22505 research outputs found
Sort by
Predicting Employee Attrition with Machine Learning: Data-Driven Strategies for EnhancingWorkforce Retention
No full textIn this research, the dual prediction and prescription model is developed and validated so that this model can not only predict employee turnover risk, but it also proposes the appropriate retention interventions, which apply across industries. On the basis of the IBM HR Analytics Attrition dataset (n=1,470), we preprocessed demography, job and satisfaction variables and trained three machine-learning classifiers, Random Forest, Logistic Regression and XGBoost to predict voluntary turnover. XGBoost model recorded the best discrimination (AUC=0.87), sensitivity (0.76), and specificity (0.81), which signifies strong predictive power. Analysis of feature-importance was conclusive with time, rate of frequent business travel and compensation measures as major causal factors of attrition, but the factors had different levels of prominence per sector, which required a customized approach to intervention. In order to operationalize predictions, we paired the best predictors with evidence-based HR lever and came up with a dynamic monitoring solution that included real-time risk scores and an employee engagement survey to operationalize the prediction. The dataset exhibited class imbalance, with attrition representing a minority proportion of the sample. To address this, model development incorporated ROSE resampling and threshold tuning to improve sensitivity to true leavers, achieving strong discrimination (AUC = 0.95) while reducing false negatives. We have prescriptive recommendations which are specific to different job functions based on how to cope with the workload demands of front office jobs, as well as how to streamline promotion channels within technical divisions, with an A/B testing strategy which would help to improve the effectiveness of applications. The study contributes to the understanding of usingworkforce analytics with a clear example on how predictive analytics lead to implementing actionable HR policies so that attrition becomes not a reactive practice in talent stewardship, but an active one. Future researchers are advised to use longitudinal and post-pandemic data to trace the changing work pattern and include mixed-method implications to draw quantitative results into detail
Assessing the Feasibility of Large-Scale, Selective Aqueous Quadrupole Ion Trap Separation
No full textThe global challenges presented by water and resource scarcity and the drawbacks of the methods designed to resolve them escalate the need for innovative selective ion separation solutions. Environmental concerns, material constraints, high costs, and limited scalability are unavoidable disadvantages that hinder many selective separation technologies. Through its reliance solely on electric field manipulation and its avoidance of hazardous solvents or selective membranes, the quadrupole ion trap in an aqueous environment presents itself as a worthy alternative to contemporary separation methods. This research effort aims to gauge the feasibility of using a large-scale aqueous quadrupole ion trap (i.e. traps with a radius larger than 5 [mm]) for the selective separation of monatomic ions, namely sodium and lithium. The motion of a single ion in both vacuum and fluid-filled environments is reviewed analytically and used to validate models constructed using COMSOL software. Subsequent analysis of sodium and lithium separation indicates that while possible in theory, the practical application of aqueous quadrupole ion traps for monatomic ion separation is infeasible at large scales. Proof-of-concept experimentation using larger charged particles, modified polystyrene microspheres, is then discussed. A device is built and tested, and the results suggest that continued research into aqueous quadrupole ion trapping for selective ion separation is not only justified, but necessary
Potential and Low-Cost Football Talents for UAE Clubs Based on Data-Driven Analysis
No full textThe use of data analytics in professional football has changed the way clubs view, value and invest in players. Meanwhile, elite European teams have consistently exploited the data-driven strategies that offer them a competitive edge, but in up-and-coming football markets, such as the UAE Pro League, nepotism has remained strong, with reputation-based and agentdriven recruitment being the transformation choice of even the biggest profile moves. This work explores whether predictive analytics can discover hidden high-quality football talent from ”hotbeds” of talent including Brazil and Argentina, in a way that matches the economic capabilities of clubs in the UAE, given the constraints of the local league. Amidst increasing transfer fees and uncertain performances, this research investigates not only the theoretically and practically relevant intersections of talent identification, machine learning-based valuation models, and financial risk management. There are two main research questions of interest: (1) What approaches can be used through data-driven models to better estimate player value for regions that receive less attention from scouts? (2) Which performance metrics are best at predicting future market growth and on-field success? (3) What way do clubs fit these models into their strategy process around scouting and investment? We use a mixed-methods approach: supervised learning models that compare past input data to prediction output with statistical regression techniques and datasets fromTransfermarkt andWyscout. A total of 9596 players across various South America leagues were filtered by age, position and the trajectory of their value. These are then measured against UAE clubs for tactical fit and historical markers of success. To validate some observed trends in performance from model recommendations we study case studies. The findings suggest predictive models have utility in making scouting more effective and cost-efficient, and that over years predictive models can offer significant ROI particularly as qualitative scouting and video analysis are integrated with model reccomendations. The paper ends with suggestions on how clubs in the UAE can implement optimal, cost-effective, analytics-based recruitment strategies along with a plea for more research exploring ethical data use, contextual model tuning and cultural suitability in emerging markets
