Physical Sciences and Mathematics Commons^™

Image Instance Segmentation: Using The Cirsy System To Identify Small Objects In Low Resolution Images, Orghomisan William Omatsone

Dissertations

The CIRSY system (or Chick Instance Recognition System) is am image processing system developed as part of this research to detect images of chicks in highly-populated images that uses the leading algorithm in instance segmentation tasks, called the Mask R-CNN. It extends on the Faster R-CNN framework used in object detection tasks, and this extension adds a branch to predict the mask of an object along with the bounding box prediction. Mask R-CNN has proven to be effective ininstance segmentation and object de-tection tasks after outperforming all existing models on evaluation of the Microsoft Common Objects in Context (MS COCO) …

Machine Learning Assisted Gait Analysis For The Determination Of Handedness In Able-Bodied People, Hugh Gallagher

Dissertations

This study has investigated the potential application of machine learning for video analysis, with a view to creating a system which can determine a person’s hand laterality (handedness) from the way that they walk (their gait). To this end, the convolutional neural network model VGG16 underwent transfer learning in order to classify videos under two ‘activities’: “walking left-handed” and “walking right-handed”. This saw varying degrees of success across five transfer learning trained models: Everything – the entire dataset; FiftyFifty – the dataset with enough right-handed samples removed to produce a set with parity between activities; Female – only the female …

An Examination Of The Smote And Other Smote-Based Techniques That Use Synthetic Data To Oversample The Minority Class In The Context Of Credit-Card Fraud Classification, Eduardo Parkinson De Castro

Dissertations

This research project seeks to investigate some of the different sampling techniques that generate and use synthetic data to oversample the minority class as a means of handling the imbalanced distribution between non-fraudulent (majority class) and fraudulent (minority class) classes in a credit-card fraud dataset. The purpose of the research project is to assess the effectiveness of these techniques in the context of fraud detection which is a highly imbalanced and cost-sensitive dataset. Machine learning tasks that require learning from datasets that are highly unbalanced have difficulty learning since many of the traditional learning algorithms are not designed to cope …

Transformer Neural Networks For Automated Story Generation, Kemal Araz

Dissertations

Towards the last two-decade Artificial Intelligence (AI) proved its use on tasks such as image recognition, natural language processing, automated driving. As discussed in the Moore’s law the computational power increased rapidly over the few decades (Moore, 1965) and made it possible to use the techniques which were computationally expensive. These techniques include Deep Learning (DL) changed the field of AI and outperformed other models in a lot of fields some of which mentioned above. However, in natural language generation especially for creative tasks that needs the artificial intelligent models to have not only a precise understanding of the given …

Identifying Online Sexual Predators Using Support Vector Machine, Yifan Li

Dissertations

A two-stage classification model is built in the research for online sexual predator identification. The first stage identifies the suspicious conversations that have predator participants. The second stage identifies the predators in suspicious conversations. Support vector machines are used with word and character n-grams, combined with behavioural features of the authors to train the final classifier. The unbalanced dataset is downsampled to test the performance of re-balancing an unbalanced dataset. An age group classification model is also constructed to test the feasibility of extracting the age profile of the authors, which can be used as features for classifier training. The …

Classification Of Animal Sound Using Convolutional Neural Network, Neha Singh

Dissertations

Recently, labeling of acoustic events has emerged as an active topic covering a wide range of applications. High-level semantic inference can be conducted based on main audioeffects to facilitate various content-based applications for analysis, efficient recovery and content management. This paper proposes a flexible Convolutional neural network-based framework for animal audio classification. The work takes inspiration from various deep neural network developed for multimedia classification recently. The model is driven by the ideology of identifying the animal sound in the audio file by forcing the network to pay attention to core audio effect present in the audio to generate Mel-spectrogram. …

2-(Di­Phenyl­Methyl­Idene)-2,3-Di­Hydro-1h-Inden-1-One, Tao Zhang, Vilmar Bandero, Tom Mccabe, Neil Frankish, Helen Sheridan

Articles

In the title mol­ecule, C₂₂H₁₆O, the indanone ring system is approximately planar with a dihedral angle between the fused rings of 5.13 (14)°. Two benzene rings are linked together at one side of a double bond, sitting on either side of the indanone ring system and making dihedral angles of 70.30 (12) and 44.74 (13)° with it. In the crystal, hydrogen bonding is not present, but weak C—H⋯π or π–π inter­actions occur and mol­ecules form a sheet-like structure in the bc plane.

