Prediction-based Decisions & Planning

The U.S. healthcare system struggles with heavy administrative burdens, with medical coding as a significant source of inefficiency and cost. This paper develops an analysis of the potential for artificial intelligence (AI) and automation to drive the evolution of medical coding methodologies. This paper discusses the underlying technologies, such as machine learning (ML), natural language processing (NLP), deep learning, and generative AI, that automate the assignment of code from unstructured clinical documents. The primary objective is to examine the impact of these tools on coding accuracy, coder productivity, revenue cycle management, and, in the process, regulatory adherence. By conducting an industry-based systematic review of peer-reviewed literature, industry reports, and recorded case studies, this paper identifies significant positive outcomes, including a substantial reduction in claim denial rates, increased coding throughput, and faster revenue velocity. It also examines what is wrong with it, including the persistence of algorithmic bias, major data privacy issues, extreme job displacement and evolution, and the urgent need for more flexible regulatory frameworks. The results provide evidence that AI represents a paradigm shift for medical coding: successful integration requires a strategic approach that addresses both technical and ethical considerations. From systematic and principled consideration of human-centered approaches toward data quality and data cleansing, the paper ends with the idea that AI-aided automation will revolutionize the human-coder dynamic toward a new role, moving coding from a role of repetitive task to one more complex in the case review, audit, and documentation integrity in clinical documentation system thus enhancing efficiency and quality of the processing of data, which is the heart and soul of the healthcare system.

Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bottleneck when there is a shortage of medical practitioners, and the images must be manually processed. In such a situation, there is a need to reduce the amount of manual work by automating part of the analysis. In this study, we investigate the potential of a machine-learning algorithm for trauma detection in medical image processing. A new method called ResNet50V2 was developed on the trauma dataset to detect trauma disease. We compare the results of the new method analysis with other state-of-the-art networks. The proposed base model, ResNet50V2, received a score of 99.40%.

In today's expanding and densely populated world, it's crucial to design an automatic intelligent garbage sorter machine that uses advanced sensors. Garbage picture classification is a fundamental computer vision problem that must be solved before sensors can be included in this system. This research presents a model for autonomous trash classification using deep learning that can be applied in high-tech garbage sorting equipment. The 2,527 photos in the rubbish dataset are categorized into six types: trash, cardboard, glass, metal, paper, and plastic. The next step is the creation of GD-DLM, a deep learning model for garbage categorization that is an upgrade from Xception and DenseNet121 models. At last, the tests are run to evaluate GD-DLM against the best-of-breed approaches to garbage classification. The suggested Xception and DenseNet-121 models scored 92.11% and 88.63%, respectively, compared to the baseline accuracy.

Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bottleneck when there is a shortage of medical practitioners, and the images must be manually processed. In such a situation, there is a need to reduce the amount of manual work by automating part of the analysis. In this study, we investigate the potential of a machine-learning algorithm for trauma detection in medical image processing. A new method called ResNet50V2 was developed on the trauma dataset to detect trauma disease. We compare the results of the new method analysis with other state-of-the-art networks. The proposed base model, ResNet50V2, received a score of 99.40%.

In today's expanding and densely populated world, it's crucial to design an automatic intelligent garbage sorter machine that uses advanced sensors. Garbage picture classification is a fundamental computer vision problem that must be solved before sensors can be included in this system. This research presents a model for autonomous trash classification using deep learning that can be applied in high-tech garbage sorting equipment. The 2,527 photos in the rubbish dataset are categorized into six types: trash, cardboard, glass, metal, paper, and plastic. The next step is the creation of GD-DLM, a deep learning model for garbage categorization that is an upgrade from Xception and DenseNet121 models. At last, the tests are run to evaluate GD-DLM against the best-of-breed approaches to garbage classification. The suggested Xception and DenseNet-121 models scored 92.11% and 88.63%, respectively, compared to the baseline accuracy.

The prevailing model of memory as a linear, archival storage system is fundamentally inadequate to explain the dynamic, associative, and instantaneous nature of recall. This paper introduces and validates a novel theoretical framework: the Dynamic-Holographic-Implicit (DHI) Memory Model, which reconceptualizes memory not as a stored record, but as a living, non-linear fabric woven from sensory, emotional, and contextual threads. We posit that this fabric exists within a non-chronological state-space manifold, where recall operates through hologenic projection. Empirical validation is drawn from three distinct cohorts: 1) Clients with Trauma, where trauma cues trigger full-body re-experiencing via hyper-consolidated DHI pathways, bypassing declarative recall; 2) Psychedelic users, in whom substances like psilocybin, LSD and MDMA induce a temporary dissolution of default mode network integrity, leading to vivid, non-linear access to autobiographical and transpersonal memory networks, thereby providing direct evidence for state-dependent DHI malleability; 3) Behavioral expressions in dementia patients, where preserved musical and olfactory DHIs sustain identity and emotional responsiveness despite hippocampal degeneration; and 4)Behavioural Design in Business Leaders with meditative process in whom Dhyana happens for focusing Authentic Identity, demonstrating the traitcrystallized nature of sensory-emotional memory. These case studies provide a robust evidentiary base for the model's core principles. The implications are profound, revolutionizing therapeutic and design intervention into a process of re-weaving the mnemonic fabric. Protocols leveraging timed trigger exposure during neuroplastic windows (informed by psychedelic reconsolidation studies) and somatic techniques offer novel pathways for healing trauma and enhancing cognition. Furthermore, this evidence base necessitates a new ethical paradigm to address the risks of false memory implantation and the potential for culturally exploitative applications of DHI mechanisms. This paper establishes the DHI Memory Model as a foundational, empirically-grounded paradigm shift, arguing that understanding the holographic fabric of memory is essential for advancing a holistic science of cognition.