Play of Curiosity: A Table-top Game that Cultivates a Creative Attitude by Encouraging Curiosity in Young Adults
No full textIn a time that increasingly demands instant creativity, adaptability, and innovative thinking on a constant basis, nurturing a curious attitude among young adults must become a critical focus. Creativity and curiosity can be encouraged throughout various stages of life, and for myriads of personality types, the focus demographic of this paper is young adults, ages 18 to 26 years old. Young adulthood is when one starts to recognize post-formal thoughts. This stage of cognitive development helps to approach concepts beyond binary thinking, developing the unique abilities of ambiguous thinking and relativism. The enigmatic, ever-changing, and easygoing mind will often try new and challenging experiences. However, the older we get, the more we settle into our thoughts and beliefs. Employing a well-balanced playful exploration in gamified structures, games can transform routine tasks into enriching opportunities for personal growth and intellectual stimulation. This paper aims to explore the role of playful exploration and gamification in enhancing creative thinking, with an emphasis on designing games that cater to diverse intellectual styles. It investigates how tailored gameplay, supported by theories of creativity, emotional gratification, and gamification can reignite curiosity and enhance creative thinking among young adults. This is tested through dual approaches of engaging strategic and visual intellectual styles, offering practical insights into game design and its broader applications in education, professional development, social interactions, and everyday life
Scout 07
No full textThroughout my tenure at RIT, I have produced multiple short films, undertaken gaming co-ops, and pursued an independent study centered on gaming assets to expand my technical and creative skills. For my thesis film, I sought to merge these experiences by concentrating on environmental storytelling—a deliberate challenge, given faculty concerns that narratives lacking strong character focus may struggle to engage audiences emotionally. With these considerations in mind, I crafted a film featuring a secondary character within a rich environment, designed to immerse viewers and provoke curiosity about the story’s temporal and spatial context
Forecast: A Helmet Visor HUD
No full textHigh-performance track-day driving requires drivers to maintain situational awareness while operating vehicles at high speeds. During these conditions, drivers must continuously monitor track signals, surrounding vehicles, and changing hazards while maintaining precise vehicle control. Missed or delayed recognition of critical information can increase safety risks and disrupt traffic flow on the racetrack. This thesis explores the design of a helmet-mounted visor head-up display (HUD) intended to support experienced track-day drivers by selectively presenting critical information in real time. The system prioritizes contextually relevant alerts and minimizes visual distraction through a simplified visual hierarchy. Hazards are categorized by severity and communicated using brief or persistent visual cues depending on risk level. In addition, the system addresses the point-by passing protocol commonly used in United States track-day events by visually confirming passing signals to reduce ambiguity and hesitation. The contribution of this project is a context-aware visual hierarchy for safety-critical, high-speed driving environments that emphasizes clarity and restraint over continuous data display. The proposed system was developed and evaluated through iterative mock-ups and peer review, focusing on legibility, perceived usefulness, and perceived cognitive demand in track-day scenarios
From Waste to Wall Finish: Developing and Characterizing Sustainable Concrete Finishes with High-Volume Fly Ash and Biochar for Interior Applications
No full textThis study explores the creation of environmentally friendly interior concrete finishes by recycling agricultural and industrial waste. In a 1:3 cementitious-to-aggregate mortar mix, the study investigates high-volume (30%) cement replacement using fly ash (FA30), biochar (BC30), and a hybrid combination (FAB30). It illustrates the viability of converting waste streams into workable architectural finishes through meticulous material investigation, mechanical testing, and aesthetic evaluation. Different performance characteristics were found by the technical examination. FA30 outperformed the control mix with a 14-day compressive strength of 8.00 MPa thanks to pozzolanic activity and decreased water demand. On the other hand, BC30 (7.33 MPa) significantly lost strength due to the large porosity and water absorption of biochar. An intermediate strength of 6.66 MPa was offered by FAB30. Biochar-containing mixtures failed gradually and non-catastrophically, according to failure mode analysis, confirming their suitability for non-structural interior applications. Strong appreciation for each finish\u27s distinctive visual characteristics was found in an aesthetic perception research. The smooth, light-gray FA30 finish was seen as contemporary and polished. The speckled FAB30 finish, which was characterized as natural and energetic, was the most favored overall, while the charcoal-black BC30 finish generated thoughts of drama and luxury. Significant sustainability gains were found in the environmental evaluation: replacing cement resulted in an estimated 105 kg CO₂e per m³. Additionally, mixes that included biochar had an extra ~206 kg CO₂e per m³ sequestration capacity, making them possible carbon sinks. This work suggests a new direction for sustainable interior design by showing how waste-derived materials can offer practical, aesthetically pleasing interior finishes while addressing environmental issues. The findings extend the aesthetic and environmental potential of concrete beyond traditional uses by providing designers and architects with a scientifically supported framework for material choices