Adaptive Background Correction Of Crystal Image Datasets: Towards Automated Process Control, Luke Kiernan, Ian Jones, Lauri Kurki, Patrick J. Cullen, Toufic El Arnaout

Articles

Improving the data descriptor calculation of crystal’s physical properties requires sophisticated imaging techniques and algorithms. It has been possible to construct 2D population balance models benefiting from characteristic measurements of both crystal’s length and width, compared to the single representative sizes used in 1D models. Our aim is to ameliorate the procedure of determining shape (and not only size) factors, in an automated fashion and directly from the process, for implementation in future models. Here, approaches suitable for real-time applications were employed including engineered imaging sensors and adaptive algorithms. We described the latter in detail for varying 2D image datasets. …

Pilot Scale Pyrolysis Of Activated Sludge Waste From Milk Processing Factory, Marzena Kwapinska, Alen Horvat, Yupeng Liu, James Leahy

Articles

The majority of the sludge from the treatment of wastewater in milk processing plants is land spread. The drawbacks of land spreading include local oversupply due to high transport costs, which results in sludge being spread on lands in the vicinity of the dairy factories. Local oversupply can lead to accumulation of certain substances in soil through annual application over many years. Therefore, in the long term, there is a need for alternative methods to recover energy and nutrients from increasing volumes of sludge generated from dairy processing. Pyrolysis ofers a potential alternative to land spreading, which can reduce health …

Dissipation Of Pesticide Residues On Grapes And Strawberries Using Plasma-Activated Water, Chaitanya Sarangapani, Laurence Scally, Miroslav Gulan, P. J. Cullen

Articles

In this study, we present a novel atmospheric air plasma discharge for the generation of plasma-activated water (PAW), with the aim of reducing pesticide residues on fresh fruit. For this purpose, a large discharge volume pin-to-plate cold plasma reactor was employed. The pesticide-spiked grapes and strawberries were processed with varying PAW concentrations to study their efficacies for pesticide degradation combined with an evaluation of any induced changes in key nutritional and quality attributes. The results suggest that the reduction of chlorpyrifos was 79% on grapes and 69% on strawberries while that of carbaryl was 86% on grapes and 73% on …

Saperi: Approaching Gender Gap Using Spatial Ability Training Week In High-School Context, Maria Giulia Ballatore, Gavin Duffy, Sheryl Sorby, Anita Tabacco

Conference papers

The purpose of this paper is to describe the structure of a girls summer school, “SAperI – Spatial Ability per l’Ingegneria” (in English, “Knowledge – Spatial Ability for Engineering”), and to illustrate its impact on spatial ability development and future career preferences on those who participated in the week long summer school compared to a control group that did not participate.The 5 days school,
organized by Politecnico di Torino (Italy), was included in a larger project addressing 17 years old high-school students. Thirtyseven girls actively took part in a summer school, while 167 students (both males and females) were tested …

Calibration For A Hybrid Mimo Near-Field Imaging System To Mitigate Antennas Effects, Ha Hoang, Zeeshan Ahmed, Matthias John, Patrick Mcevoy, Max Ammann

Conference Papers

A calibration method for a high-resolution hybrid MIMO turntable radar imaging system is presented. A line of small metal balls is used in the calibration process to measure the position shift caused by undesired effects of the antennas. The unwanted effects in the near-field antenna response are analysed and significantly mitigated based on the referential features of the MIMO configuration.

A Comparative Study Of Text Summarization On E-Mail Data Using Unsupervised Learning Approaches, Tijo Thomas

Dissertations

Over the last few years, email has met with enormous popularity. People send and receive a lot of messages every day, connect with colleagues and friends, share files and information. Unfortunately, the email overload outbreak has developed into a personal trouble for users as well as a financial concerns for businesses. Accessing an ever-increasing number of lengthy emails in the present generation has become a major concern for many users. Email text summarization is a promising approach to resolve this challenge. Email messages are general domain text, unstructured and not always well developed syntactically. Such elements introduce challenges for study …

Customer Churn Prediction, Deepshikha Wadikar

Dissertations

Churned customers identification plays an essential role for the functioning and growth of any business. Identification of churned customers can help the business to know the reasons for the churn and they can plan their market strategies accordingly to enhance the growth of a business. This research is aimed at developing a machine learning model that can precisely predict the churned customers from the total customers of a Credit Union financial institution. A quantitative and deductive research strategies are employed to build a supervised machine learning model that addresses the class imbalance problem handled feature selection and efficiently predict the …