The prevailing model of memory as a linear, archival storage system is fundamentally inadequate to explain the dynamic, associative, and instantaneous nature of recall. This paper introduces and validates a novel theoretical framework: the Dynamic-Holographic-Implicit (DHI) Memory Model, which reconceptualizes memory not as a stored record, but as a living, non-linear fabric woven from sensory, emotional, and contextual threads. We posit that this fabric exists within a non-chronological state-space manifold, where recall operates through hologenic projection. Empirical validation is drawn from three distinct cohorts: 1) Clients with Trauma, where trauma cues trigger full-body re-experiencing via hyper-consolidated DHI pathways, bypassing declarative recall; 2) Psychedelic users, in whom substances like psilocybin, LSD and MDMA induce a temporary dissolution of default mode network integrity, leading to vivid, non-linear access to autobiographical and transpersonal memory networks, thereby providing direct evidence for state-dependent DHI malleability; 3) Behavioral expressions in dementia patients, where preserved musical and olfactory DHIs sustain identity and emotional responsiveness despite hippocampal degeneration; and 4)Behavioural Design in Business Leaders with meditative process in whom Dhyana happens for focusing Authentic Identity, demonstrating the traitcrystallized nature of sensory-emotional memory. These case studies provide a robust evidentiary base for the model's core principles. The implications are profound, revolutionizing therapeutic and design intervention into a process of re-weaving the mnemonic fabric. Protocols leveraging timed trigger exposure during neuroplastic windows (informed by psychedelic reconsolidation studies) and somatic techniques offer novel pathways for healing trauma and enhancing cognition. Furthermore, this evidence base necessitates a new ethical paradigm to address the risks of false memory implantation and the potential for culturally exploitative applications of DHI mechanisms. This paper establishes the DHI Memory Model as a foundational, empirically-grounded paradigm shift, arguing that understanding the holographic fabric of memory is essential for advancing a holistic science of cognition.

Early Detection: AI analyzes vast data; detecting subtle disease cues (cancer, TB) for earlier, proactive interventions and improved outcomes. Beyond Individuals: AI scans populations, predicting outbreaks and risk factors, guiding resource allocation and prevention strategies. Personalized Care: AI tailors treatment plans based on unique patient data, maximizing efficacy, minimizing side effects, and acting as a trusted medical advisor. Challenges & Solutions: India's booming tech scene positions it to tackle data privacy, infrastructure, and ethical concerns through AI research, data infrastructure upgrades, and strong ethical frameworks. Overall Impact: Unleashing AI's potential can revolutionize India's healthcare, ensuring brighter, more equitable future for millions.

 Introduction: Health entrepreneurship is an emerging field with the potential to transform healthcare delivery through innovative products and services. As the healthcare sector faces escalating challenges, the demand for entrepreneurial solutions has intensified.  Objectives: This article aims to define health entrepreneurship, analyze its evolution in response to contemporary healthcare challenges, examine influencing factors, and highlight the importance of collaboration and social responsibility in fostering innovative health solutions.  Method of Literature Review: A comprehensive literature review was conducted using academic databases to analyze peer-reviewed articles, systematic reviews, and case studies related to health entrepreneurship, focusing on its impact on healthcare delivery.  Discussion: Health entrepreneurship encompasses diverse sectors, including telehealth and health IT, driven by the need for quality care, cost reduction, and operational efficiency. Collaborative efforts among stakeholders enhance innovation and scalability, while the integration of advanced technologies significantly improves patient outcomes.  Conclusion: Health entrepreneurship represents a transformative force that addresses critical healthcare challenges and promotes equity. Ongoing research and collaborative initiatives are essential for sustaining these efforts, ultimately leading to a more effective and equitable healthcare system.

This study investigates the impact of modern technology on photographic memory among university students at African Rural University, focusing on how digital tools influence memory retention and recall. Utilizing a mixed-methods approach, the research combines quantitative memory assessments with qualitative interviews and surveys to explore students' experiences and perceptions. Findings indicate a complex relationship where extensive technology use-particularly smartphones correlate with diminished self-reported memory confidence and recall capabilities. Despite acknowledging that technology may hinder their innate memory abilities, students often rely on these tools for academic success. Visual and auditory memory tests revealed that many participants struggled with detailed recall, reinforcing concerns about cognitive overload. The study concludes that while technology offers organizational benefits, it may simultaneously impair natural memory functions, highlighting the need for balanced technology integration in educational practices. Recommendations include training on memory strategies, practice sessions, and promoting active recall techniques to enhance memory retention amidst technological reliance. Future research should explore the long-term effects of technology use on memory development.

Myocarditis is a rare but key adverse event linked to mRNA COVID-19 vaccines, predominantly in young males. Epidemiological data indicate an incidence of approximately 12.6 cases per million doses administered to patients aged 12-39 years, mostly following the second dose of the vaccine. Most patients present with elevated levels of cardiac biomarkers, chest pain, and abnormal ECG findings within a few days of vaccination. Proposed mechanisms for the exact pathophysiology of this include molecular mimicry between the SARS-CoV-2 spike protein and cardiac antigens, activation of immune pathways, and dysregulated cytokine expression. Despite these findings, the overall benefit-risk balance for COVID-19 vaccination remains positive, as the majority of patients recover fully. In contrast, COVID-19-associated myocarditis is more common and more severe, with an estimated incidence of 1,000-1,400 cases per 100,000 infections. Clinical presentation of vaccine-associated myocarditis is usually mild and self-limiting, and most patients do recover without significant long-term effects. Treatment is usually supportive in nature and has an emphasis on ruling out acute coronary syndrome and symptomatic management for heart failure or arrhythmias if present. Given its low incidence and the generally good outcome, vaccination against COVID-19 is recommended from 12 years of age and above, with provision for ongoing surveillance for monitoring and management of rare adverse events like myocarditis.

