Articles

Social media platforms like X (formerly Twitter) generate vast volumes of user-generated content that provide real-time insights into public sentiment. Despite the widespread use of traditional machine learning methods, their limitations in capturing contextual nuances in noisy social media text remain a challenge. This study leverages the Sentiment140 dataset, comprising 1.6 million labeled tweets, and develops predictive models for binary sentiment classification using Naive Bayes, Logistic Regression, and the transformer-based BERT model. Experiments were conducted on a balanced subset of 12,000 tweets after comprehensive NLP preprocessing. Evaluation using accuracy, F1-score, and confusion matrices revealed that BERT significantly outperforms traditional models, achieving an accuracy of 89.5% and an F1-score of 0.89 by effectively modeling contextual and semantic nuances. In contrast, Naive Bayes and Logistic Regression demonstrated reasonable but consistently lower performance. To support practical deployment, we introduce SentiFeel, an interactive tool enabling real-time sentiment analysis. While resource constraints limited the dataset size and training epochs, future work will explore full corpus utilization and the inclusion of neutral sentiment classes. These findings underscore the potential of transformer models for enhanced public opinion monitoring, marketing analytics, and policy forecasting.

Mathematical modeling plays a central role in infectious disease epidemiology, shaping outbreak response strategies and informing public health policy. The COVID-19 pandemic demonstrated the value of these models but also exposed persistent limitations related to data fragility, lack of transparency, limited stakeholder engagement, and insufficient consideration of social and political contexts. Rather than critiquing modeling as a discipline, this perspective argues for a reorientation of infectious disease modeling toward a more responsive, equity-centered, and participatory paradigm. We propose a conceptual framework built on three interrelated principles: adaptability through real-time data integration, transparency via open-source and reproducible practices, and relevance through interdisciplinary and co-produced model design. Drawing on illustrative examples from COVID-19 and dengue control efforts, we highlight how integrating behavioral dynamics, local knowledge, and policy feedback can improve model usefulness and public trust. Reconceptualizing models as dynamic systems of inquiry rather than static forecasting tools can enhance decision-making and promote more equitable and effective responses to future public health emergencies.

The gut-brain axis (GBA) has emerged as a central focus in the study of neurodevelopmental disorders, particularly autism spectrum disorder (ASD). Research suggests that microbial composition and its metabolic byproducts influence neural development, synaptic plasticity, and behavior [1,2,3]. A structured bibliometric analysis of Scopus and Web of Science records was performed using Bibliometrix and VOSviewer to trace trends and thematic evolution of GBA–ASD literature [7,8]. In parallel, a data-driven pathway modeling approach maps microbial metabolites (e.g., short-chain fatty acids, tryptophan catabolites) to host signaling pathways including vagal stimulation, immune cytokine modulation, and blood–brain barrier (BBB) permeability [4,5]. Simulations implemented in Python’s NetworkX illustrate how perturbations in metabolite flux may influence CNS outcomes. The findings reveal growing emphasis on butyrate, serotonin, microglial priming, and maternal immune activation in ASD-related GBA studies, and highlight the need for rigorous empirical validation of computational predictions [9,10,11].

This research is a collaboration involving a university team, a partnering corporation, and a hemodialysis clinic, which is a cross-disciplinary research initiative in the field of Artificial Intelligence of Things (AIoT) within the medical informatics domain. The research has two objectives: (1) The development of an <i>Internet of Things (IoT)</i><i>-based</i><i> Information System</i> customized for the hemodialysis machines at the clinic, including transmission bridges, clinical personnel dedicated web/app, and a backend server. The system has been deployed at the clinic and is now officially operational; (2) The research also utilized de-identified, anonymous data (collected by the officially operational system) to train, evaluate, and compare <i>Deep Learning-based Intradialytic Blood Pressure</i><i> (BP)</i><i>/Pulse </i><i>Rate (PR) </i><i>Predictive Models</i>, with subsequent suggestions provided. Both objectives were executed under the supervision of the Institutional Review Board (IRB) at Mackay Memorial Hospital in Taiwan. The system completed for objective one has introduced three significant services to the clinic, including automated hemodialysis data collection, digitized data storage, and an information-rich human-machine interface as well as graphical data displays, which replaces traditional paper-based clinical administrative operations, thereby enhancing healthcare efficiency. The graphical data presented through web and app interfaces aids in real-time, intuitive comprehension of the patients’ conditions during hemodialysis. Moreover, the data stored in the backend database is available for physicians to conduct relevant analyses, unearth insights into medical practices, and provide precise medical care for individual patients. The training and evaluation of the predictive models for objective two, along with related comparisons, analyses, and recommendations, suggest that in situations with limited computational resources and data, an Artificial Neural Network (ANN) model with six hidden layers, SELU activation function, and a focus on artery-related features can be employed for hourly intradialytic BP/PR prediction tasks. It is believed that this contributes to the collaborating clinic and relevant research communities.

