University of Moncton

A pandemic is a disease outbreak that affects an alarmingly high percentage of the population and spreads over a large geographic area. Some diseases are more likely to start pandemics because they are contagious and can cause severe illness or death. The most recent lethal disease to emerge and cause global devastation among all other pandemics is COVID-19. Since the COVID-19 disease breakout in December 2019, it has become a global pandemic that has caused millions of people throughout the planet. Modern information technology applications have emerged as a result of the pandemic's heightened demand for healthcare products and services. To effectively manage future pandemic-prone diseases and slow their vigorous spread, their early detection is crucial. New-age technologies, such as artificial intelligence, internet of things, cloud computing, etc., are therefore a major asset in the fight against such terrible diseases. Therefore, the current study employs the proposed architecture of a recurrent neural network (RNN) for the accurate identification of patients infected with COVID-19 disease through analysis of its major symptoms. Before classification, extra trees-based feature selection was used to collect the most significant features that accurately characterize COVID-19 positive or COVID-19 negative classes. This work also takes into account several deep learning models viz., RNN, Bi-LSTM, GRU, LSTM along with other machine learning models such as Logistic Regression to identify the COVID-19 pandemic. The thorough analysis of results shows that, the RNN classifier appears to perform better than the other classifiers in the early diagnosis of this fatal disease, with an accuracy of 98.70%, sensitivity of 97.81%, specificity of 95.55%, precision value equal to 98.97%, F1-score of 96.16%, and false discovery rate of 1.03% only. Therefore, the proposed RNN-based approach can help identify fatal infections caused by pandemic-prone diseases at an early stage, enabling timely intervention and containment. Highlights • The study presents an RNN-based model for early detection of pandemic-prone diseases using symptom analysis. • The proposed model achieves 98.70% accuracy, surpassing other classifiers like LSTM, GRU, and Logistic Regression. This framework can be extended to detect other diseases, aiding timely treatment and reducing healthcare strain.

The concepts of compensation and additive mortality form the ecological basis for understanding animal population responses to exploitation by humans. In the context of pest management, compensation is a density‐dependent response that allows populations to offset control‐related mortality, often via increased survival or reinvasion. Additive mortality, in contrast, accrues when a population's compensatory capacity is insufficient to offset losses, resulting in a net reduction in population size or growth rate. These concepts are rarely considered in forest insect pest management, which tends to emphasise short‐term plant protection over long‐term population control. We used published life table data for a major native forest insect defoliator, the spruce budworm (Choristoneura fumiferana [Lepidoptera: Tortricidae]) to simulate the amount of additive mortality required to suppress an outbreak. Simulations also assessed how the failure to account for different compensatory responses could hinder successful control. Our results suggest that only relatively modest amounts of additive mortality (perhaps as low as approximately 8%–18%) may be needed to stop spruce budworm from outbreaking, with immigration being the strongest potential compensatory hindrance to outbreak suppression. Many of the compensatory responses that thwarted outbreak suppression in the past (e.g., low detection efficiency, immigration, indiscriminate killing of predators and parasitoids) have contemporary solutions that could increase additive mortality and thereby enhance the feasibility of population control strategies for native forest insect pests. Our results suggest that some native forest insect pests may require relatively little additive mortality to suppress outbreaks if compensation‐limiting strategies are used. Incorporating theoretical and strategic frameworks used in vertebrate population management could advance the development of native insect population control programmes.

Smart contracts are changing many business areas with blockchain technology, but they still have vulnerabilities that can cause major financial losses. Because deployed smart contracts (SCs) are irreversible once deployed, fixing these vulnerabilities before deployment is critical. This research introduces a new method that combines code embedding with Generative Adversarial Networks (GANs) to find integer overflow vulnerabilities in smart contracts. Using Abstract Syntax Trees, we can vectorize the source code of smart contracts while keeping all of the important contract characteristics and going beyond what can be achieved with conventional textual or structural analysis. Synthesizing contract vector data using GANs alleviates data scarcity and facilitates source code acquisition for training our detection system. The proposed method is very good at finding vulnerabilities because it uses both GAN discriminator feedback and vector similarity measures based on cosine and correlation coefficients. Experimental results show that our GAN-based proactive analysis method achieves up to 18.1% improvement in accuracy over baseline tools such as Oyente and sFuzz.