Human Resource Management (HRM) has evolved from an administrative function to a strategic driver of organizational success. This paper examines HRM's critical role in talent management, leadership, and organizational resilience, supported by empirical evidence and real-world case studies. It explores how HRM adapts to challenges such as the COVID-19 pandemic, the Fourth Industrial Revolution (4IR), and the VUCA (Volatility, Uncertainty, Complexity, Ambiguity) environment. Drawing on peer-reviewed research and corporate examples, this study provides actionable insights for HR professionals to enhance employee engagement, compliance, and innovation.

The frequency and risk of flash floods in Ozoro have increased due to climate change and intense rainfall events. The territory was divided into five preexisting communities throughout the three-month research period, which ran from July to September 2023. Measurements were made to ascertain the flood's volume, area, length, and depth. Using a regular rain gauge with a moveable geo-referenced device, rainfall data was gathered. The rainfall total for July 2023 dropped to 6732.6 mm, and by September of the same year, it further reduced to 1121.5mm. This resulted in a flood that covered an area of 6435m 2 and had a volume of 14431.4m 3. The neighbourhood that experienced the highest level of flooding was Oruamahdu Quarters, with an average depth of 0.6 metres. The average rainfall rate is 89.7 millimetres per hour, suggesting heavy rainfall. The most return rainfall occurred in July, while the least amount occurred in August. The calculated F value of 77.34 indicates a substantial correlation between the volume of rainfall and the flood volume in Ozoro. Flood flow decreased at a rate of 11.57 m3/day over the study period. In Ozoro, the increasing intensity of rainfall is responsible for 85.6% of floods. To help city planners visualise the combined dangers of floods and drainage, the rainfall intensity-durationfrequency (IDF) curve should be employed as a metric for climate adaptation.

This paper presents a novel approach to predictive Ischemic brain stroke analysis using game theory and machine learning techniques. The study investigates the use of the Shapley value in predictive Ischemic brain stroke analysis. Initially, preference algorithms identify the most important features in various machine learning models, including logistic regression, K-nearest neighbor, decision tree, support vector machine (linear kernel), support vector machine ( RBF kernel), neural networks, etc. For each sample, the top 3, 4, and 5 features are evaluated and selected to evaluate their performance. The Shapley Value method has been used to rank the models using their best four features based on their predictive capabilities. As a result, better-performing models have been found. Afterward, ensemble machine learning methods were used to find the most accurate predictions using the top 5 models ranked by shapely value. The research demonstrates an impressive accuracy of 92.39%, surpassing other proposed models' performance. This study highlights the utility of combining game theory and machine learning in Ischemic brain stroke prediction and the potential of ensemble learning methods to increase predictive accuracy in Ischemic stroke analysis.

In recent years, various state of the art autonomous vehicle systems and architectures have been introduced. These methods include planners that depend on high-definition (HD) maps and models that learn an autonomous agent's controls in an end-to-end fashion. While end-to-end models are geared towards solving the scalability constraints from HD maps, they do not generalize for different vehicles and sensor configurations. To address these shortcomings, we introduce an approach that leverages lightweight map representations, explicitly enforcing geometric constraints, and learns feasible trajectories using a conditional generative model. Additional contributions include a new dataset that is used to verify our proposed models quantitatively. The results indicate low relative errors that can potentially translate to traversable trajectories. The dataset created as part of this work has been made available online. 1

We introduce Argoverse 2 (AV2) -a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry -sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license. In the last two years, the Argoverse team has hosted six competitions on 3D tracking, stereo depth estimation, and motion forecasting. We maintain evaluation servers and leaderboards for these tasks, *Equal contribution. † Work completed while at Argo AI. 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks.

This research explores the traditional handloom weaving sector of Tamil Nadu, a cornerstone of the state's cultural identity and rural economy. The study investigates the socioeconomic conditions of weavers, examines the challenges faced in sustaining this ancient craft, and analyzes the role of government initiatives and modern interventions. With data collected from key handloom clusters, the research emphasizes the importance of preserving this heritage while proposing strategies for modernization and sustainable development.

Effective land use and land cover (LULC) change assessment requires tools to measure past, current, and based on them to create a future scenario. LULC changes are unavoidable in the world, particularly in developing countries. Since LULC are too dynamic and complicated without the identification of appropriate methods and approaches the future perdition will be less accurate. Therefore, the integrated Cellular Automata Markov chain (CA-Markov) model is known as a capable estimator. In this study, LULC changes in Zarriné-R ū d River Basin (ZRB) in Iran was analyzed based on different images and data extracted from satellite data in 1989 and 2019 to create the LULC scenario in 2049. The model was validated using actual and projected to 2019. The overall agreement on two extracted maps was 97.85% in 1989 and 96.55% in 2019. The more detailed analysis of validation of calibration based on the kappa showed the highest data reliability of 0.98 in 1989 and 0.95 in 2019, respectively. According to the transition matrix of probabilities, the most significant changes in the ZRB based on the past scenario is in rainfed and built up land classes of LULC in 2049. Concurrently, the other classes continue to decline except irrigated agriculture and water bodies. The results obtained showed that the pasture and mountain LULC class had continued to reduce more than other classes. Furthermore, water resources and the amount of the precipitation in past and future are important to spatial and temporal expansion on LULC classes. ✩ I am submitting a contribution titled: "Predicting spatial and decadal of land use and land cover change using integrated cellular automata Markov chain model based scenarios (2019-2049) Zarriné-R ū d River Basin in Iran ".