<b>Background: </b>Nicotine pouches, gummies, and candies have emerged as popular alternatives to traditional tobacco products among U.S. adolescents. While parental educational attainment is generally associated with youth substance use, marginalization-related diminished returns (MDRs) suggest that this effect may be weaker in marginalized populations, including non-Latino White communities. In particular, place-based marginalization—such as neighborhood economic disadvantage and school-level poverty—may attenuate the benefits of parental education. This study examines MDRs in the relationship between parental educational attainment and nicotine pouch/gummy/candy use among non-Latino White 12th graders in the 2024 Monitoring the Future (MTF) study. <b>Methods: </b>This study analyzed nationally representative data from the 2024 MTF study, focusing on non-Latino White 12th graders who reported parental education levels and adolescents’ use of nicotine pouch/gummy/candy. Structural equation modeling (SEM) was used to estimate the effects of parental education on adolescents’ use of nicotine pouches, gummies, and candies, while adjusting for demographic covariates. Place-based marginalization was operationalized using rural vs urban /suburban residence. Interaction terms tested whether the effect of parental education varied based on place of residence. <b>Results: </b>Higher parental educational attainment was associated with lower use of nicotine pouches, gummies, and candies. However, this effect was significantly weaker in rural areas. <b>Conclusion: </b>Public health interventions should account for place-based disparities rather than assuming a uniform effect of SES factors. This study highlights the need for policy responses that address structural inequities beyond individual family SES.

<b>Background: </b>Electronic cigarette (e-cigarette) use and vaping tobacco have increased rapidly worldwide, raising concerns about their health effects, social acceptability, and regulatory challenges. In many countries, e-cigarettes are more commonly used by individuals from higher socioeconomic status (SES) backgrounds, who, in theory, should have greater knowledge about e-cigarettes and their associated risks. However, it remains unclear why a group with more knowledge about e-cigarette risks would also hold more positive attitudes toward vaping and exhibit higher usage rates — a phenomenon that may represent a knowledge-behavior paradox. Understanding this paradox, along with the complex relationships between e-cigarette knowledge, attitudes, and behaviors, is critical for informing effective public health interventions, campaigns, social media messaging, and regulatory policies. <b>Objectives: </b>This study aimed to evaluate the complex relationship between SES, e-cigarette knowledge, pro-vaping attitudes, and e-cigarette use. <b>Methods: </b>The SMOKES Study (Study of Measurement of Knowledge and Examination of Support for Tobacco Control Policies) used a multi-center, cross-sectional design, collecting data from 2,403 college and university students across 15 provinces in Iran (covering nearly half of the country's provinces). The survey measured family income, age, sex, ethnicity, e-cigarette use, knowledge, and attitudes. Structural Equation Modeling (SEM) was employed to examine the interrelations between SES, knowledge, attitudes, and behavior, while adjusting for age, sex, and ethnic minority status. <b>Results</b>: SEM analysis confirmed the hypothesized paradox. Although greater knowledge about e-cigarettes was linked to less favorable attitudes toward vaping and lower use, pro-vaping attitudes emerged as the strongest predictor of vaping behavior, while knowledge played a weaker protective role. Notably, individuals with higher SES simultaneously showed higher knowledge and, paradoxically, more pro-e-cigarette attitudes and greater usage. Female students and ethnic minority students reported higher correct knowledge and lower pro-vaping attitudes and use. Although age and higher family income were associated with more favorable attitudes, they did not directly predict vaping behavior. These results suggest that for higher SES individuals, poor knowledge is not the main driver of e-cigarette use; rather, their pro-e-cigarette attitudes, which seem to outweigh the influence of knowledge, play a key role. <b>Conclusions: </b>Although individuals from higher SES backgrounds report greater correct knowledge about e-cigarettes, this knowledge does not necessarily translate into reduced positive attitudes or lower usage. This study highlights the complexity of these paradoxical effects and suggests that public health strategies need to go beyond simple education and knowledge-based interventions. Targeted approaches should address industry messaging, challenge misconceptions, and strengthen regulatory efforts to reduce e-cigarette use among young adults, including those from higher SES backgrounds.

