.33%
Design and implementation of diabetes detection model using machine learning
No full textThis work introduces a diabetes prediction machine learning model creation and application process. This work focuses on the performance of machine learning models in predicting the risk of diabetes in individuals and identifying the most relevant factors associated with diabetes using the 2015 Behavioral Risk Factor Surveillance System (BRFSS) dataset, which comprises a strong sample of 253,860 individuals and 21 health-related features. Two primary models—a Support Vector Machine (SVM) and an Artificial Neural Network (ANN)—as well as K-Nearest Neighbors (KNN), Logistic Regression, XGBoost—were also built for comparative study between aforementioned models. Handling missing variables and oversampling to solve class imbalance were part of the steps for training these models. The project sought to evaluate these models' diabetes prediction ability by means of accuracy, precision, recall, F1-score analysis, so establishing their efficacy. Emphasizing the need of variable analysis in improving model accuracy, the results support the continuous study in predictive analytics for treatment of chronic diseases
Comparative analysis between the implementation of agile project management and critical chain project management in the cyber security sector of the IT industry.
No full textThis study focuses on assessing and comparing agile project management and critical chain project management contributions within the cybersecurity sector in the IT industry. To gather a valuable and deeper understanding of this topic, its research aims, objectives and research questions are selected that help in providing a clear path for the investigation. The significance of the research is not just related to obtaining the impacts of both of the approaches but also associated with the contribution to the implementation in the industry by the organisation.
The incorporation of relevant literature on the effectiveness, benefits and implementation challenges of agile and critical chain project management have been broadly evaluated within the empirical findings. To gather in-depth information related to the implementation of both approaches in the cybersecurity sector in the IT industry, some relevant literature sources are analysed. After analysing literature sources, few best practices, success factors and crucial considerations within the implementation of both approaches were highlighted. The primary research is the methodology used for completing this study and obtaining valuable information. The positivist research philosophy, descriptive research method, inductive research design, interview, and thematic analysis are the processes that follows to collect the relevant data related to the research topic and analysis of collected data for discussion. Following this method helps in gathering real-world data from the industry’s professionals and makes the work more reliable and appropriate.
The chapters focus on providing relevant information taken from the transcript of the interview session conducted to understand more about the research topic, bringing about relevant information directly connected to agile project management and critical chain project management. The generation of various themes is done with the help of the thematic analysis technique, which further provides significant information, ideas and patterns associated with the data collected providing relevant information about the entire research topic. The discussion part of the assignment provides deeper knowledge related to the findings obtained from the primary research. After analysing the findings, it is noticed that agile project management and critical chain project management are the two popular approaches that are used in the IT industry including the cybersecurity industry. Investigating the capability of the approaches and usage process in projects, it is noticed that several strengths, limitations and best practices are related to mitigating the challenges faced while implementing these practices in the organisations. The discussion part also helps in identifying the strength of the study and the limitations that reflect the potentiality of the research in this domain. After analysing the overall discussion, within the conclusion part, it is summarised that both of the approaches are useful in the context of the cybersecurity sector in the IT industry. Some recommendations are suggested for the study that has the capability to improve the effectiveness of the study
Investigate the impact of Industry 4.0 (IoT) and cloud computing on automated manufacturing system in the Irish pharmaceutical industry
No full textThis study investigates the impact of Industry 4.0, focusing on IoT and cloud computing, in the Irish pharmaceutical industry. Its objectives include assessing adoption levels, identifying integration challenges, and proposing enhancement strategies tailored to the sector. Findings from a quantitative research approach involving 77 participants reveal a mean adoption score of 4.0606 for Industry 4.0 technologies, with significant progress noted. Challenges such as technical complexities, regulatory constraints, and organizational resistance are identified, alongside opportunities for real-time monitoring. Enhancement strategies include workforce upskilling, technology collaboration, regulatory advocacy, and change management. The study's sample size ranges between 70-90 professionals, employing SPSS for analysis with an emphasis on descriptive and inferential statistics. Results underscore positive correlations between adoption and proposing strategies, challenges and opportunities, and organizational change. Regression analysis confirms the significant positive effect of proposing strategies on adoption (β = 0.348, p = 0.026), highlighting their influence in facilitating the Irish pharmaceutical industry's transition to Industry 4.0