Over the past years, humans have directly or indirectly affected the Earth's surface through various activities. These changes in terrestrial ecosystems are closely linked with the issue of the sustainability of socioeconomic development since they affect essential parts of our natural capital such as climate, soils, vegetation, water resources and biodiversity. Land Cover has undergone several changes in Cameroon since its independence in 1960. One of the major drivers of this change is urbanization. Uncontrolled, rapid urbanization has had many negative impacts on the center region of Cameroon, around the continuum of its headquarter and in Cameroon metropolises such as anarchical constructions, pollution and traffic congestions. Faced with these urbanization issues, planners need to know the spatiotemporal trends of Land Use Land Cover for the past, present and have predictions of possible future patterns in order to better orient their planning. This is possible through the establishment of Land Use Land Cover maps. Remote sensing and Geographic Information Systems represent a cost-effective method for accomplishing this. In this work, we examine the case of Monatélé, a growing city around the Yaoundé metropolis. Satellite images from 2010, 2017, 2022 were downloaded and classified into five classes using the Support Vector Machine algorithm of image classification. It was found that between 2010 and 2022, settlements have increase continuously from 1.61% to 4.28%, water has decreased continuously from 9.81% to 6.72%, forest has experienced a net decrease from 73.77% to 68.25%, agriculture has experienced a net increase from 12.44% to 16.92%, while Bare Land has had a net increase from 2.38% to 3.82%. of the total surface area of the subdivision of Monatélé. Predictions made for 2029 and 2035 show that by 2035, settlements would have increased to 6.58%, water would have decreased to 4.58%, forest would have decreased to 61.22%, agriculture will take 25.19%, and bare land would have almost remained unvaried, taking up 2.43% of the surface area from 2010 to 2035. This will represent for Monatélé an increase in anarchical settlements, an increased loss in biodiversity, an increased pollution, an increase in demand for basic commodities, and an increased pressure on natural resources, if no planning measures are put in place, though it may represent an increase in human capital, an increase in local employment opportunities, a reduction of groceries expenditures.

The decline in global biodiversity is a pressing concern due to human activities, leading to millions of species at risk of extinction. East Africa is especially affected by habitat destruction, poaching, and climate change, resulting in significant losses in wildlife populations. Machine learning (ML) has demonstrated potential in identifying species, especially in camera trap images, acoustic recordings, and genetic data. However, there is a need to further explore the use of ML in identifying wildlife species in East Africa. To address this need, we developed ML classification models to identify wildlife species in East Africa. Our dataset included taxonomic features and characteristics of wildlife species from East African countries between 2018 and 2021. We used the random forest algorithm, which is suitable for complex datasets with multiple features. Our evaluation achieved an accuracy of 63.4% and a baseline score of 8.02%, showing the potential of our models in identifying wildlife species in East Africa. Our study could contribute to wildlife conservation by detecting and preventing illegal wildlife trade activities, monitoring population trends, assessing the impact of human activities on different species in East Africa, and preserving biodiversity.

The proliferation of Android devices has resulted in a rise in complex malware specifically designed for these platforms, requiring higher detection techniques beyond conventional static and dynamic analyses. In this study, the Artificial Bee Colony (ABC) algorithm for feature selection is integrated with the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) classifiers to provide a novel method for Android malware detection. The ABC algorithm, which draws inspiration from honeybee foraging behavior, improves the performance of classifiers by balancing exploration and exploitation within feature subsets. Evaluation of the suggested approach on the Debrin Android malware dataset showed significant enhancements in detection accuracy and decreased false positives. The experimental findings demonstrated that both RF and XGBoost classifiers showed excellent performance, with RF slightly surpassing XGBoost in accuracy, precision, recall, and ROC-AUC metrics. The results highlight the efficacy of integrating metaheuristic feature selection with strong classifiers to enhance Android malware detection and tackle the difficulties presented by progressing threats.

The proliferation of Android devices has resulted in a rise in complex malware specifically designed for these platforms, requiring higher detection techniques beyond conventional static and dynamic analyses. In this study, the Artificial Bee Colony (ABC) algorithm for feature selection is integrated with the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) classifiers to provide a novel method for Android malware detection. The ABC algorithm, which draws inspiration from honeybee foraging behavior, improves the performance of classifiers by balancing exploration and exploitation within feature subsets. Evaluation of the suggested approach on the Debrin Android malware dataset showed significant enhancements in detection accuracy and decreased false positives. The experimental findings demonstrated that both RF and XGBoost classifiers showed excellent performance, with RF slightly surpassing XGBoost in accuracy, precision, recall, and ROC-AUC metrics. The results highlight the efficacy of integrating metaheuristic feature selection with strong classifiers to enhance Android malware detection and tackle the difficulties presented by progressing threats.

The purpose of the current study was to analyse and predict of customer sentiment towards real estate organizations using Machine Learning Approaches (ML) approaches. The study employed five ML models to predict customer sentiment toward real estate organizations. The data was collected from Yelp.com and filtered using the "Real Estate" tag. The findings revealed that all four machine learning models effectively classified the review text. The logistic regression (LR) and support vector machine (SVM) models achieved the highest accuracy scores at 93.1 and 93.16, respectively. This study emphasizes the potential of machine learning in improving customer experience and facilitating better decision-making in the real estate industry. The results can guide real estate organizations in understanding customer opinions and preferences, enabling them to make necessary improvements. Additionally, the findings have social implications, as they can enhance products, services, and overall customer experiences, leading to increased satisfaction and trust in the industry.

