Digital Commons Network^™

Neural Networks Activation Functions And Hybrid Activations Functions Accuracy And Loss Comparison On Small Dataset Against Large Datasets For Classification Problems., Antonio Felipe Cora Martins

ICT

Even on the era of Big Data, small datasets are the reality of many companies and sectors. Many datasets in rare disease diagnosis, custom manufacturing, military sciences, bioengineering, and disaster events are commonly limited in size, making machine learning predictive modelling difficult. Being the Activation Function choice crucial for Neural Networks learning, it raises the question of their effectiveness in such scenarios. This study compares five standard (single) activation functions (Sigmoid, Tanh, ReLU, Leaky ReLU, ELU) and two hybrid variants (one a mix of ReLU plus Tanh and a Learnable Activation Function with a trainable weight (alpha) that balances ReLU …

Predicting Early Hospital Readmissions For Diabetic Patients Using Machine Learning, Amanda Ferraz, Leonardo Oliveira

ICT

This project applies machine learning to predict whether diabetic patients will be readmitted to a hospital within 30 days of discharge. Early readmissions are a costly and critical issue in healthcare, often signalling gaps in post-discharge care and risk management. Diabetic patients face unfair high readmission rates compared to the general population. According to the CDC Diabetes Report Card 37.3 million people in the U.S. or 11.3% of the population had diabetes as of 2019 (CDC, 2021). Our goal here is to develop a binary classification model capable of flagging high risk patient (< 30-day readmission) based on their clinical, demographic, and administrative data. This lets healthcare institutions to take measures,

European Air Pollution And The Proposed Timelines Of Implementing The World Health Organization 2021 Air Quality Guidelines Ca3., Lukia Hartin

ICT

This research examines Ireland’s air pollution trends and evaluates whether current reductions in PM2.5, PM10, and NO₂ are sufficient to meet the WHO 2021 Air Quality Guidelines by 2040. Using four years of EPA-validated pollutant data (2020–2023), alongside Building Energy Rating (BER) and national transport datasets, the study applies the CRISP-DM methodology to guide analysis, preprocessing, modelling, and evaluation. Extensive data cleaning and alignment were required due to inconsistent station coverage, varying formats, and missing values. Forecasting models—including Random Forest, Gradient Boosting, SVR, and linear regression—were assessed using MSE, R², and trend significance to project pollutant levels across different Irish …

Analysis Of The Patterns And Features Importance In Predicting Demand For Sustainable Urban Mobility. A Comparative Analysis Of Machine Learning Models Using The Dublin Bikes Dataset., Wojciech Sochanski

ICT

This study explores the application of machine learning models to predict demand in the Dublin bike-sharing scheme. A comprehensive literature review examines prior work on sustainable urban mobility, the evolution of bike-sharing schemes, the application of machine learning in predictive analytics and relevant case studies. Secondary data were gathered from publicly available sources, pre-processed and merged into a single, unified dataset. Exploratory data analysis was conducted before preparing the data for modelling to assess the data quality, with a focus on missing values.

Four predictive machine learning models – Linear Regression (LR), Decision Tree (CART), Random Forest (RF) and Gradient …

Analyse The Mechanical Property Optimization For Fdm/3d-Printed Polycarbonate Using Taguchi And Topsis Techniques, N. Srinivasa Rao, Raman Kumar, N. Kavitha, Ramachandran T., Hari Prasadarao Pydi, Aman Shankhyan, Ram Subbiah, Vikasdeep Singh Mann

Journal of Metals, Materials and Minerals

Fused Deposition Modeling is 3D printing techniques which chiefly appreciated for prototypes. This manufacturing process works by extrusion of thermoplastic materials to make the three-dimensional objects. In this work, we pursued to identify the FDM parameters to increase mechanical properties, specifically ultimate tensile strength (UTS) and compressive strength (CMS). Polycarbonate was chosen to create the test samples because of the best thermal and mechanical properties, which was the increasing manufacturing applications of 3D printing. Nine experiments were conducted to verify the interaction of the considered parameters, namely infill rate (IR), printing speed (PS), and film height (FH). The combined use …

Studies Of Structural, Microstructural, Dielectric, And Electrical Characterization Of Binaznmoo6 Double Perovskite, Swati Panda, Supriya Barik, Ritu Purna Sahu, Adwit Prasad Sahu, S. Mishra, S. K. Parida