<b>Background:</b> As a central component of the brain's reward system, nucleus accumbens (NAcc) plays a crucial role in reward salience and substance use behaviors. Changes in the NAcc are also relevant to higher rates of substance use of youth and adults from low-income backgrounds. Although resting-state functional connectivity (rsFC) of the NAcc provides valuable insights into the neural mechanisms underlying reward processing and the propensity for self-reported reward salience and substance use, research exploring the association between NAcc rsFC and brain networks beyond the default mode network (DMN) and prefrontal cortex (PFC) is limited. <b>Objective:</b> To investigate the role of the resting-state functional connectivity of the NAcc with the cingulo-opercular network, sensorimotor mouth network, and sensorimotor hand network in the association between socioeconomic status, self-reported reward salience, and future substance use. <b>Methods:</b> Data were obtained from the Adolescent Brain Cognitive Development (ABCD) study. NAcc rsFC with the cingulo-opercular network, sensorimotor mouth network, and sensorimotor hand network was assessed at baseline. Socioeconomic status was measured using family income. Self-reported reward salience was assessed using validated psychometric scales. Substance use outcomes were tracked longitudinally over the study period. Structural Equation Modeling was employed to examine the covariances between family income, NAcc rsFC, reward salience, and subsequent substance use. <b>Results:</b> Higher baseline family income was positively associated with baseline NAcc rsFC (B = 0.092, p < 0.001) and negatively associated with baseline reward salience (B = -0.040, p = 0.036) and future substance use (B = -0.081, p < 0.001). Baseline NAcc rsFC was strongly and positively associated with reward salience (B = 0.734, p < 0.001) and future substance use up to age 13 (B = 0.124, p < 0.001). Additionally, baseline reward salience was positively associated with future substance use (Covariance = 0.176, p < 0.001). <b>Conclusion:</b> The findings suggest that NAcc rsFC with brain networks beyond the DMN or PFC may contribute to the links between low parental socioeconomic status, reward salience, and substance use risk. Expanding the understanding of NAcc rsFC provides new insights into the neural mechanisms underlying these associations. These results have important implications for developing targeted interventions aimed at preventing substance use, particularly among low-income youth with heightened reward salience. Further research is needed to explore causal pathways and moderating factors influencing these relationships.

<b>Background: </b>Emotional problems have been associated with substance use, yet longitudinal research examining this relationship during childhood and adolescence in large, diverse, community-based samples remains limited.<b> </b><b>Aims: </b>This study investigates the prospective associations between three emotional problems—hopelessness, depression, and suicide attempts—before ages 9–10 and the subsequent initiation of tobacco and marijuana use before ages 14–15, using data from the Adolescent Brain Cognitive Development (ABCD) study.<b> </b><b>Methods: </b>Data from the ABCD study were analyzed. Baseline emotional problems, including hopelessness, depression, and suicide attempts, were assessed at ages 9–10 through structured parent interviews. Substance use outcomes (tobacco and marijuana initiation) were tracked from baseline to follow-up at ages 14–15 using structured self-report measures. Structural Equation Modeling (SEM) was employed to assess the predictive roles of these early-life emotional problems, controlling for potential confounders such as demographic factors and family and neighborhood socioeconomic status.<b> </b><b>Results: </b>Baseline hopelessness, depression, and suicide attempts at ages 9–10 were significant predictors of tobacco and marijuana use initiation at ages 14–15. These associations remained robust after adjusting for confounders, indicating the independent effects of early emotional problems on adolescent substance use initiation.<b> </b><b>Conclusions: </b>Emotional problems in early childhood, including hopelessness, depression, and suicidal behavior, are critical predictors of substance use initiation during adolescence. These findings underscore the importance of early identification and targeted mental health interventions to reduce the risk of substance use among vulnerable youth.

