22505 research outputs found
Sort by
Mixed-Integer Linear Programming (MILP) model for Transportation Cost Optimization
No full textMotivated by a request from a real company, this study presents a mixed integer linear programming (MILP) model for labor transportation at real company located in Dubai (BSG). The study integrates routing, assignment, and environmental pricing into one model, with the focus on fixed shift worker transport and featuring several dorms and sites. It also tests the model with the real company data from the UAE service sector. The model assigns workers from dormitories to the client sites by busses in a manner that minimizes daily transport cost and monetized CO₂ emissions, subject to capacity, routing, and utilization constraints. The model represents one day of planning horizon, with multiple dorms and sites, as well as bus types. Decision variables describe bus activation, route selection, arc movements, and worker flows. Cost terms combine fuel use, lease and driver payments, and a carbon price per kilogram of CO₂. Python and PuLP tools were used to solve modelbased problems using BSG data. The models considered a small network with three buses and nine sites and a larger network with six buses and thirty-nine sites. The results revealed an optimized assignments that satisfy all site demands and operational constraints while reducing financial cost relative to current practice. The daily financial cost falls from 951.65 AED to 726.07 AED in Scenario 1, for a reduction of about 23.7%. While in Scenario 2, the daily financial cost falls from 1,630.37 AED to 1,325.88 AED, for a reduction of about 18.7%. Routes chosen by the model concentrate demand on fewer buses with higher occupancy and lower avoidable distance. The findings also confirmed that an MILP-based decision support tool reduces operating expenditure and supports transparent reporting of CO₂ emissions for labor transport in facilities management
Optimizing Power Grids in UAE using Data Analytics for Improved Efficiency and Reliability
No full textThe United Arab Emirates (UAE) has aims to triple its renewable energy capacity to 14 GW to attain the objective of 30% contribution of clean energy by 2031. Energy consumption, on the other hand, will increase from 5.2 to 5.8 exajoules by 2028. The grid infrastructure for which was developed to facilitate the centralized generation of power, is not conducive to dealing with the variability of the decentralized renewable resources that lead to inefficiencies in operation and reliability problems. The Dubai power grid is analyzed using historical data of 105,120 residential, commercial and industrial supplies. In this analysis machine learning models using Random Forest and LSTM were found to be superior in respect of risk assessment characteristics and load forecasting in so far as the capability to predict 89% of the capacity variation and reduce forecast error to MSE 0.0639 in respect of risk levels. An artificial intelligence enabled digital twin was set up to optimize current time grid optimization including predictive maintenance and renewable portfolio planning. This digital twin was effective in respect of risk level prediction and next step predictions were in the Cautious range (2.59–2.72) in 80% of cases and more effective in predicting surplus energy and fault detection. The seasonal analysis indicated that peak energy always requires in summer as well as from the industrial area where peak demand capacity is (peaking to 4.91 MW) and surplus whilst being of significance in respect of intervention point criticalities. The findings indicate increased efficiency, reliability and integration of renewables by utilization of AI translational digital twins applied to the grid reduce risk of operation whilst assisting in the UAE energy transition. Demonstration samples consist of standard calibrated recalibration advice for sensor readings and seasonal load management techniques as well as worldwide predictive analytical advisement implementation leading to realization of a smart adaptive grid
Hypnosis and mindfulness audio recordings for reducing fatigue in individuals with multiple sclerosis: A randomized controlled study
No full textBackground
Fatigue is a common problem in individuals with multiple sclerosis (MS).
Objective
The objective was to evaluate the effects on fatigue of having 4 weeks of
access to audio recordings of therapeutic hypnosis (HYP) and mindfulness meditation
(MM) practices.
Methods
A total of 333 individuals with MS and fatigue were randomly assigned to
one of the three treatment conditions for 28 weeks: (1) access to therapeutic HYP audio
recordings, (2) access to MM audio recordings, or (3) no access to recordings
(treatment as usual or TAU). Fatigue impact (primary outcome) and other outcomes
were assessed at 4, 16, and 28 weeks after random assignment.
Results
Participants assigned to the HYP and MM conditions reported significantly greater reductions in fatigue impact, sleep disturbance, and depressive symptom severity than participants assigned to the TAU condition after 4 weeks of access to audio recordings of these interventions. These improvements were maintained for 16 and 28 weeks following initial access and did not result in any serious adverse events.