Artificial intelligence (AI) is transforming cloud analytics and real-time business intelligence (BI), but its rapid evolution has introduced new challenges in scalability, operational efficiency, environmental sustainability, and domain-specific adaptability. As AI models become larger and workloads more complex, businesses must grapple with rising infrastructure costs, latency bottlenecks, and performance degradation when deploying models in fast-paced, data-intensive environments. This paper introduces a unified theoretical framework designed to tackle these challenges through a strategic integration of four core components: Scalability-Efficiency Optimization Framework (SEOF), Edge-Cloud Hybrid Model (ECHM), Green AI Optimization (GAO), and Domain-Specific Tuning (DST).
At the heart of the framework is SEOF, which combines model compression, distributed processing, and serverless deployment to optimize AI systems for responsiveness, cost-effectiveness, and resource efficiency. A new conceptual metric—the Scalability-Efficiency Trade-off Index (SETI)—is proposed to evaluate the interplay between data volume, processing speed, latency, and cloud infrastructure costs. SETI aims to help researchers and practitioners quantify trade-offs and identify optimal system configurations.
ECHM addresses the growing need for low-latency AI services by moving part of the computation to edge devices, enabling faster, localized responses for applications such as real-time retail checkout, healthcare monitoring, and IoT analytics. GAO focuses on reducing the environmental impact of AI by promoting energy-efficient architectures, carbon-aware workload scheduling, and lightweight model deployment strategies—key for organizations aiming to align with sustainability goals. DST ensures that generalized AI models are tailored to industry-specific needs through fine-tuning, transfer learning, and retrieval-augmented methods that enhance accuracy and relevance in domains like finance, healthcare, and logistics.
Backed by insights from over 20 academic and industry sources, this framework offers a comprehensive and adaptable roadmap for building AI systems that are scalable, sustainable, and tuned for real-world business use. By combining theoretical rigor with practical strategies, the paper contributes to the ongoing discourse on how to make AI not only smarter, but also faster, greener, and more context-aware in cloud-based business intelligence systems.

The COVID-19 epidemic commenced in December 2019 in Wuhan, China. In contrast to the Spanish flu pandemic of 1918, the death rate from COVID-19 is merely 5%. The condition is caused by the Severe Acute Respiratory Syndrome Coronavirus 2 strain. In reaction to this catastrophe, several nations have implemented quarantines to mitigate the worldwide dissemination of the COVID-19 virus. COVID-19 vaccines will not be accessible until December 2020. A dependable identification method is essential for the early detection of COVID-19 to preserve humanity. Recent studies indicate that Chest X-ray (CXR) imaging is the most expedient way for diagnosing and classifying COVID-19, and it is also more reliable than Reverse Transcription Polymerase Chain Reaction (RT-PCR) as it yields critical information regarding the coronavirus. Clinical practitioners may initiate treatment at the preliminary stage based on this CXR diagnosis. This article proposes methods for predicting the spread of the COVID-19 pandemic utilizing GLCM-CNN, a deep learning system.

Tuberculosis (TB) is the ninth leading cause of death worldwide. According to WHO at least 1.5 million people each year succumb to TB, thus making it the world's top infectious killer as well as the leading cause from a single infectious agent, ranking above HIV/AIDS. Zambia is one of the top 30 high TB burden countries. People with active TB can infect 5– 15 other people through close contact over the course of a year. TB patients with compromised immune systems, such as people living with HIV, malnutrition or diabetes, or people who use tobacco, have a higher risk of falling ill. Without proper treatment, 45% of HIV-negative people with TB on average and nearly all HIV-positive people with TB will die. Defaulting on TB medication is a major barrier to both local and global TB control. Defaulting increases, the risk of drug resistance, treatment failure, relapse and death, and may prolong infectiousness. Poor adherence to treatment means that
patients remain infectious for longer and are more likely to relapse or succumb to tuberculosis. The rate of anti-TB treatment compliance, adherence and perpetual defaulting TB treatment was and is still high during the intensive phase of treatment.
A qualitative, phenomenological cross-sectional research design was used.
The SPSS package version 23 was applied to conduct quantitative analysis. The proposal was approved by the Chreso University Ethics Clearance Committee and National Health Research Authority.
Researcher ensured confidentially and voluntary participation with informed consent.
The age of the respondents in this study ranged from 18 years to 50 years. Knowledge on TB-related questions was very
high in this study and stood at 87.3%. TB treatment default was found in 34 (32.7%) respondents and was associated with distance to the facility and transport costs, feeling unwell and the drug side effects.
TB treatment default was found in 34 (32.7%) respondents and was associated with distance to the facility and transport
costs, feeling unwell and the drug side effects.

Artificial Intelligence (AI) has become a transformative force in healthcare, particularly in nursing, where it offers innovative
solutions for improving patient care, enhancing clinical decision-making and advancing educational methodologies. This review
explores the current applications of AI in nursing, highlighting its role in clinical practice, education and ethics. By synthesizing
recent literature, we aim to provide an overview of how AI can support the nursing profession in addressing contemporary
challenges and shaping the future of patient care. Additionally, we examine the potential challenges, including data privacy
concerns, ethical dilemmas and the integration of AI into clinical workflows. This paper emphasizes the importance of integrating
AI responsibly and ethically to ensure that its benefits are maximized while minimizing risks to patient care.

The integration of artificial intelligence (AI) in healthcare has revolutionized the prediction and management of cardiac diseases. Given that cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, there is an urgent need for innovative diagnostic methodologies. This paper explores the intersection of AI and cardiac disease prediction, emphasizing machine learning and deep learning applications. By synthesizing existing literature, this study critically evaluates the advantages of AI over traditional diagnostic methods, highlighting improvements in predictive accuracy and personalized treatment strategies. Furthermore, this review addresses methodological inconsistencies and ethical concerns regarding AI deployment in clinical settings. The findings underscore the potential of AI-driven models to enhance early detection and risk assessment in cardiovascular healthcare. However, challenges such as data biases, lack of transparency, and the need for regulatory frameworks must be addressed to harness AI's potential in cardiology fully. This study contributes to the growing discourse on AI in medical diagnostics, offering insights for future research and clinical implementation.

A 2-page article. 
Predictability. 
It would be interesting to see the outcome if AI could create a White Swan Event by looking for the vectors that lead to the predictability and development of a White Swan Event.  A place to start would be to consider the potential of incomplete social theories.