Journal of Metals, Materials and Minerals

This study investigates the structural, microstructural, dielectric, and electrical properties of BiNaZnMoO₆ (BNZM) ceramic synthesized using a conventional solid-state reaction method. Preliminary structural analysis using X-ray diffraction (XRD) suggests orthorhombic crystal symmetry. Scanning electron microscopy (SEM) micrographs reveal a uniform distribution of well-grown grains with well-defined grain boundaries, which may contribute to the enhanced dielectric properties. Energy dispersive X-ray spectroscopy (EDX) analysis confirms the presence of all constituent elements Bi, Na, Zn, Mo, and O in the studied sample. Dielectric spectra analysis as a function of frequency and temperature indicates the formation of high-quality dielectric materials, evidenced by a high …

Green-Synthesized Yttrium-Doped Cerium Oxide Nanoparticles: A Promising Optical Material, Sasmita Sarangi, Nibedita Nayak, Binita Nanda, Tapas Sahoo

Journal of Metals, Materials and Minerals

This work focuses on the green synthesis, characterization, and optical properties of yttrium-doped cerium dioxide (CeO2) nanoparticles. A green approach was adopted using Acacia concinna fruit extract as surfactant and stabilizing agent. Their structural, morphological, and physical-chemical properties were characterized using different analytical techniques, like XRD, FE-SEM, FTIR, PL, Raman, UV-Visible Spectroscopy. XRD study validated the structure of cubic fluorite-type structure of CeO2 nanoparticles, with the average crystallite size ranging between 7-15 nm. Raman spectroscopy validated this structure with F2g band observed at 463 cm−1. FESEM images showed irregular spherical morphologies with grain sizes in the range of 50-60 nm. …

Pyrolysis And Modification Of Coconut Shell Into Sulfonated Biochar And Its Catalytic Activity On Cellobiose Conversion, Addy Rachmat, Yessi Eka Wahyu, Poedji Loekitowati Hariani, Fahma Riyanti, Fatma Fatma

Journal of Metals, Materials and Minerals

Coconut shell was successfully valorized into sulfonated biochar through carbonization in various temperatures and duration. This work aims to provide suitable solid acid carbonaceous catalyst for cellobiose conversion into valuable product. Sulfonated biochar is characterized to evaluate its crystallinity, sulfonate, and oxygenated functional groups by XRD method and FTIR spectroscopy. The resulting solid acid carbonaceous material was tested toward cellobiose hydrolysis to assess its catalytic activity in various time, temperature, and catalyst weight. FTIR spectra reveals some of the biochar product has sulfonate group as indicated by absorbance band at 1234 cm‒1, 1070 cm‒1 and 1180 cm‒1, which belongs to …

Macro-Encapsulation Of Polyethylene Glycol And Magnetite (Fe3o4) In Concrete As Phase Change Materials For Building Thermal Management, Muhammad Fauzi, Budhy Kurniawan, Anggito Pringgo Tetuko, Timbangen Sembiring, Fanna Nilam, Amdy Fachredzy, Perdamean Sebayang

Journal of Metals, Materials and Minerals

Thermal management technology is a crucial strategy for reducing energy consumption in buildings by utilizing stored solar energy. This study developed a polyethylene glycol (PEG)-based phase-change material (PCM), selected for its superior physicochemical stability, high latent enthalpy, and environmental compatibility. To enhance thermal conductivity, 20 vol% magnetite (Fe₃O₄) was incorporated into the PEG matrix. The composite was synthesized via an ultrasonic-assisted method (37 kHz, 80°C, 1 h). X-ray diffraction (XRD) confirmed the crystalline structure of PEG and the cubic phase of Fe3O4, while Fourier-transform infrared spectroscopy (FTIR) validated the synthesis by identifying Fe–O, C–H, and O–H functional groups. Scanning electron …

The Effect Of Pt And Pd Decoration On Sno2 Slant Nanorods Fabricated Using Dc Magnetron Sputtering With Oad Technique For Co Gas Sensing Applications, Nampueng Pangpaiboon, Thitiporn Kaewyou, Sethavut Duangchan, Kata Jaruwongrungsee, Manatsawee Srirak, Tossaporn Lertvanithphol, Viyapol Patthanasettakul, Tawee Pogfay, Mati Horprathum, Saksorn Limwichean

Journal of Metals, Materials and Minerals

This research investigates the effect of Pt and Pd decoration on the structure of SnO2 slant nanorods (SNRs) films produced using DC magnetron sputtering with Oblique Angle Deposition (OAD), as well as their impact on the films' physical properties and gas sensing applications. Pt and Pd were deposited onto the SnO2 SNRs for the same duration of 20 s each. Following deposition, all the films were heat-treated temperature at 400℃ for 2 h. The characterization of both as-deposited and annealed films involved analyzing the physical morphology using FE-SEM and the crystal structure using GI-XRD. It was observed that the structure …