Introduction Having a child with complex care needs (CCNs) can significantly impact families’ daily life structure. High caregiving responsibilities perceived by mothers and limited access to services—especially in rural settings—can affect their mental health and lead to caregiver burnout. Objectives This study aimed to explore the challenges faced by mothers of children with CCNs living in a rural setting. Methods: Eight mothers, recruited through a Community Social Pediatrics Centre in New Brunswick (CA), were individually interviewed between July 2020 and January 2021. Interviews were transcribed and analyzed using a thematic analysis method. Results Results highlight challenges experienced by mothers in accessing care and formal resources for their children. Both the lack of support and challenges faced by the child increased mothers’ burden. Discussion Future research and intervention are warranted to better identify and meet the needs of mothers having a child with CCNs and living in rural settings.

The Arctic is warming four times faster than the global average¹ and plant communities are responding through shifts in species abundance, composition and distribution2, 3–4. However, the direction and magnitude of local changes in plant diversity in the Arctic have not been quantified. Using a compilation of 42,234 records of 490 vascular plant species from 2,174 plots across the Arctic, here we quantified temporal changes in species richness and composition through repeat surveys between 1981 and 2022. We also identified the geographical, climatic and biotic drivers behind these changes. We found greater species richness at lower latitudes and warmer sites, but no indication that, on average, species richness had changed directionally over time. However, species turnover was widespread, with 59% of plots gaining and/or losing species. Proportions of species gains and losses were greater where temperatures had increased the most. Shrub expansion, particularly of erect shrubs, was associated with greater species losses and decreasing species richness. Despite changes in plant composition, Arctic plant communities did not become more similar to each other, suggesting no biotic homogenization so far. Overall, Arctic plant communities changed in richness and composition in different directions, with temperature and plant–plant interactions emerging as the main drivers of change. Our findings demonstrate how climate and biotic drivers can act in concert to alter plant composition, which could precede future biodiversity changes that are likely to affect ecosystem function, wildlife habitats and the livelihoods of Arctic peoples5,6.

Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The system shows great potential in facilitating the initial screening of skin cancer patients, empowering healthcare professionals to make timely decisions regarding patient referrals to dermatologists or specialists for further diagnosis and appropriate treatment. Our advanced adaptive fine-tuned CNN approach for automatic skin cancer diagnosis offers a valuable tool for efficient and accurate early detection. By leveraging DL and transfer learning techniques, the system has the possible to transform skin cancer diagnosis and improve patient outcomes.

Brain tumor detection is essential for early diagnosis and successful treatment, both of which can significantly enhance patient outcomes. To evaluate brain MRI scans and categorize them into four types—pituitary, meningioma, glioma, and normal—this study investigates a potent artificial intelligence (AI) technique. Even though AI has been utilized in the past to detect brain tumors, current techniques still have issues with accuracy and dependability. Our study presents a novel AI technique that combines two distinct deep learning models to enhance this. When combined, these models improve accuracy and yield more trustworthy outcomes than when used separately. Key performance metrics including accuracy, precision, and dependability are used to assess the system once it has been trained using MRI scan pictures. Our results show that this combined AI approach works better than individual models, particularly in identifying different types of brain tumors. Specifically, the InceptionV3 + Xception combination hit an accuracy level of 98.50% in training and 98.30% in validation. Such results further argue the potential application for advanced AI techniques in medical imaging while speaking even more strongly to the fact that multiple AI models used concurrently are able to enhance brain tumor detection.