Purpose of the study-The paradigm shift of human resource management (HRM) has changed in the modern era to include a number of innovations and solutions for transitioning to new business models and sources of income. Moreover, human resource management and organizational services are evolving new, fashionable gears. The purpose of this study is to understand the changes and rapidly evolving field of human resource management. Also, understanding the theoretical models and practical applications of paradigm shifts and impacts of Humana Resource Management was the main objective of this research study. Methodology-The secondary source of data was examined in this conceptual study in order to reach a conclusion. For this basic fundamental study data was gathered from peer reviewed journal articles, Reports, and other conference proceedings. Data was gathered using exploratory research questions, then it was analysed, and interpreted using diagrams with relevant information. The practical consequences and the peer reviewed articles were examined in this conceptual background study. Study Findings-The development of new technologies and paradigm shifts offer the chance to enhance what may not have previously worked as well. In the end, HR must continually grow, reskill, upskill, and stay abreast of the most recent innovations. HR Leaders and HR practitioners will need to develop their technological collaboration skills or manage the implementation of automation. Originality/value-This fundamental research fills a knowledge gap about the paradigm change in human resource management. In addition, the study will discover what HR leaders and practitioners should understand about HRM in consideration of the advancement of new technology.

Cardiovascular diseases are a leading cause of death globally, resulting in 17.9 million deaths each year, according to a new report by the World Health Organization. However, with the advancement of technology, machine learning approaches have shown promise in the health industry, providing an opportunity to diagnose and treat heart disease at an earlier stage. In this research project, we aim to build a machine learning model to predict the likelihood of heart disease based on relevant factors. We use a Kaggle heart disease dataset, which includes a comprehensive list of factors related to heart disease, and employ various machine learning algorithms such as Naive Bayes, Support Vector Machine, Random Forest, K-NN, and Decision Tree. Our results indicate that Random Forest provides better prediction accuracy in less time than other machine learning approaches, making it an effective decision support system for medical professionals. This project has the potential to

Automation testing has become indispensable in modern software development, yet it faces challenges due to increasing complexity and rapid software delivery cycles. This paper systematically analyzes how machine learning (ML) techniques are being applied to enhance automation testing processes. The study examines key areas where ML demonstrates promise, including smart test selection, defect prediction, test optimization, and automated debugging. The research synthesizes findings from recent academic literature and industry case studies to provide a holistic view of the current state of ML in automation testing. The paper also discusses implementation challenges, best practices, and future research directions in this emerging field. By providing a comprehensive overview of ML applications in automation testing, this study aims to guide researchers and practitioners in leveraging these techniques to address current challenges and improve testing efficiency and effectiveness.

The rural healthcare system in Nigeria faces significant challenges, including inadequate infrastructure, limited access to specialized care, and a shortage of healthcare professionals. Many people have died on their way while migrating to urban areas in search of medical care. Artificial Intelligence (AI) offers a promising solution by enhancing diagnostic accuracy, improving access to medical care through telemedicine, and enabling real-time monitoring of chronic conditions. AI-driven diagnostic tools can alleviate the strain on healthcare systems by providing faster, more accurate diagnoses and reducing the need for patients to travel long distances for medical attention. AI-powered telemedicine platforms further bridge the gap between rural and urban healthcare, offering real-time consultations and remote monitoring. While these technologies hold significant promise, successful implementation requires collaboration across multiple stakeholders, investments in digital infrastructure, and addressing potential challenges related to algorithmic bias. AI presents a transformative opportunity to revolutionize healthcare delivery in rural Nigeria, improving health outcomes and expanding access to care.

"How to predict crime?" is an important question. But to understand the notions developed by ethnography, entrepreneurships, and timing theories, and to prove they were efficient, it is no enough. To see the future drives the policies and policymakers into a most-of-the-time undesirable situation. In general it is no true that policymakers and entrepreneurs want to believe in the prospections, which it makes very difficult prevention. However, the author develops the "three clocks theory", which is a central issue on the ability of prospection.

Artificial intelligence and robotics are revolutionizing surgical practices by enhancing precision, efficiency, and patient outcomes. With global healthcare systems increasingly adopting AI-driven technologies, the integration of robotics in surgery addresses critical challenges such as surgical accuracy, minimally invasive techniques, and healthcare accessibility. However, disparities in access and ethical concerns regarding automation persist globally, necessitating a balanced discourse on these advancements. The primary objective of the review is to explore the intersection of AI and robotic technologies in surgical practices, highlighting key innovations, their impact on precision medicine, and future trajectories. The novelty of the review lies in synthesizing findings across diverse surgical specialties, including urology, plastic surgery, ophthalmology, and pediatric surgery, to provide a comprehensive understanding of AI's transformative role. The systematic review evaluates the integration of AI and robotics in surgery, synthesizing studies published in 2024. It follows PRISMA guidelines for study selection, data extraction, and synthesis. The review assesses surgical specialties, AI technologies, and outcomes like accuracy, recovery, and complications, ensuring methodological rigor and transparency. The findings indicate substantial advancements in AI-driven surgical systems, improving decision-making, reducing surgical errors, and facilitating personalized treatment strategies. Notable breakthroughs include AI-enhanced imaging, real-time data analysis, and automated robotic instruments, which collectively improve procedural efficiency and patient safety. The discussion emphasizes the critical implications of these innovations, particularly in advancing minimally invasive techniques and expanding surgical capabilities in complex procedures. However, challenges such as cost, ethical considerations, and the need for rigorous training protocols are highlighted as barriers to widespread adoption. The review underscores the implications for policymakers, healthcare institutions, and technology developers to address these barriers and promote equitable access to AI-driven surgical solutions. Limitations include the reliance on recent studies, necessitating long-term evaluations of clinical outcomes. Future research should focus on integrating AI with emerging technologies like augmented reality, fostering interdisciplinary collaboration, and addressing socio-ethical dimensions to fully realize the potential of AI in surgical advancements.

