Engineering Commons^™

Operational Feasibility Of Reinforcement Learning For Vehicle Routing Under Heterogeneous Fleet Capacity Constraints, Freddy Giovanny Aviles Moreno

Electronic Theses and Dissertations

Reinforcement learning methods have demonstrated strong performance on vehicle routing benchmarks, yet their behavior under severe capacity constraints remains unexplored. This dissertation investigates whether PPO-based neural routing policies maintain operational viability when vehicle capacity is severely constrained, as occurs in resource-limited rural logistics settings.

Through controlled experiments on synthetic instances and validation on real-world rural healthcare networks in Florida, this research reveals a critical capacity threshold effect. Moderate capacity reductions from 40 to 20 produce negligible performance loss (4.1%), while severe reductions to capacity 10 trigger catastrophic failure with 243% degradation, manifested through degenerate single-customer routing patterns. Convergence analysis identifies …

Boiling Flow Estimation For Aero-Optic Phase Screen Generation, Jeffrey W. Utley, Gregery T. Buzzard, Charles A. Bouman, Matthew R. Kemnetz

Faculty Publications

Aero-optic effects due to turbulence can reduce the effectiveness of transmitting light waves to a distant target. Methods to compensate for turbulence typically rely on realistic turbulence data, which can be generated by i) experiment, ii) high-fidelity computational fluid dynamics (CFD), iii) low-fidelity CFD, and iv) autoregressive methods. However, each of these methods has significant drawbacks, including monetary and/or computational expense, limited quantity, inaccurate statistics, and overall complexity. By contrast, the boiling flow algorithm is a simple, computationally efficient model that can generate atmospheric phase screen data with only a handful of parameters. However, boiling flow has not been widely …

En-Feat: An Effective Feature Selection Method Using Ensemble Approach, Sasank Nath, Dhruba Kumar Bhattacharyya

Mansoura Engineering Journal

Feature selection is a crucial step in machine learning and data preprocessing, significantly influencing model performance and interpretability. This paper presents a comprehensive study and contributions in the domain of feature selection by integrating traditional learning techniques with ensemble-based, proposing an effective approach. We propose a Mutual Information-based feature aggregation approach applied to union sets of features, aiming to derive an optimal subset of features that maximizes accuracy. Then, we employ an ensemble method that utilizes forward selection over union sets to identify the optimal feature subsets through sequential feature selection. Our ensemble-based feature selection method called En-feat, is evaluated …

Some New Oscillatory Behavior Of Higher-Order Elliptic Partial Differential Equations, S. Priyadharshini, V. Sadhasivam, Samrajesh Mault, K. K. Viswanathan

Mansoura Engineering Journal

The main objective of this study is to investigate the new adequate conditions for oscillation of higher-order elliptic partial differential equations by using the Riccati transformation and integral average method. The Riccati transformation converts a nonlinear first order Riccati differential equation into a second order linear ordinary differential equation, enabling solution via standard linear methods followed by inversion. Our plan of action is to reduce the multidimensional problem to an ordinary differential problem by using Jensen's inequality. Elliptic partial differential equations are used in almost every field of mathematics and physics, including Lie theory, geometry, and harmonic analysis. An elliptic …

Adaptative And Structured Optimization Stockwell Transform For Robust Power-Quality Disturbances Detection, Moudjibatou Afoda, Séna Apeke, Filippo Gatti, Alessio Iovine, Léonce W. Tokam, Guy M. Toche Tchio, Ouro-Djobo S. Sanoussi

Mansoura Engineering Journal

The monitoring of electrical power quality requires advanced analysis techniques capable of accurately detecting and localizing non-stationary disturbances. This work proposes a structured and adaptive optimization of the Stockwell Transform (ST), referred to as Two-Power Optimization (TPO). A multiparametric Gaussian window governed by four parameters (m, p, k, r), is introduced, and a genetic algorithm is applied independently to each signal to optimize these parameters. The optimization process adapts the analysis scale to the local characteristics of the signal while preserving the physical consistency of the window function. Simulation results on synthetic power quality signals demonstrate that the proposed method …

Effect Of Rotating Cylinder On Boundary Layer Behavior And Aerodynamic Performance Of Naca 0015 Airfoil, K. Suresh, Inamul Hasan