Cu(Ii) Phenanthroline-Phenazine Complexes Dysregulate Mitochondrial Function And Stimulate Apoptosis, Garret Rochford, Zara Molphy, Kevin Kavanagh, Malachy Mccann, Michael Devereux, Andrew Kellett, Orla L. Howe

Articles

Herein we report an in-depth study on the cytotoxic mechanism of action of four developmental cytotoxic copper(II) complexes: [Cu(phen)2]2+ (Cu-Phen); [Cu(DPQ)(Phen)]2+ (Cu-DPQ-Phen); [Cu(DPPZ)(Phen)]2+; and [Cu(DPPN)(Phen)]2+ (where Phen = 1,10-phenanthroline, DPQ = dipyrido[3,2-f:20,30-h]quinoxaline, DPPZ = dipyrido[3,2-a:20,30-c]phenazine, and DPPN = benzo[i]dipyrido[3,2-a:20,30-c]phenazine). This complex class is known for its DNA intercalative properties and recent evidence—derived from an in vivo proteomic study—supports the potential targeting of mitochondrial function. Therefore, we focused on mitochondrial-mediated apoptosis related to cytotoxic activity and the potential impact these agents have on mitochondrial function. The Cu(II) complexes demonstrated superior activity regardless of aromatic extension within the phenazine ligand to the …

Birefringent Optofluidic Gratings, Sergio Calixto, Jose L. Garcia-Cordero, Diana F. Cedillo-Alcantar, Izabela Naydenova, Guillermo Garnica

Articles

A set of parallel microfluidic channels behaving as a diffraction grating operating in the Raman-Nath regime has been fabricated and studied. The diffraction efficiency of such structure can be tuned by selecting a liquid with a particular refractive index and/or optical anisotropy. Alternatively the optical properties of the liquid can be characterised by measuring the diffraction efficiency and the state of polarization of the diffracted beam. In this work, the microfluidic channels under study have been filled with penicillin molecules dissolved in water. Due to the chirality of the penicillin, the liquid has been found to have circular birefringence of …

Identifying And Disentangling Interleaved Activities Of Daily Living From Sensor Data, Eoin Rogers

Doctoral

Activity discovery (AD) refers to the unsupervised extraction of structured activity data from a stream of sensor readings in a real-world or virtual environment. Activity discovery is part of the broader topic of activity recognition, which has potential uses in fields as varied as social work and elder care, psychology and intrusion detection. Since activity recognition datasets are both hard to come by, and very time consuming to label, the development of reliable activity discovery systems could be of significant utility to the researchers and developers working in the field, as well as to the wider machine learning community.

This …

Self-Reported Data For Mental Workload Modelling In Human-Computer Interaction And Third-Level Education, Lucas Rizzo, Luca Longo

Articles

Mental workload (MWL) is an imprecise construct, with distinct definitions and no predominant measurement technique. It can be intuitively seen as the amount of mental activity devoted to a certain task over time. Several approaches have been proposed in the literature for the modelling and assessment of MWL. In this paper, data related to two sets of tasks performed by participants under different conditions is reported. This data was gathered from different sets of questionnaires answered by these participants. These questionnaires were aimed at assessing the features believed by domain experts to influence overall mental workload. In total, 872 records …

An Empirical Evaluation Of The Inferential Capacity Of Defeasible Argumentation, Non-Monotonic Fuzzy Reasoning And Expert Systems, Lucas Rizzo, Luca Longo

Articles

Several non-monotonic formalisms exist in the field of Artificial Intelligence for reasoning under uncertainty. Many of these are deductive and knowledge-driven, and also employ procedural and semi-declarative techniques for inferential purposes. Nonetheless, limited work exist for the comparison across distinct techniques and in particular the examination of their inferential capacity. Thus, this paper focuses on a comparison of three knowledge-driven approaches employed for non-monotonic reasoning, namely expert systems, fuzzy reasoning and defeasible argumentation. A knowledge-representation and reasoning problem has been selected: modelling and assessing mental workload. This is an ill-defined construct, and its formalisation can be seen as a reasoning …

Food Fraud In Nigeria: Challenges, Risks And Solutions, Joy Ewomazino Opia

Theses

Food fraud is one of the most urgent and active food research and regulatory areas. It is an evolving problem in Nigeria that has led to the deaths of many people especially the vunerable groups that includes mostly children, the elderly and immunocomprised persons. Therefore the aim of this study is to investigate the current challenges of food fraud in Nigeria, identify the risks it poses on the health and wellbeing of Nigerians and propose measures to tackle food fraud at local and international levels by regulatory and government agencies. This study explored the relationship between food fraud, food security …