Internet of Things (IoT) in Developing Smart City Traffic Management Systems in Dubai
No full textTraffic congestion is an ever-present problem affecting most cities, negatively affecting the economy, the environment, and people’s quality of life. Dubai is one of the rapidly growing cities in terms of urbanization and the usage of technologies, and it is aware of the ability of IoT to design intelligent city traffic control systems to resolve this problem. Consequently, this study sought to assess the implication of IoT in improving traffic management systems within the Emirate of Dubai, gleaning data concerning the factors that have a direct impact on the implementation of the IoT, the challenges, and barriers met during the implementation of the IoT, and the strategies and the best practices associated with the integration of IoT. It also used secondary qualitative collection methods involving synthesizing data from an extensive literature search of academic and industry publications, case studies, and reports. Three main questions guided the research: It is, therefore, against this backdrop that the findings highlighted a range of practitioners’ challenges that span across the technical, organizational, and socio-economic domains, with the challenges specifically being technical challenges such as interoperability, scalability, and data management; organizational challenges like governance and stakeholder collaboration, change management; and socio-economic challenges such as user acceptance, the digital divide, and sociocultural factors. Altogether, the study revealed issues and considerations, including security and privacy, integration problems, regulatory and policy matters, and constraints in cost and resources. The study highlights key approaches and success factors for IoT implementation, including big data and analytics, edge computing, real-time processing, PPP, and new business models. It contributes to understanding IoT adoption for traffic management systems in Dubai, offering valuable insights for policymakers, planners, and related agencies. Recommendations include developing IoT management guidelines, community involvement, capacity building, and incorporating big data and decision-support systems. Future research directions involve pilot studies, exploring advanced technologies and trends, comparative case studies, and examining economic and environmental impacts
Beyond Static Models - A Framework for Evaluating Dynamic ML Approaches in Heart Failure Risk Prediction
No full textHeart failure remains a pressing global health challenge, affecting approximately 64 million people and incurring annual healthcare costs of $108 billion, driven by high readmission rates and delayed interventions. Current risk prediction models predominantly rely on static machine learning approaches, utilizing fixed datasets that fail to adapt to the evolving nature of patient health. This limitation results in outdated risk assessments, hindering timely clinical responses and worsening patient outcomes and resource efficiencies. This research addresses a fundamental methodological gap by developing and validating a chunk-based ensemble framework that enables researchers to evaluate dynamic machine learning potential using readily available static clinical datasets, with synthetic heart failure data serving as a controlled proof-of-concept. Using the Heart Failure Prediction - Clinical Records Dataset from Kaggle, comprising 5,000 synthetic records with 13 clinical attributes, this study addressed two research questions on how a simulation framework can be designed using sequential patient data partitioning, and how within this controlled environment performance compares to traditional static approaches. The methodology employed a comprehensive Data Analytics approach following the CRISP-DM framework, splitting the dataset into baseline, follow-up, and testing subsets. Seven machine learning algorithms including Random Forest, XGBoost, Gradient Boosting Machine, SVM, Logistic Regression, KNN, and Naive Bayes were implemented using Python in Jupyter Notebook. The framework employed an innovative chunk-based ensemble methodology where models were trained on baseline data combined with sequential follow-up chunks, then predictions were averaged to simulate dynamic updating behaviour. The findings validate the framework\u27s ability to detect performance differences between static and dynamic approaches within controlled conditions, though the exceptionally high-performance metrics achieved reflect the simplified nature of synthetic data rather than realistic clinical expectations. The research contributes a scalable framework for evaluating sequential patient data integration that could guide future validation studies using real-world clinical datasets. These outcomes demonstrate the methodological foundation for evaluating whether dynamic approaches could potentially enhance clinical decision-making through more responsive and accurate risk prediction, pending validation with authentic longitudinal clinical data