Comprehensive Study On The Structural And Optical Properties Of Bismuth Manganese Oxide Composite Ceramic For Optoelectronic Applications, P. P. Nayak, B. Swain, R. R. Patro, S. S. Hota, O. P. Das, S. Bhuyan

Journal of Metals, Materials and Minerals

This work assessed the potential of bismuth manganese oxide composite ceramic for optoelectronic applications by methodically examining its structural, vibrational, and optical characteristics. X-ray diffraction (XRD) spectroscopy provided the coexistence of Bi12MnO20 (sillenite-type) and Bi2Mn4O10 (mullite-type) phases, indicating a deviation from the ideal perovskite structure and suggesting a complex crystallographic nature influencing its functional properties. Fourier transform infrared (FTIR) spectroscopy confirmed the modes of vibration of Bi–O and Mn–O bonds that were contained, supporting the structural composition. UV-Vis-NIR spectroscopy demonstrated strong optical absorption in the 300 nm to 800 nm range, affirming the suitability of the material for optoelectronic applications. …

Dogs Emotion System, Muhammad Anas Baig

ICT

For our capstone project, we built a machine learning model that can look at pictures of dogs and figure out how they’re feeling, like if they’re happy, sad, or just chill. The idea came from how important pets are in people’s lives these days and how cool it would be to actually understand their emotions better using tech. This system will allow users to upload images of dogs, which are then analysed by a trained model to classify the dog's emotional states such as happy, sad, or neutral. We followed the CRISP-DM process to build it, which basically means we …

Optimizing Lstm Neural Network For Multimodal Multivariate Footfall Prediction., Aws Al Adhami

ICT

Accurate forecasting of pedestrian activity is important for smart city planning, retail analytics, and public service management. This study presents a forecasting framework using Long Short-Term Memory (LSTM) neural networks that integrates multiple data sources, including weather, calendar variables, and engineered temporal features. The model development follows a structured pipeline from baseline univariate models to a fully optimized multivariate model using feature engineering and hyperparameter tuning techniques such as Hyperband and Bayesian optimization. The final model achieved a Mean Absolute Error of 24.05 and explained 97.10% of the variance in unseen data, effectively capturing both regular patterns and short-term fluctuations …

Comparative Evaluation Of Ai-Generated Synthetic Data And Real-World Data Performance In Predictive Analytics, Corey Louise Hughes

ICT

There are growing restraints when it comes to Real World Data (RWD), these include topics such as privacy regulations, ethical concerns, and the cost of collecting the data, and they have drove an interest in AI-generated synthetic data as a potential alternative in predictive analytics. This project examines the possibilities of synthetic data and if it can act as a reliable substitute for RWD in predictive modelling. This project uses Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic reproductive health data and evaluates its predictive performance against RWD using linear regression and key metrics, including Mean Absolute …

A Comparative Evaluation Of The Effectiveness Of Mel Frequency Cepstral Coefficients And Difference Files For Audio Effect Identification Using Convolutional Recurrent Neural Networks., Patrick Sneyd

ICT

The field of Music information retrieval (MIR) is concerned with computational systems which help humans better make sense of the processing, searching, organizing, and accessing of music-related data and takes in disciplines such as music theory, computer science, psychology, neuroscience, library science, electrical engineering and machine learning. MIR processes relating to audio classification have applications in fields such as speech recognition, automatic bandwidth allocation and Audio Database Indexing which is especially of relevance to large audio collections in broadcasting facilities, the movie industry or music content providers.

These indexing aspects of MIR have been applied to classifying audio into musical …

Customer Service Support. Utilizing Machine Learning To Classify, Prioritize And Summarize Issues., Hoai Nhan Nguyen

ICT

This capstone project investigates the application of machine learning and natural language processing (NLP) to enhance customer support operations through automated ticket classification, prioritization, and summarization. Using the multilingual Customer Support Emails dataset from Kaggle, the project follows the CRISP-DM methodology, performing extensive data cleaning, preprocessing, feature engineering, and class balancing. Five machine learning models—Decision Tree, KNN, LinearSVC, Naive Bayes, and Random Forest—were evaluated using hyperparameter tuning, cross-validation, confusion matrix analysis, and learning curves. LinearSVC demonstrated the strongest performance for both queue and priority classification, achieving accuracies of 89.8% and 81.2% respectively, with consistent generalization across folds. For summarization, extractive …