Food Proteins: Sustainable Sources Of Proteins Responsible For Emulsions Stability In Food Products, Gleicy Kelly Oliveira Nogueria

Theses

One of the major challenges manufactures are facing is the fact that consumer’s personal health standards are changing constantly, modern consumers are willing to know more about the ingredients used in their food. The relationship with ethics and sustainability is leading to changes in the food industry. Seen this, manufactures are opting for other sources of ingredients, such as plant-based alternatives. However, the use of these sort of products need to be developed due to of their unknown properties. The use of sustainable plant proteins provides a variety of benefits to the product, such as added nutritional value as fiber, …

Quantitative Analysis Of Human Blood Serum Using Vibrational Spectroscopy., Hugh Byrne, Franck Bonnier, Jennifer Mcintyre, Drishya Rajan Parachalil

Articles

Analysis of bodily fluids using vibrational spectroscopy has attracted increasing attention in recent years. In particular, infrared spectroscopic screening of blood products, particularly blood serum, for disease diagnostics has been advanced considerably, attracting commercial interests. However, analyses requiring quantification of endogenous constituents or exogenous agents in blood are less well advanced. Recent advances towards this end are reviewed, focussing on infrared and Raman spectroscopic analyses of human blood serum. The importance of spectroscopic analysis in the native aqueous environment is highlighted, and the relative merits of infrared absorption versus Raman spectroscopy are considered, in this context. It is argued that …

Multimodal Vibrational Studies Of Drug Uptake In Vitro: Is The Whole Greater Than The Sum Of Their Parts?, David Perezguaita, Karolina Chrabaszcz, Kamilla Malek, Hugh Byrne

Articles

Herein, we investigated the use of multimodal Raman and infrared (IR) spectroscopic microscopy for the elucidation of drug uptake and subsequent cellular responses. Firstly, we compared different methods for the analysis of the combined data. Secondly, we evaluated whether the combined analysis provided enough benefits to justify the fusion of the data. A459 cells inoculated with doxorubicin (DOX) at different times were fixed and analysed using each technique. Raman spectroscopy provided high sensitivity to DOX and enabled an accurate estimation of the drug uptake at each time point, whereas IR provided a better insight into the resultant changes in the …

Raman Mapping Coupled To Self Modelling Mcr-Als Analysis To Estimate Active Cosmetic Ingredient Penetration Profile In Skin, Aline Stella, Franck Bonnier, Ali Tfayli, Florent Yvergnaux, Hugh Byrne, Igor Chourpa, Emilie Munnier, Clovis Tauber

Articles

Confocal Raman mapping (CRM) is a powerful, label free, non-destructive tool, enabling molecular characterization of human skin with applications in the dermo-cosmetic field. Coupling CRM to multivariate analysis can be used to monitor the penetration and permeation of active cosmetic ingredients (ACI) after topical application. It is presently illustrated how multivariate curve resolution alternating least squares (MCR-ALS) can be applied to detect and semi-quantitatively describe the diffusion profile of Delipidol, a commercially available slimming ACI, from Raman spectral maps. Although the analysis outcome can be critically dependent on the a priori selection of the number of regression components, it is …

Liposomal Encapsulation Of Silver Nanoparticles (Agnp) Improved Nanoparticle Uptake And Induced Redox Imbalance To Activate Caspase-Dependent Apoptosis, Azeez O. Yusef, Alan Casey

Articles

Macrophages play a crucial role in several diseases’ development and progression, such as in cancer and arthritis through ROS generation and infammation. This makes macrophages a therapeutic target in these diseases. While silver nanoparticles (AgNP) have been widely used as an antibacterial and investigated as anticancer, its potential against macrophages may be limited due to its inherent oxidative mechanism. Here we encapsulated AgNP in a dipalmitoyl-phosphatidyl choline (DPPC) liposome (forming Lipo-AgNP) to suppress AgNP-induced ROS and enhance its cytotoxicity against THP1-diferentiated macrophages (TDM). Our fndings showed that while Lipo-AgNP had signifcantly more of a cytotoxic efect on TDMs (p< 0.01), it also signifcantly suppressed AgNP induced ROS generation and unexpectedly suppressed reduced glutathione (GSH) levels (p< 0.05) resulting in a redox imbalance in comparison to the unexposed control TDMs. Lipo-AgNP was also found to cause an increase DNA damage through H2AX histone phosphorylation and inhibition of Bcl-2 protein expression. This increased the Bax/Bcl2 ratio causing possible release of cytochrome C and subsequent caspase 3/7-dependent apoptosis. It was found that the diference between the mechanism of AgNP and Lipo-AgNP cytotoxicity may have been through the signifcantly increased Lipo-AgNP uptake by the TDMs as early as 30 min post-exposure (p< 0.05), changing the nanoparticle pharmacokinetic. In conclusion, the improved uptake of AgNP within the liposome caused ROS-independent caspase activation induced by Lipo-AgNP and this was facilitated by increased DNA damage, the induced redox imbalance and an increased Bax/Bcl-2 ratio.