Conclusion Given the ease with which audio recordings of HYP and MM could be provided to individuals with MS, the findings support the feasibility of a simple approach to have a significant beneficial impact on people with MS-related fatigue
Prediction of Vessel Arrival Time to Optimize Berth Allocation in Ports Using Machine Learning Methods
Get PDF80% of the world trade is carried out through the sea, which shows the importance of maintaining transportation efficiency in the maritime industry. The vessel arrival time and berth allocation pose a significant challenge in the marine field\u27s day-to-day operation, especially when a high number of vessels are waiting at the anchorage to deliver the goods on time. This increases the pressure on the responsible stakeholders and good owners as some cargo must be delivered urgently. Artificial intelligence and machine learning play a vital role in improving the operation of different fields; utilizing such technologies in the maritime industry will facilitate operations and increase efficiency. In this work, the vessel arrival prediction was tackled through implementing different machine-learning models. The historical data was collected from The Norwegian Base Station and Satellites between August 1 and September 24, 2024. Different preprocessing techniques were utilized to clean the dataset and prepare it for modeling. The three models built are Gradient Boosting Regression, K-Nearest Neighbors (KNN) Regression, and Random Forest Regression. Random Forest Regression showed better results than the other two models with R2 value equal to 0.704 and MAPE of 0.0285%
Advances in Machine Learning for Pain Recognition: A Review of Algorithms, Modalities, and Outcomes
Get PDFThe emergence of machine learning (ML) in healthcare has unlocked the transformative potential of pain detection and assessment. By providing new ways to address the challenges associated with subjective and inconsistent pain assessment methods. This review synthesizes recent advancements in ML-based approaches for pain detection, focusing on algorithms, modalities, and datasets. Techniques such as neural networks, transformer models, and multimodal fusion frameworks have demonstrated significant promise in identifying pain from diverse sources, including facial expressions, physiological signals, and synthetic datasets. Key contributions include novel transformer-based architectres like PainAttnNet for analyzing electrodermal activity [1], multimodal datasets such as BioVid for advancing pain classification [3], and innovative synthetic data generation pipelines to mitigate dataset scarcity and ethical concerns [1], [9]. Challenges related to dataset bias, interpretability, and real-world generalization remain pivotal, necessitating further research in integrating diverse data modalities and enhancing model robustness. This review underscores the role of ML as a cornerstone in advancing pain recognition, aiming to improve patient care and clinical decision-making through precise, automated, and scalable solutions
Roads of Tomorrow: Augmented Reality for Enhanced Road Maintenance
Get PDFThe rapid deterioration of roads creates major obstacles that affect public security, urban movement capacity, and economic durability. Standardized road maintenance operations depend heavily on human inspections that prove time-consuming while being labour-intensive and subject to human mistakes. Implementing Augmented Reality (AR) with Point Cloud Data represents a smart approach that improves delivery efficiency in road maintenance procedures for modern cities. AR enables real-time visual content and interactive displays through this research, yet Point Cloud Data delivers detailed, precise road inspections through high-definition three-dimensional mapping. These technologies are evaluated for their usability, effectiveness, and adoption barriers in research that advance digital transformation knowledge for infrastructure management. Qualitative and quantitative research methods collected data to provide complete feedback about the proposed technologies. A structured questionnaire (with close- and open-ended questions) was first administered to road maintenance professionals to gather information about their present procedures and difficulties and understand their perspectives regarding AR and Point Cloud Data systems. The study conducted pilot tests and field demonstrations, bringing Point Cloud Data and AR-based solutions together to validate the technology in real-world conditions. Quantitative data analysis involved applying descriptive statistics and correlation methods with open-ended answers evaluated through thematic pattern identification. Tests against traditional workflows were carried out to determine how AR technologies performed better than conventional methods in maintenance operations. The evaluation results show robust endorsement for AR and Point Cloud Data systems in road infrastructure maintenance. These technologies enhance how defects appear to operators, provide clear step-by-step instructions, and make maintenance procedures more efficient. Real-time system overlays in AR applications received high praise because they improved situational awareness while diminishing inspection outcomes and manual documentation requirements. Point Cloud Data delivered accurate road condition mapping as its main benefit, which helped predictive maintenance teams and extended further into asset management practices. Multiple barriers emerged during the assessment process because existing infrastructure management tools proved difficult to merge with this new technology while training requirements proved extensive and the total expenditure proved high. The research reveals that Point Cloud Data and AR show strong implementation potential but need systematic strategic deployment. This research validates that AR and Point Cloud Data systems possess transformative capabilities for road maintenance by improving the precision of work, operational speed, and managerial choices for maintenance staff. The barriers to large-scale deployment include technical connection problems, computing requirements, and budgetary restrictions. The implementation speed and safety from AR-based solutions require more research on machine learning algorithms, data processing optimization, and total cost assessment for extended maintenance periods. Additional research should work to expand the scale and standardize information systems for AR and Point Cloud Data implementation within various road infrastructure management ecosystems
Examining the Influence of Sports Nutrition Counseling on Collegiate Athletes
Get PDFThis study explored the influence of nutrition counseling provided by registered dietitian nutritionists (RDNs) on collegiate athletes’ dietary behaviors, knowledge, and perceptions of nutrition. A mixed-methods approach was employed, incorporating qualitative interviews with 15 athletes from six sports across four schools. Participants reflected on their counseling experiences, focusing on its impact on their nutritional habits, health, and athletic performance. Quantitative data, including a one-sample t-test on recommendation scores, revealed a mean score of 6.73 (SD = 0.46) on a 7-point scale, indicating consistently high satisfaction with nutrition counseling. Thematic analysis identified five themes: Influence of Counseling, Behavioral Changes, Self-Reported Understanding of Nutrition, Value of Recommending Counseling, and Areas for Improvement. Subthemes encompassed topics such as improved health and performance, behavioral influences, sports-specific nutrition knowledge, and the need for advanced, individualized counseling. Participants emphasized the importance of nutrition in athletic performance, highlighting counseling’s role in improving hydration, meal planning, and supplement use. Findings suggest that nutrition counseling is highly valued by collegiate athletes and supports their health and performance. The findings for Areas of Improvement suggest that counseling can be enhanced by tailoring it to individual needs, offering more advanced counseling sessions, and addressing accessibility barriers for athletes. Implications for research and practice are discussed, aiming to enhance the delivery of RDN-led counseling and effectively meet the specific needs of collegiate athletes