Dogs Emotion System- Poster, Muhammad Anas Baig

ICT

This project is all about a deep learning-based “Dog Emotion System” that can figure out how dogs are feeling just by looking at their faces. We used a balanced set of 4,000 dog images with four different emotion categories and followed the CRISP-DM process to build it. The model was trained from scratch using a Convolutional Neural Network (CNN) without any pre-existing models. It is deployed using Steamlit, where people can upload pictures of their dogs and get their emotional state predicted in real time. The goal of this tech is to make it easier for pet owners to understand …

Comparison Of Statistical, Machine Learning, And Deep Learning Models For Time-Series Forecasting Using Weather Data From Dublin, Ireland., Erick Eduardo Rios Treviño

ICT

This study compares three time-series forecasting paradigms—statistical, machine learning, and deep learning—using ten-years of historical weather data from Dublin. The objective is to evaluate the performance of Prophet, XGBoost, and LSTM when forecasting daily solar radiation under multiple preprocessing strategies. An extensive data analysis was conducted, including descriptive statistics, inferential testing, stationarity assessment, outlier detection, feature selection, and exploratory visualisation. These steps revealed strong annual seasonality, nonlinear feature relationships, and variability across meteorological variables, informing the modelling framework and feature-engineering decisions. Four experiments were conducted using cleaned data, differenced data, log-transformed data, and cross-validation. Results show that XGBoost achieved the …

Enhancing Insider Threat Detection Through A Hybrid Approach Using Different Artificial Intelligence Techniques., Jose Roberto Da Silva Dure

ICT

Insider threats pose significant challenges in cybersecurity due to their origin from individuals with legitimate access. Traditional defenses often fail to detect malicious behavior embedded within normal activities. This study proposes a hybrid artificial intelligence framework that integrates unsupervised anomaly detection, supervised and ensemble learning, and deep learning to enhance insider threat detection. Using the CERT 4.1 dataset, features encompassing temporal, behavioral, network, and psychometric aspects were engineered. Anomaly detection models informed supervised and ensemble classifiers, while a multi-input deep learning architecture captured sequential and contextual patterns. Performance evaluation using ROC-AUC, precision, recall, F1-score, and cost-sensitive analysis demonstrates that the …

Time Series Forecasting In Financial Markets: Benchmarking The Temporal Fusion Transformer Against N-Beats., Fergus Fleury

ICT

This study compares the performance of two deep learning architectures, the Temporal Fusion Transformer (TFT) and N-BEATS, for 10-day stock price forecasting. Both models were implemented using the Darts Python library, which ensured consistent preprocessing, training, and evaluation. The dataset, sourced from Yahoo Finance, included daily equity prices, technical indicators, a market sentiment index, and earnings announcements.

TFT was applied as a multivariate model incorporating past, future, and static covariates, while N-BEATS was trained as separate univariate models with past covariates only. A rolling forecast cross-validation approach was used for evaluation. Results show that TFT consistently outperformed N-BEATS, particularly under …

Brain Tumor Classification Using Deep Learning- Poster, Rayen Bentemessek

ICT

The project presents deep learning solutions to classify brain tumors through MRI images. Two Convolutional Neural Network (CNN) models were developed, a custom CNN designed from scratch and a pretrained ResNet50 that was transfer learned and fine-tuned.

Both models were implemented following CRISP-DM methodology from data understanding to deployment, and they were evaluated using different metrics such as accuracy, precision, recall and F1-score.

Key Highlights: •The custom CNN model achieved higher accuracy but failed to locate tumors. •ResNet50 provided a good performance while balancing explainability through Grad-CAM. •Model was deployed through Gradio to demonstrate a real-world use of the solution.

Strategic Analysis Of Employment Permit Statistics And Predictive Analytics For Workforce Planning In Ireland, Amy Souza, Thaynna Vieira

ICT

By analysing historical employment permit data from Enterprise.gov.ie (Enterprise.gov.ie, 2024), this project has the aim to use Data Analytics and Machine Learning to make predictions of employment permits trends across sectors and companies, providing insights to optimize workforce planning for Recruitment Agencies and guide international job seekers requiring work visas. The insights gained are intended to enhance strategic recruitment practices and empower job seekers to make informed career decisions in Ireland’s competitive labour market.

Predicting Repeat Purchases In E-Commerce Using Interpretable Machine Learning, Zahid Bhatti

ICT

This project investigates the prediction of repeat purchase behaviour in e-commerce using machine learning, with a focus on balancing predictive accuracy and interpretability. Large volumes of transactional and behavioural data are analysed to identify customer-level features that drive loyalty and repeat purchases. Various supervised learning models, including Random Forests and Logistic Regression, are evaluated for predictive performance, while SHAP (SHapley Additive Explanations) is employed to provide both global and local interpretability. The study aims to generate actionable insights for customer relationship management and marketing strategy, demonstrating how advanced predictive models can support informed business decisions without sacrificing transparency.