<b>Objective: </b>This study investigates the pathways linking socioeconomic status (SES), trauma, early puberty, and tobacco use, with a focus on how these relationships differ by sex. Using data from the Adolescent Brain Cognitive Development (ABCD) study, we explore how SES and race contribute to trauma exposure, which in turn may influence early puberty and tobacco use. The study also examines potential mediating effects of trauma and early puberty on the association between SES and tobacco use, while comparing these pathways for males and females.<b> </b><b>Methods: </b>Data were drawn from the ABCD study, and structural equation modeling (SEM) was employed to test direct and indirect pathways between SES, trauma, early puberty, and tobacco use. The sample was stratified by sex to assess differences in these relationships for males and females. Key predictors included SES, race, and age, while outcomes were trauma, early puberty, and tobacco use. The model assessed mediating effects of trauma and early puberty on tobacco use.<b> </b><b>Results: </b>Trauma was a significant predictor of early puberty for females (B = 0.032, SE = 0.015, p = 0.039) but not males. Early puberty was significantly linked to tobacco use for females (B = 0.048, SE = 0.015, p = 0.001) but not for males. Additionally, trauma had an effect on tobacco use among females (B = 0.048, SE = 0.014, p < 0.001) but not males.<b> </b>Lower SES was significantly associated with higher trauma exposure for both males (B = -0.109, SE = 0.014, p < 0.001) and females (B = -0.110, SE = 0.015, p < 0.001). <b>Conclusions: </b>The findings suggest that trauma and early puberty play more significant roles in the pathways from SES to tobacco use for females than for males. While trauma and early puberty are crucial mediators for females, these factors are less predictive for males. These results highlight the importance of sex-specific interventions targeting trauma and early puberty as pathways to early tobacco use.

Background:</b> Early life socioeconomic conditions and race/ethnicity are critical determinants of long-term health and behavioral outcomes. Epigenetic changes, particularly those measured by the GrimAge biomarker, may mediate the impact of these early adversities on later life outcomes. This study investigates the relationships between race/ethnicity, poverty at birth, epigenetic aging at age 15, and subsequent self-rated health, school discipline, depression, and school dropout at age 22. We explored sex differences in these paths. <b>Methods:</b> Data were drawn from the Fragile Families and Child Wellbeing Study (FFCWS), which included 733 youth with comprehensive follow-up data up to age 22. Structural Equation Modeling (SEM) was employed to assess the pathways from race/ethnicity and poverty at birth to epigenetic aging (GrimAge) at age 15, and subsequently to self-rated health and school discipline at age 22. The model controlled for potential confounders including sex, family structure, and parental education. <b>Results:</b> Race/ethnicity and poverty at birth were significantly associated with higher GrimAge scores at age 15 (p < 0.05). Higher GrimAge scores were predictive of poorer self-rated health (β = -0.08, p < 0.05) and increased instances of school discipline (β = 0.13, p < 0.01) at age 22. The indirect effects of race/ethnicity and poverty at birth on self-rated health and school discipline through GrimAge were also significant (p < 0.05), suggesting that epigenetic aging partially mediates these relationships. Sex differences were also observed. Poverty at birth predicted faster epigenetic aging at age 15 for males not females. We also observed that faster epigenetic aging at age 15 was predictive of school discipline of male not female participants at age 22. In contrast, faster epigenetic aging at age 15 was predictive of self-rated health (SRH) of female not male participants at age 22. <b>Conclusions:</b> This study provides evidence that with some sex differences, race/ethnicity and poverty at birth contribute to accelerated epigenetic aging (GrimAge) by age 15, which in turn predicts poorer self-rated health and increased school discipline issues by age 22. These findings emphasize the importance of early interventions targeting social determinants to mitigate long-term health and behavioral disparities. Addressing these early life conditions is crucial for improving health equity and outcomes in young adulthood.