Impact of interpersonal trust on employee loyalty in UK business divisions
No full textThe research considers how interpersonal trust has an impact on employee loyalty in the UK business divisions. The factors such as communication methods, leadership styles, recognition processes, organizational structure, team dynamics, and organizational transparency are under scrutiny for how they affect this relationship. A descriptive approach and quantitative research methods will be employed to determine the underlying mechanisms that link trust and loyalty. Surveys are carried out among workers aged 25-60 from several industries to devise the background for the research. The results show that the higher the interpersonal trust level, the greater the employee loyalty, but this relationship can be moderated by job satisfaction and organizational culture. Advice comprises of creating communication channels, adopting transformational leadership, developing fair recognition systems, promoting team collaboration and transparent policy which will in result enhance employees trust in the organization with the conviction to contribute to best organizational performance
Exploring Unconventional Strategies for Enhancing Business Performance
No full textThe article delves into the significant role that real-time data plays in quality control, with a particular focus on the utilization of machine learning to enhance manufacturing outcomes. Through a thorough examination, it evaluates both the advantages and difficulties associated with harnessing real-time data, analyses the potential for machine learning to optimize Quality Control and Project Management procedures and the accuracy results of 5 different machine learning models. In doing so, it emphasises the value of real-time data in aiding Quality Managers and Project Managers in making well-informed decisions and increasing project success rates. Moreover, the article explores the integration of machine learning techniques to leverage current data and outlines the potential benefits and challenges that come with this approach. By providing insight into how project managers can effectively utilize machine learning, the article offers valuable guidance for enhancing project performance and achieving better overall results
Teacher gender bias in the recognition of ADHD symptoms: a study with Irish teachers
Full text linkThis study endeavoured to investigate levels of gender bias among Irish teachers in the recognition of ADHD symptoms. Four potential influencing factors on levels of gender bias were also explored. These factors included: teacher knowledge of ADHD, teacher self-efficacy, experience teaching students with ADHD and participation in continuous professional development about ADHD. For this quantitative study, a cross-sectional, non-manipulative approach was taken, with participating teachers (n=100) engaging with an anonymous online questionnaire. The results indicated that there were significant levels of gender bias among participants towards the recognition of ADHD symptoms in boys. Significant negative relationships were also recorded between gender bias and teacher knowledge of ADHD, gender bias and teacher self-efficacy and gender bias and participation in continuous professional development about ADHD. These findings provide support for previous research carried out in the field, as well as the emerging picture of the under diagnosis of girls with ADHD in Ireland
Speech Emotion Recognition Using Deep Learning
No full textThis study delves into the realm of emotion recognition in speech, employing advanced deep learning techniques to analyse and categorize emotions from audio data. The primary dataset used is Crema, a comprehensive collection of vocal expressions representing various emotions. The research involves preprocessing the audio data and extracting meaningful features, particularly Mel-Frequency Cepstral Coefficients (MFCCs) alongside x-vectors, which are crucial in understanding the tonal aspects of the speech. The processed data is then fed into two different neural network models: a Recurrent Neural Network (RNN) with SimpleRNN layers and a Long Short-Term Memory (LSTM) network. These models are trained and validated on the dataset to classify emotions into categories such as neutral, happy, sad, angry, fear, and disgust. The performance of these models is evaluated based on metrics like accuracy and F1 score. Results indicate a significant potential of deep learning in effectively recognizing and categorizing emotions in speech, though challenges in accuracy and model optimization persist. Keywords: Emotion Recognition, Speech Processing, Deep Learning, Neural Networks, MFCC, RNN, LSTM, Audio Data Analysis