The Actuarial Applications Of Machine Learning And Big Data In The Life Assurance Industry: Managing Customer Retention And Customer Outcomes By The Application Of Data Science., Brian Cunningham

ICT

Lapses are an issue in the insurance industry in general. They affect a company’s profitability, cash flows and solvency. High levels of lapses can cause reputational damage that could provoke a cycle of even more lapses. It is therefore incumbent on a company to do its utmost to retain the business it has written for the term it was written for.

If a company could predict which of its policies were about to lapse, it could proactively attempt to prevent them by contacting the policyholder and engaging in a discussion to ascertain the likelihood of their choosing to leave. In …

Assemble The Ensemble: A Multi Model Approach For Customer Churn Prediction In The Gambling Industry., Paul Corcoran

ICT

Churn rates are remarkably high in the gambling industry, an extremely competitive landscape coupled with a severe lack of brand loyalty among its customer base makes churn prediction one of the main problems an operator will face. This paper explores the range of possible modelling solutions with a key emphasis on ensemble learning to improve on existing methods. During this exploration, a host of modelling techniques are formulated with a focus on scalability facilitated by Apache Spark distributed computing language. Thirteen variations of models, including single classifiers and ensemble families are evaluated as to their suitability in solving the problem. …

A Comparative Analysis Of Machine Learning And Neural Network Performance In House Price Prediction: Dublin Vs. Other Irish Regions, Diarmuid Carroll

ICT

This research presents a comparative analysis of machine learning and neural network performance in predicting house prices across Ireland’s regional housing markets. It addresses important methodological challenges and offers new empirical insights into how market complexity influences algorithm accuracy and performance. Drawing on 627,294 residential transactions from the Irish Property Price Register (2012–2024), the study applies a dual validation strategy, temporal and stratified sampling, across four regional classifications: Dublin, Other Cities, the Commuter Belt, and Rural areas.

The study makes three main contributions to data analytics theory and practice. First, it identifies and resolves temporal confounding effects in algorithm evaluation. …

Predictive Analytics For Customer Churns In Financial Services., Thant Thiha

ICT

This project presents a customer churn prediction analysis in the telecommunications sector, achieving an ROC-AUC of approximately 0.86 using statistically validated features and interpretable AI models. Key churn drivers identified include the number of products held, customer age, and geographic location. Ensemble models, such as Random Forest and Gradient Boosting, provided the highest predictive performance. Ethical AI principles were applied to ensure fairness, transparency, privacy, and accountability. Business insights derived from the analysis inform targeted retention strategies, prioritising multi-product users, specific age groups, and geographic segments. Deployment recommendations include the tuned Random Forest model with ongoing monitoring, governance, and future …

Predicting Customer Churn And Enhancing Retention Strategies Through Machine Learning., Swan Saung Lwin

ICT

Customer Churn is a critical challenge faced by businesses across industries, especially in the digital market. Many companies struggle to predict customer churn accurately and have difficulties in carrying out effective retention strategies. Key challenges include ineffective traditional methods, lack of insights into impact of different services, generalized retention strategies, and the need to have cost-effective retention strategies. This project aims to predict customer churn using machine learning and identify the impact of key services offered by a telecommunication company.

Customer Response To Marketing Campaigns., Alexandru Enoiu

ICT

This project applies machine learning to predict customer responses to marketing campaigns, aiming to enhance customer engagement and optimise resource allocation. Using a dataset containing demographic, lifestyle, and purchase behaviour data, a Random Forest classifier was developed to identify potential responders to marketing initiatives. The project follows a structured methodology including data exploration, preprocessing, model building, and evaluation. By accurately predicting customer behaviour, businesses can improve campaign targeting, design personalised marketing strategies, and allocate resources more efficiently. The results provide actionable insights to support customer segmentation and strategic decision-making, promoting business growth and customer satisfaction.

Data-Driven Public Transport Planning For Dublin: A Clustering And Forecasting Approach, Magdalena Burtinik Urueta, Mirae Yu

ICT

Dublin has been experiencing severe traffic congestion due to rapid economic and population growth, with residents losing an average of 158 hours per year in traffic during rush hour (Europe Data, 2025). A 2022 European Commission study found that 76% of Irish people use a car as their primary mode of transport on a typical day—an 8% increase from 2019, compared to the EU average of 47% (MacCarthaigh, 2022).

This project proposes a data-driven approach to identifying current transport accessibility gaps and forecasting future population growth across Dublin to support sustainable infrastructure development. Using Ireland’s Census data, an unsupervised method …