Droughts are increasingly recognized as a significant global challenge, with severe impacts observed in Canada's Prairie provinces. While less frequent in Eastern Canada, prolonged precipitation deficits, particularly during summer, can lead to severe drought conditions. This study investigates the causes and consequences of droughts in New Brunswick (NB) by employing two drought indices: the Palmer Drought Severity Index (PDSI) and Standardized Evapotranspiration Deficit Index (SEDI)– at ten weather stations across NB from 1971 to 2020. Additionally, the Canadian Gridded Temperature and Precipitation Anomalies (CANGRD) dataset (1979–2014) was utilized to examine spatial and temporal drought variability and its alignment with station-based observations. Statistical analyses, including the Mann–Kendall test and Sen's slope estimator, were applied to assess trends in drought indices on annual and seasonal timescales using both station and gridded data. The results identified the most drought-vulnerable regions in NB and revealed significant spatial and temporal variability in drought severity over the 1971–2020 period. Trend analyses further highlighted the intensification of extreme drought events during specific years. Coastal areas in southern NB were found to be particularly susceptible to severe drought conditions compared to inland regions, consistent with observed declines in both the frequency of rainy days and daily precipitation amounts in these areas. These findings underscore the need for targeted drought mitigation strategies particularly in NB’s coastal zones, to address the region’s increasing vulnerability to extreme drought events.

Human memory is reconstructive and thus fundamentally imperfect. One of its critical flaws is false recall—the erroneous recollection of unstudied items. Despite its significant implications, false recall poses a challenge for existing computational models of serial recall, which struggle to provide item-specific predictions. Across six experiments, each involving 100 young adults, we address this issue using the Embedded Computational Framework of Memory (eCFM) that integrates existing accounts of semantic and episodic memory. While the framework provides a comprehensive account of memory processing, its innovation lies in the inclusion of a comprehensive lexicon of word knowledge derived from distributional semantic models. By integrating a lexicon that captures orthographic, phonological, and semantic relationships within an episodic memory model, the eCFM successfully accounts for patterns of veridical serial recall (e.g., proportion correct, intralist errors, omissions) while also capturing false recall (e.g., extralist errors including both critical lures and non-critical lures). We demonstrate the model’s capabilities through simulations applied to six experiments, with lists of words (Experiments 1A, 1B, 2A, and 2B) and non-words (Experiments 3A and 3B) that are either related or unrelated semantically (Experiments 1A and 1B), phonologically (Experiments 2A and 2B), or orthographically (Experiments 3A and 3B). This approach fills a computational gap in modelling serial recall and underscores the importance of integrating traditionally separate areas of semantic and episodic memory to provide more precise predictions and holistic memory models.

Many people suffer from Parkinson’s disease globally, a complicated neurological condition caused by the deficiency of dopamine, an organic chemical responsible for regulating movement in individuals. Patients with Parkinson face muscle stiffness or rigidity, tremors, vocal impairment, slow movement, loss of facial expressions, and problems with balance and coordination. As there is no cure for Parkinson, early diagnosis can help prevent the progression of this disease. The study explores the potential of vocal measures as significant indicators for early prediction of Parkinson. Different machine learning models such as Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), and Decision Tree (DT) are used to detect Parkinson using voice measures and differentiate between the healthy and Parkinson patients. The dataset contains 195 vocal recordings from 31 patients. The Synthetic Minority Over-Sampling Technique (SMOTE) is used for handling class imbalance to improve the performance of the models. The Principal Component Analysis (PCA) method was used for feature selection. The study uses different parameters to evaluate the model’s classification results. The results highlight RF as the most effective model with an accuracy of 94% and a precision of 94%. In addition, SVM achieves an accuracy score of 92%, and precision of 91%. However, with the PCA method, SVM achieves an accuracy of 89%, 92%, and 87% for RF and DT respectively. This study highlights the significance of using vocal features along with advanced machine learning methods to reliably diagnose Parkinson’s disease, considering the challenges associated with early detection.