Intersectionality has significantly enhanced our understanding of how overlapping social identities—such as race, ethnicity, gender, sex, class, and sexual orientation—interact to shape individual experiences. However, despite its theoretical importance, much of the existing literature has relied on qualitative approaches to define and study intersectionality, limiting its application in predictive modeling, comparative analysis, and policy development. This paper introduces the concept of Quantitative Intersectionality Scoring System (QISS), a novel approach that assigns numerical scores to intersecting identities, thereby enabling a more systematic and data-driven analysis of intersectional effects. We argue that QISS can substantially enhance the utility and predictive validity of quantitative models by capturing the complexities of multiple, overlapping social determinants. By presenting concrete examples, such as the varying impacts of socioeconomic mobility on life expectancy among different intersectional groups, we demonstrate how QISS can yield more precise and reliable forecasts. Such a shift would allow policymakers and service providers to dynamically assess economic and health needs, as well as the uncertainties around them, as individuals move through different social and economic contexts. QISS-based models could be more responsive to the complexities of intersecting identities, allowing for a more quantified and nuanced evaluation of policy interventions. We conclude by discussing the challenges of implementing QISS and emphasizing the need for further research to validate these quantifications using robust quantitative methods. Ultimately, adopting QISS has the potential to improve the accuracy of predictive models and the effectiveness of policies aimed at promoting social justice and health equity.

High-Performance Computing (HPC) is indispensable for large-scale scientific simulations, but achieving optimal performance on modern supercomputers is increasingly challenging. As HPC systems scale toward exascale, they face escalating complexity in hardware, software, and workloads. Traditional optimization methods (manual tuning and heuristic algorithms) struggle to cope with dynamic workloads and intricate system behaviors. Artificial Intelligence (AI) techniques offer a promising approach to address these challenges. This article provides an overview of AI-powered optimization in HPC, focusing on how machine learning and related AI methods enhance performance, efficiency, and scalability of scientific simulations. We survey key AI techniques applied to HPC optimization including machine learning for performance modeling, deep reinforcement learning for resource management, and AI-driven surrogate models for accelerating simulations and illustrate their impact through case studies in domains such as job scheduling and fluid dynamics. We discuss the practical applications of these techniques, highlighting reported performance gains (e.g., substantial reductions in simulation run time and improved resource utilization). We also examine the challenges in integrating AI with HPC (such as training overhead, data movement, and reliability concerns) and outline future directions for research. The convergence of AI and HPC is poised to produce “smart” simulation workflows that intelligently adapt and optimize in real time, pushing the frontiers of scientific computing.

The management of supply chains is increasingly complex. This study provides a comparative analysis of the cost-benefit analysis for managing various risks. It identifies the financial implications of leveraging artificial intelligence in supply chains to better address risk. Empirical results show a business case for managing some sources of risk more proactively facilitated through predictive modeling techniques offered by AI. Across investigation streams, the use of AI results in an average total cost saving ranging from 41,254 to 4,099,617. Findings from our research can be used to inform managers and theorists about the implications of integrating AI technologies to manage risks in the supply chain. Our work also highlights areas for future research. Given the growing interest in studying sub-second forecasting, our research could be a point of departure for future investigations aimed at considering the impact of forecasting horizons such as an intra-day basis. We formulate a conceptual framework that considers how and to what extent performance evaluation metrics vary according to differences in the fidelity of predictive models and factor importance for identifying risks. We also utilize a mixed-method approach to demonstrate the applicability of our ideas in practice. Our results illustrate the financial implications of integrating AI predictive tools with business processes. Results suggest that real-world companies can circumvent inefficiencies associated with trying to manage many classes of risk via the use of AI-enhanced predictive analytics. As managers need to justify investment to top management, our work supports decision-making by providing a means of conducting a trade-off analysis at the tactical level.