Health is wealth. The maintenance of health is of paramount importance. Due to increasing environmental decay, human health is threatened and therefore requires maintenance. Healthcare providers are few in number and therefore may not be able to cater for everyone. They tend to get fatigued because of the volume of work required on daily basis. This terribly affects their decision making and may lead to death as a result of wrong diagnosis or recommendations. This is the motivation behind this work; design and implementation of a hybrid medical softbot for enhanced decision making. This work was designed with the aid of machine learning algorithms for image analysis and classification and a rule based system that accepts input in the form of symptoms from user to make expert diagnosis and recommendation. Object oriented analysis and design methodology was employed in the analysis and design phase. The result is a hybrid softbot capable of analyzing and classifying X-ray images and giving expert diagnosis for patients.

A heart attack, also known as a myocardial infarction, occurs when the flow of blood to a part of the heart muscle is
suddenly blocked. This blockage prevents the heart from receiving enough oxygen. If blood flow is not promptly
restored, the heart muscle begins to die. Machine learning algorithms are a powerful tool for predicting heart disease,
allowing for more accurate results than traditional methods. Different models are compared and evaluated to identify
the most accurate algorithm. Early detection is key to managing heart disease, and machine learning can help to
identify at-risk individuals. Prevention of heart disease is invaluable for saving lives and reducing medical costs.
Machine learning algorithms can provide the most accurate predictions possible, offering the best chance of preventing
serious health issue

Diabetes mellitus is a chronic metabolic disorder with significant global prevalence and associated healthcare burdens, necessitating early detection and effective management strategies. The integration of Machine Learning (ML) and Artificial Intelligence (AI) has revolutionized diabetes care, offering innovative approaches to prediction, monitoring, and personalized management. This study conducted a systematic review of 82 high-quality peer-reviewed articles, following the PRISMA guidelines, to provide a comprehensive evaluation of ML and AI applications in diabetes prediction and management. The review highlights the widespread adoption of supervised learning models, such as Random Forest and Support Vector Machines (SVM), which consistently demonstrate high accuracy and reliability in predicting diabetes risk. Ensemble learning methods, particularly Gradient Boosting, emerged as superior techniques for predictive performance, while deep learning models, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), proved effective in analyzing unstructured data such as medical images and time-series glucose data. The integration of AI into wearable devices and mobile health applications has further enhanced real-time monitoring and glycemic control, bridging the gap between technological advancements and practical healthcare solutions. Despite these advancements, challenges such as data imbalance, limited external validation, and the need for explainable AI frameworks persist, underscoring the necessity for methodological rigor and standardization. This review provides critical insights into the current state, limitations, and opportunities of ML and AI in diabetes care, emphasizing their transformative potential in addressing this global health challenge.

Employee turnover is a critical challenge for organizations, leading to significant costs and disruptions. This study aims to leverage Machine Learning (ML) techniques within the framework of Human Resources Analytics (HRA) to predict employee turnover effectively. The research evaluates and compares the performance of six widely used models: Decision Trees, Support Vector Machines (SVM), Logistic Regression, Random Forest, XGBoost, and Artificial Neural Networks. These models were implemented using the R programming language on an open-source dataset from IBM. The methodology involved data preprocessing, splitting into training, validation and testing sets, model training, and performance evaluation using metrics such as accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC. The results indicate that the Logistic Regression model outperformed the other models, achieving high accuracy and a good F1-score. The study concludes by emphasizing the importance of HRA and ML techniques in predicting and managing employee turnover, while discussing limitations such as class imbalance and the need for more rigorous performance evaluation. Future research directions include exploring alternative models, feature selection techniques, and addressing class imbalance.

We predict IMDb movie ratings and consider two sets of features: surface and textual features. For the latter, we assume that no social media signal is isolated and use data from multiple channels that are linked to a particular movie, such as tweets from Twitter and comments from YouTube. We extract textual features from each channel to use in our prediction model and we explore whether data from either of these channels can help to extract a better set of textual feature for prediction. Our best performing model is able to ...

Predicting the trajectories of surrounding agents is an essential ability for autonomous vehicles navigating through complex traffic scenes. The future trajectories of agents can be inferred using two important cues: the locations and past motion of agents, and the static scene structure. Due to the high variability in scene structure and agent configurations, prior work has employed the attention mechanism, applied separately to the scene and agent configuration to learn the most salient parts of both cues. However, the two cues are tightly linked. The agent configuration can inform what part of the scene is most relevant to prediction. The static scene in turn can help determine the relative influence of agents on each others motion. Moreover, the distribution of future trajectories is multimodal, with modes corresponding to the agent's intent. The agent's intent also informs what part of the scene and agent configuration is relevant to prediction. We thus propose a novel approach applying multi-head attention by considering a joint representation of the static scene and surrounding agents. We use each attention head to generate a distinct future trajectory to address multimodality of future trajectories. Our model achieves state of the art results on the nuScenes prediction benchmark and generates diverse future trajectories compliant with scene structure and agent configuration.

Coastal zones, important for human settlements and economies globally and particularly in Sri Lanka, are experiencing significant changes driven by natural and human-induced activities. This study investigated the shoreline changes over the southwestern coastal zone between for three periods as; 1988 to 2023, 1988 to 2001 and 2001 to 2023 by calculating the change rates, preparing erosion/accretion maps and predicting future positions for years 2034 and 2044.Landsat images and Normalized Difference Water Index (NDWI) were used for shoreline extraction and Digital Shoreline Analysis System (DSAS) tools was used to calculate change rates and predict future positions.. Findings reveal significant changes over the three study periods. During the 1988-2001 period, the mean Endpoint Rate (EPR) averaged 2.31 m/year, while the mean Linear Regression Rate (LRR) averaged 2.34 m/year. The majority of the study area faced land accretion, with only 200 out of 3,475 transects experiencing erosion. However, during the 2001-2023 period, erosion became predominant at an alarming rate of 62.72%, with 2,192 out of 3,495 transects facing erosion. During this period, the mean EPR and mean LRR shiftedto -0.46 m/year and -0.25 m/year, respectively. During the overall period of 1988-2023, only 404 transects out of 3,422 transects were eroded, with a decreased percentage of 11.81%. The mean EPR was 0.61 m/year, while the mean LRR was 0.52 m/year. Kalutara, Beruwala, Hikkaduwa, Kahawa, and Galle experienced significant erosion, aligning with previous vulnerability assessments. Predictions for 2034 and 2044 suggest a trend towards land accretion, potentially influenced by recent beach nourishment efforts. Even though the erosion rate decreased for the overall period 1988-2023, mitigation measures should be taken, especially for Kalutara, Beruwala, Hikkaduwa, Kahawa, and Galle areas.