Objective: This study aims to develop an explainable artificial intelligence (XAI) model integrated with machine learning (ML) to comprehensively investigate metabolic differences between individuals with Down syndrome (T21) and healthy controls (D21) and to identify novel/pathway-specific biomarkers. In this study, ML classifiers including AdaBoost, LightGBM, Random Forest, KTBoost, and XGBoost are applied to metabolomics data obtained from metabolomic analyses by high-resolution liquid chromatography-mass spectrometry (LC-MS) using blood plasma samples of 316 T21 and 103 D21 individuals, and the importance of metabolites is evaluated by XAI-based SHAP analysis. The KTBoost model shows the highest classification performance with an accuracy of 90.4% and area under the curve (AUC) of 95.9%, outperforming AdaBoost, LightGBM, Random Forest, and XGBoost. Significant downregulation and upregulation of some metabolites were observed in the T21 group compared to the D21 group. Metabolites such as vitamin C, taurolithocholic acid, sphingosine, and prostaglandin A2/B2/J2 are observed at low levels in the T21 group. In contrast, metabolites such as thymidine, tau-roursodeoxycholic acid, serine, and nervonic acid are elevated. SHAP analysis revealed that L-Citrulline, Kynurenin, Prostaglandin A2/B2/J2, Urate, and Pantothenate metabolites could be novel/pathway-specific biomarkers to differentiate the T21 group. This study revealed significant metabolic alterations in individuals with T21 and demonstrated the effectiveness of the combination of ML and XAI methods to identify novel/pathway-specific biomarkers. The findings may contribute to a better understanding of Down syndrome’s molecular mechanisms and the development of future diagnostic and therapeutic strategies.

Objectives This study aimed to gather an in-depth understanding of Francophone community-dwelling seniors’ needs and expectations regarding physical activity to inform the design and implementation of a community-based program in a rural area in New Brunswick. Methods Using the socioecological model, a qualitative design was co-created and an interview guide co-developed to collect data from 24 participants, including two focus groups and 13 individual interviews. Content analyses were carried out to categorize and conceptualize the data into main and subthemes. Results Four major themes emerged, including the presence of challenges and barriers (community and environmental obstacles, personal challenges, and social or cultural challenges), motivators and incentives (demographics, understanding the benefits of the program, sense of belonging, and preferred physical activities), designing program infrastructure (How, What, Where, time of offer, evaluation of capabilities, feelings of familiarity), and strategies to improve recruitment and retention (what would best allow participants to join and remain in the program). The findings of this study highlighted the key challenges community-dwelling seniors living in a rural area face in participating in physical activity programs (i.e., personal issues, geographic aspects, the importance of physical capacities, and cultural trends). Conclusion While codesigning physical activity programs for community-dwelling seniors living in rural areas is time-consuming, it allows for a better understanding of the social and organizational assets and challenges of the target community. It also strategically contributes to managers’ ownership and community engagement of/for the program to support its implementation and promotion.

The present study focuses on the synthesis and structural analysis of poly-ε-caproamide (PA6), produced through anionic polymerization of ε-caprolactam in bulk, utilizing mono and bifunctional activators. The research investigates the physical properties of PA6 synthesized under various polymerization conditions, aiming to understand how these conditions influence the polymer's behavior. The polymerization kinetics were monitored via dynamic rheology, offering insights into the progression of ε-caprolactam's conversion into PA6. Microstructural changes in the PA6 samples, including variations in the degree of crystallinity and the formation of α and γ crystalline structures, were systematically studied. These transformations were dependent on both the type and concentration of the activator used, as well as the specific polymerization parameters applied. The interplay between these factors significantly impacted the resulting chemical and physical structure of the PA6 samples. In the latter part of the study, hybrid composites were fabricated by reinforcing poly-ε-caproamide with two distinct types of fiber fabrics by reactive processing, achieving a 25% weight fraction of reinforcement. Scanning electron microscopy (SEM) revealed excellent interfacial adhesion between the fibers and the polymer matrix, confirming the effectiveness of the fabrication process and the potential of these composites for advanced material applications.

OPEN Abstract The intricacies and instability of introducing cryogenic propellants into the combustion system have piqued the curiosity of scientists studying the procedure. The latest innovation is utilizing data-driven machine learning and deep learning approaches to gain deeper insights into the related difficulties. However, the current work serves as a baseline for future research because relatively few studies have used data-driven methodologies to assess the temperature of liquid fuel injections in combustion systems.