Progress in the development and adoption of technological innovations is instrumental in enhancing the efficiency of production systems across the globe. Through the introduction of cost-efficient and high-performing technologies, countries can both reduce the resource use intensity of their economies and boost the global supply of essential products. The focus of this study is to analyze the application of advanced machinery and mechanisms within the agricultural sector, a primary industry that acts as a major contributor to the gross domestic product (GDP) of many nations. Specifically, this paper provides an in-depth review of the latest impact assessments based on analytical and modeling tools conducted on agricultural machinery and production technologies. Our findings highlight the positive role played by scientific progress and innovation in driving the competitiveness, growth and improved sustainability of the agricultural sector. Over the years, advanced technologies have accelerated the development and modernization of machinery, equipment, and processes in farming. Typically, modern machinery and equipment have enabled large-scale production on farms, enhancing the cost-efficient use of both land and labor, as well as the capacity and timeliness in performing essential agricultural operations. The rapid diffusion of technical advancements has further contributed to resource savings, productivity growth, and the overall transformation of agricultural value chains. Accordingly, the implementation of appropriate enabling conditions is of vital importance in encouraging the widespread integration of technologies in agriculture, not only boosting productivity along the agri-food chain but also yielding widespread social, economic, and environmental benefits.

The price of grains like maize and sorghum is subject to significant fluctuations, which can have a significant impact on a country's economy and food security. The aim of the study is to model sorghum and maize price volatility in Nigeria. The data utilized in the study was extracted from World Bank Commodity Price Data (WBCPD), 2022. The data consists of monthly prices in nominal US dollars for maize and sorghum from January 1960 – August 2022. The Autoregressive Conditional Heteroskedasticity (ARCH) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models were utilized for capturing the two-grain price volatility. Two types of conditional heteroscedastic models exist, the first group uses exact functions to control the evolution of , while the second group describes with stochastic equations. It is inferred from the result that inherent uncertainties and fluctuations existed in the prices of maize and sorghum in Nigeria which implies that the price volatility is positive and statistically significant suggesting that historical information and past shocks play a crucial role in determining the volatility observed in the grains. It is recommended that the ARCH, GARCH, EGARCH, TGARCH, PARCH, CGARCH, and IGARCH models should be employed for modeling and managing the volatility of maize and sorghum prices in Nigeria. These models have shown effectiveness in capturing different aspects of volatility, including the impact of past shocks, conditional volatility, asymmetry, and other relevant factors.

The accurate estimation of Individual Wave Components (IWC) is crucial for automated diagnosis of the human digestive system in a clinical setting. However, this process can be challenging due to signal contamination by other signal sources in the body, such as the lungs and heart, as well as environmental noise. To address this issue, various denoising techniques are commonly employed in bowel sound signal processing. While denoising is important, it can increase computational complexity, making it challenging for portable devices. Therefore, signal processing algorithms often require a trade-off between fidelity and computational complexity. This study aims to evaluate an IWC parameter extraction algorithm that was previously developed and reconstruct the IWC without denoising using synthetic and clinical data. To that end, the role of a reliable model in creating synthetic data is paramount. The rigorous testing of the algorithm is limited by the availability of quality and quantity recorded data. To overcome this challenge, a mathematical model has been proposed to generate synthetic bowel sound data that can be used to test new algorithms. The proposed algorithm’s robust performance is evaluated using both synthetic and clinically recorded data. We perform time-frequency analysis of original and reconstructed bowel sound signals in various digestive system states and characterize the performance using Monte Carlo simulation when denoising is not applied. Overall, our study presents a promising algorithm for accurate IWC estimation that can be useful for predicting anomalies in the digestive system.