What is indigenous African knowledge? Before the coming of Europeans, Africans had a complete way of life. We had ways of farming, medicine, education, security, family life, governance, communication, art, etc. Yes, they could be primitive compared to what colonisers brought to us, but the important thing is that they worked. Even today, there are instances whereby doctors would advise family members to "go home and try traditional medication" when modern medical care does not improve the condition of the patient. Thus, indigenous African knowledge refers to the traditional understanding, wisdom, and practices developed and passed down through generations by African communities based on their experiences, and observations of nature, culture, and environment.

 Background: Type 2 diabetes mellitus poses a momentous challenge when accompanied by psychiatric symptoms like depression, anxiety, and stress, adding to the complaint's threat. Research on these factors in patients with uncontrolled chronic illnesses in India, particularly in Tamil Nadu, is limited. Hence, this study aims to determine the prevalence and risk factors of these psychiatric symptoms among Type 2 diabetes patients.

 Background of the Study: Tuberculosis (TB) is the ninth leading cause of death worldwide. According to WHO at least 1.5 million people each year succumb to TB, thus making it the world's top infectious killer as well as the leading cause from a single infectious agent, ranking above HIV/AIDS. Zambia is one of the top 30 high TB burden countries. People with active TB can infect 5-15 other people through close contact over the course of a year. TB patients with compromised immune systems, such as people living with HIV, malnutrition or diabetes, or people who use tobacco, have a higher risk of falling ill. Without proper treatment, 45% of HIV-negative people with TB on average and nearly all HIV-positive people with TB will die. Defaulting on TB medication is a major barrier to both local and global TB control. Defaulting increases, the risk of drug resistance, treatment failure, relapse and death, and may prolong infectiousness. Poor adherence to treatment means that patients remain infectious for longer and are more likely to relapse or succumb to tuberculosis. The rate of anti-TB treatment compliance, adherence and perpetual defaulting TB treatment was and is still high during the intensive phase of treatment. Most people who are called "lost to follow up" don't have adequate information as to why they should continue and finish their TB medication.  Methodology: A qualitative, phenomenological cross-sectional research design was used. Namuseche Prison Clinic and surrounding compounds of Chipata Township in Eastern Province Zambia. A total of 141 participants was recruited through purposive sampling. In-depth interviews were conducted. The SPSS package version 23 was applied to conduct quantitative analysis. The proposal was approved by the Chreso University Ethics Clearance Committee and National Health Research Authority. Researcher ensured confidentially and voluntary participation with informed consent.  Results: The age of the respondents in this study ranged from 18 years to 50 years. Knowledge on TB related questions was very high in this study and stood at 87.3%. TB treatment default was found in 34 (32.7%) respondents and was associated with distance to the facility and transport costs, feeling unwell and the drug side effects.  Conclusion: TB treatment default was found in 34 (32.7%) respondents and was associated with distance to the facility and transport costs, feeling unwell and the drug side effects.

Time series are often subject to conflicting forces; we refer to these as complex time series. This paper uses of causal forces in order to decompose complex series. In particular, we hypothesized three conditions to be important for effectively decomposing a time series by causal forces: 1) the forecaster has domain knowledge that can not be applied directly to the target series, 2) the domain knowledge can be used to structure the problem so that individual causal forces can be specified for one or more component series, and 3) it is ...

 Background: Type 2 diabetes mellitus poses a momentous challenge when accompanied by psychiatric symptoms like depression, anxiety, and stress, adding to the complaint's threat. Research on these factors in patients with uncontrolled chronic illnesses in India, particularly in Tamil Nadu, is limited. Hence, this study aims to determine the prevalence and risk factors of these psychiatric symptoms among Type 2 diabetes patients.

Taśma przenośnika jest najdroższym elementem przenośnika, a jednocześnie elementem o najniższej trwałości. Decyduje ona o efektywności i niezawodności pracy całego przenośnika oraz kształtowaniu się kosztów transportu zakładowego. Najgroźniejszymi jej awariami są uszkodzenia mechaniczne oraz pożary. Do podstawowych uszkodzeń taśm przenośnikowych podczas ich użytkowania należą [4]: przecięcia podłużne lub poprzeczne taśmy, zerwanie się połączenia klejonego lub mechanicznego, oberwanie obrzeża gumowego i strzępienie się rdzenia taśmy, nadmierne wycieranie się okładki nośnej i bieżnej zerwanie się taśmy, rozwarstwienie się taśmy, zagrzewanie się taśmy przez tarcie o unieruchomione krążniki boczne, zatarte bębny zwrotne, elementy konstrukcji przenośnika.

Fire presents very often occasion, even in the modern world and can cause human victims and very serious destruction in the sense of material properties. So, it is very important to undertake every available potential to protect human lives and material properties. One of the most important procedures in the case of fire and not only fire is evacuation. Generally, evacuation is the safest, the shortest and the fastest way of moving humans, animals and material properties from endanger object/area to the secure location. The evacuation, as a very important way of protection presents always complex and open task that must be constantly improved. The evacuation will not be the same for the different objects, because there are objects with special properties that demand special procedures and actions. One of those objects are health objects. This review paper is written to show the examples of evacuation from different health objects and to present the use of simulation software as a inevitable tool in the evacuation object design.