The different steps of alternative splicing (AS) in plants and its regulatory mechanisms have already been studied extensively. Its broader impact on cell identity, plant immunity‐related genes, and their study as a whole remains to be investigated. Using transgenic plants, we sorted 11 different Arabidopsis thaliana cell types ranging from root to aerial organs using fluorescence‐activated cell sorting. RNA‐seq data were analyzed with vast‐tools and enabled us to generate a high‐resolution AS landscape across multiple cell types, all collected through the same experimental procedure. The analysis of cell type‐specific gene expression and alternative splicing events highlights the importance of AS on transcription and AS regulation itself. AS is also shown to be tightly linked to cell identity. By using closely related cell types, we captured alternative splicing events involved in specific stages of plant development. The columella cells, among others, show intensified AS regulation and an interesting splicing profile, especially regarding immunity‐related genes. Overall, our analysis brings a valuable tool in the study of cell type identity, plant immunity, and AS.

Accurate dietary intake estimation is crucial for managing weight-related chronic diseases, such as diabetes, where precise measurement of food volume and caloric content is essential. Traditional calorie counting methods are often error-prone and may not meet the specific needs of individuals with diabetes. Recent advancements in computer science offer promising solutions through automated systems that estimate calorie intake from food images using deep learning techniques. These systems provide personalized dietary recommendations, helping individuals with diabetes make informed choices. As smartphones and wearable devices become more accessible, the utilization of electronic apps for dietary monitoring is increasing, highlighting the need for more research into safe, secure, and evidence-based IoT solutions. However, challenges such as standardization, validation across diverse populations, and data privacy concerns need to be addressed. This review focuses on the role of computer science in dietary intake estimation, specifically food segmentation, classification, and volume estimation for calorie calculation. By synthesizing existing literature, this review provides insights into current methods, key challenges, and potential future directions. The review also explores advancements in technology that can improve the accuracy of dietary assessments, contributing to personalized disease management and the prevention of weight-related chronic conditions.

Community-dwelling older people (CDOP) face important risks of falling, a leading cause of chronic pain and transitions into long-term disability. While exercise-based interventions are widely studied for fall prevention, psychoeducation may play an important preventive role. Nevertheless, psychoeducation for fall prevention remains underexplored. This study aimed to describe existing psychoeducation for fall prevention among CDOP, identify its key components, and derive recommendations to inform future interventions. Using a scoping review design, we selected 20 studies with focus on psychoeducation for fall prevention. Findings revealed that all selected studies incorporated at least one of the four psychoeducation elements described by Anderson et al. Key aspects including mode of delivery, intervention facilitator, and educational resources are described, but literature lacks convergence. Moreover, theory-based psychoeducation programs and integration of technology and interactive delivery methods are underexplored. Implications for the design of a psychoeducation program for fall prevention in CDOP are discussed.

Electricity theft is a significant issue that causes substantial financial losses for utility providers and poses safety risks to the public. Detecting such theft accurately and efficiently remains a critical challenge, especially in areas with inadequate infrastructure. This research proposes a machine learning-based approach to address the problem of electricity theft, utilizing the adaptive synthetic sampling (ADASYN) technique to balance imbalanced datasets, particularly for theft detection. The study evaluates several machine learning algorithms integrated with ADASYN, including Naive Bayes, logistic regression, support vector machine, AdaBoost, decision tree, and random forest. The models were tested on publicly available datasets, yielding accuracy rates ranging from 52 to 95%. Among these, random forest demonstrated the best performance, achieving an accuracy of 95%, along with precision, recall, and F1 scores of 95% for both the “Not Theft” and “Theft” classes. The random forest model outperformed benchmarks from previous studies, showcasing its effectiveness in distinguishing between theft and non-theft instances. These results highlight the potential of machine learning models, particularly when augmented with data balancing techniques like ADASYN, to enhance the accuracy and reliability of electricity theft detection systems, thereby reducing financial losses and improving public safety.