The decision to choose between onsite and offsite construction is important in the effort toward sustainable construction. Offsite construction is often promoted as an environmentally friendly approach to construction operations. However, previous studies have shown that there is a lack of clarity on the environmental trade-offs between onsite and offsite construction. Factors that can affect the decision to build onsite or offsite include the availability of a local offsite manufacturing facility, the distance of the offsite factory to the final place of use, the proximity of the site to the local supply of material and labor, etc. This study provides a framework to apply the system dynamic modeling technique to evaluate how various factors can affect the environmental impact of the building construction phase (for onsite or offsite construction methods). The system dynamic model (using Vensim software) that was developed provides a platform that allows users to input variables such as the distance that is expected for transportation of labor, material, and equipment to both the onsite facility and the offsite construction location, factors associated with the use of equipment for construction, the distance needed for transportation of building panels or modules from the offsite facility to the final site, etc. Among other things, the model showed that an increase in the distance from the offsite yard to the final construction site increases the total impacts of transportation of completed modules. An increase in the number of trips for the transportation of material to the onsite construction location increases the total impact of onsite construction. In terms of the environmental impact of construction, none of the two methods of construction gives an absolute superiority over the other. The environmental performance of offsite and onsite depends on various associated factors. It is recommended that building practitioners review various factors that are peculiar to their projects to make an informed decision on the best construction methods.

The effects on the elderly are disproportionately Alzheimer’s disease (AD) is one of the most prevalent and chronic types of dementia. Alzheimer's disease (AD), a fatal illness that can harm brain structures and cells long before symptoms appear, is currently incurable and incurable. Using brain MRI pictures from a publicly accessible Kaggle dataset, this study suggests a prediction model based on Convolutional Neural Networks (CNNs) to help with the early detection of Alzheimer's disease. Four levels of dementia have been applied to the 6,400 photos in the collection: not demented, slightly demented, moderately demented, and considerably mildly demented. Pixel normalization, class balancing utilizing data augmentation techniques, and picture scaling to 128×128 pixels were all part of a thorough workflow for data preparation. To improve the gathering of spatial dependence in volumetric MRI data, a 3D convolutional neural network (CNN) architecture was used. We used important performance measures including F1-score, recall, accuracy, precision, and log loss to gauge the model's effectiveness. A review of the available data indicates that the total F1-score, accuracy, recall, and precision were 99.0%, 99.0%, and 99.38%, respectively. The findings demonstrate the model's potential for practical use in early AD diagnosis and establish its robustness with the help of confusion matrix analysis and performance curves.

Today, the presentation of a three-dimensional model of real-world features is very important and widely used and has attracted the attention of researchers in various fields, including surveying and spatial information systems, and those interested in the three-dimensional reconstruction of buildings. The building is the key part of the information in a three-dimensional city model, so extracting and modeling buildings from remote sensing data is an important step in building a digital model of a city. LiDAR technology due to its ability to map in all three modes of one-dimensional, two-dimensional, and three-dimensional is a suitable solution to provide hyperspectral and comprehensive images of the building in an urban environment. In this review article, a comprehensive review of the methods used in identifying buildings from the past to the present and appropriate solutions for the future is discussed.

The future of e-money is crypocurrencies, it is the decentralize digital and virtual currency that is secured by cryptography. It has become increasingly popular in recent years attracting the attention of the individual, investor, media, academia and governments worldwide. This study aims to model and forecast the volatilities and returns of three top cryptocurrencies, namely; Bitcoin, Ethereum and Binance Coin. The data utilized in the study was extracted from the higher market capitalization at 31^st December, 2021 and the data for the period starting from 9^th November, 2017 to 31^st December 2021. The Generalised Autoregressive conditional heteroscedasticity (GARCH) type models with several distributions were fitted to the three cryptocurrencies dataset with their performances assessed using some model criterion tests. The result shows that the mean of all the returns are positive indicating the fact that the price of this three crptocurrencies increase throughout the period of study. The ARCH-LM test shows that there is no ARCH effect in volatility of Bitcoin and Ethereum but present in Binance Coin. The GARCH model was fitted on Binance Coin, the AIC and log L shows that the CGARCH is the best model for Binance Coin. Automatic forecasting was perform based on the selected ARIMA (2,0,1), ARIMA (0,1,2) and the random walk model which has the lowest AIC for ETH-USD, BNB-USD and BTC-USD respectively. This finding could aid investors in determining a cryptocurrency's unique risk-reward characteristics. The study contributes to a better deployment of investor’s resources and prediction of the future prices the three cryptocurrencies.