Modulation Of Medical Condition Likelihood By Patient History Similarity, Jonathan Turner, Dympna O'Sullivan, Jon Bird

Articles

Introduction: We describe an analysis that modulates the simple population prevalence derived likelihood of a particular condition occurring in an individual by matching the individual with other individuals with similar clinical histories and determining the prevalence of the condition within the matched group.

Methods: We have taken clinical event codes and dates from anonymised longitudinal primary care records for 25,979 patients with 749,053 recorded clinical events. Using a nearest neighbour approach, for each patient, the likelihood of a condition occurring was adjusted from the population prevalence to the prevalence of the condition within those patients with the closest …

An Ammonia Sensor Using An Unadorned Bromocresol Layer, John Cassidy, Caoimhe Ní Néill, Merve Akdağ, Tony Betts

Articles

Bromocresol Purple,(BCP) cast onto an acetate sheet, was used to sense ammonia. This simple layer responded reversibly to a low concentration ( 15 ppm) of ammonia in the presence of water vapour. The BCP solution was spincoated on an acetate sheet from a solution in dichloromethane. This layer was exposed to nitrogen and NH3/H2O vapour in quick succession. The colour change occurred from yellow to purple rapidly in the solid state. The λmax for the neutral ( acid) form of the BCP was found to be 435 nm and the λmax for the dianion ( base form) of the BCP …

Determination Of Integrity, Stability And Density Of The Dna Layers Immobilised At Glassy Carbon And Gold Electrodes Using Ferrocyanide, John Colleran, Anna Banasiak

Articles

The technique chosen to immobilise DNA onto electrodes can determine the density and stability of the resultant immobilised layer. DNA‐modified electrodes were prepared using four common DNA immobilisation methods and characterised using ferrocyanide. The negatively charged DNA strands should repel ferrocyanide anions. The DNA layers created using adsorption at glassy carbon electrodes were unstable, while those created through chemisorption of thiol‐modified DNA onto gold electrodes were repeatable and stable, and returned, on average, 94 % repulsion of the probe. The presented results show how the immobilisation protocol, and DNA type, affects the stability, repeatability, and integrity of resultant DNA layers.

Structural Annotation Of Electro- And Photochemically Generated Transformation Products Of Moxidectin Using High-Resolution Mass Spectrometry, Lisa Kotthoff, Sarah-Louise O'Callaghan, Jan Lisec, Tanja Schwerdtle, Matthias Koch

Articles

Moxidectin (MOX) is a widely used anthelmintic drug for the treatment of internal and external parasites in food-producing and companion animals. Transformation products (TPs) of MOX, formed through metabolic degradation or acid hydrolysis, may pose a potential environmental risk, but only few were identified so far. In this study, we therefore systematically characterized electro- and photochemically generated MOX TPs using high-resolution mass spectrometry (HRMS). Oxidative electrochemical (EC) TPs were generated in an electrochemical reactor and photochemical (PC) TPs by irradiation with UV-C light. Subsequent HRMS measurements were performed to identify accurate masses and deduce occurring modification reactions of derived TPs …

Phenology Of Cupressaceae Urban Infrastructure Related To Its Pollen Content And Meteorological Variables, A. Monroy-Colín, J. M. Maya-Manzano, I. Silva-Palacios, R. Tormo-Molina, R. Pecero-Casimiro, Á. Gonzalo-Garijo, S. Fernández-Rodríguez

Articles

Cupressaceae pollen is one of the major airborne allergens of the Mediterranean region and in other regions around the world. Pollen production of these species causes considerable allergic problems during winter, being this type of pollen the most abundant in this period of the year. This work aims to relate phenology, meteorology and airborne pollen records in these species. Aerobiological sampling was carried out in Badajoz (SW Spain) from 2016 to 2018 using Hirst-type volumetric sampler. Pollination phenology was studied in 50 specimens, ten of Cupressus macrocarpa, ten of Cupressus arizonica, 15 of Cupressus sempervirens and 15 of …