Mansoura Engineering Journal

Flow separation over airfoils at moderate and high angles of attack leads to a significant degradation in aerodynamic performance. Active boundary layer control using moving surfaces provides an effective approach to delay separation and enhance lift. In this study, the aerodynamic efficiency of a NACA 0015 airfoil equipped with a rotating leading edge cylinder is numerically investigated using computational fluid dynamics. Simulations are carried out for a range of angles of attack and cylinder surface speed ratios at low Reynolds numbers like Re = 1.2 x105. The rotating cylinder injects momentum into the boundary layer, promoting flow attachment on the …

Finite Element Modelling On A Non-Linear Radiative Hybrid Nanofluid Flowing Through A Rotating Disk, N. Janaki Phani Madhuri, Md. Shamshuddin

Mansoura Engineering Journal

This study develops a finite element model to investigate the MHD flow and heat transfer phenomena of Cu–H₂O and Cu–Fe₃O₄–H₂O hybrid nanofluids flow across a spinning disk modelling by the Tiwari–Das model. The governing non-dimensional momentum and energy equations account for the effects of buoyancy, nonlinear radiation, and ohmic heating. The nonlinear coupled system is solved with the element method (FEM) to find the velocity and temperature fields. Parametric studies will investigate the effects of the magnetic field, buoyancy, volume fraction of nanoparticles, and radiation. Skin friction and Nusselt number are also reported. The results show that with the hybrid …

Real-Time Iot-Enabled Dissolved Oxygen Monitoring And Automated Wastewater Recirculation In Constructed Wetlands, Sivasankar Pandiarajan, Vanitha Sankararajan, Devarinti Chandu

Mansoura Engineering Journal

Wastewater treatment is necessary for environmental conservation and combating water pollution. This study demonstrates real-time dissolved oxygen (DO) monitoring in constructed wetland treatment. The system would ensure an adequate supply of oxygen through automated water circulation whenever the level is below 4 mg/L, and shut down when it reaches the normal level. From experiments conducted, it was observed that within three automated circulation processes, it is possible to increase DO concentrations from 0.5 mg/L to 5.0 mg/L. Additionally, Total Dissolved Solids reduced from 1,380 ppm to 920 ppm. pH also stabilized from 8.38 to 7.9. In this system, data is …

Bridging Machine Learning And Climate Futures: A Framework For Explainable, Self-Directed (Agentic) Ai Models In Monitoring, Mitigation, And Governance Of Anthropogenic Climate Impacts, Vijayanandh Rajamanickam, Ketaki Kulkarni, Vishwanadham Mandala, Ozgur Kisi

Mansoura Engineering Journal

Environmental and societal damage due to anthropogenic climate change demands detection and mitigation strategies that are both effective and accountable. Machine Learning (ML) appears to offer a powerful set of tools but remains unexploited in these areas. A key barrier remains its poor ability to draw causal inferences about external systems, an essential requirement for meaningful continued monitoring, acting on, and shaping of the climate. Explainable, self-directed learned models operate by attributing environmental changes and deciding how best to model the resulting dynamics—they offer a natural solution. Recent developments in computational ecology, meteorology, and ML are combined to propose a …

Nitrite Oxidation During Ozonation Revisited: Mechanisms Of Nitration Reactions, Tarek Manasfi, Christoph Dieziger, Simon A. Rath, Daisuke Minakata, Urs Von Gunten

Michigan Tech Publications

The formation of toxicologically relevant nitro compounds has been observed during ozonation of nitrite-containing secondary wastewater effluents, but their formation mechanism remains unknown. To identify key nitrating species, three reaction systems were investigated: ozonation of nitrite (O3/NO2^–), peroxynitrite (ONOOH/ONOO^–), and hydroxyl radical oxidation of nitrite with γ-radiolysis (γ/NO2^–). Nitrite ozonation (O3/NO2^–) yielded significant amounts of the nitrating agent nitrogen dioxide ^•NO2 (9.4% at pH 7 to 22% at pH 12) besides the main product nitrate. No peroxynitrite formation was detected during ozonation of nitrite-containing waters, suggesting that ^•NO2 is the …

Topographical Mobility Envelope Modeling And Geometric Analysis For Off-Road Unmanned Ground Vehicles, Huashuai Fan

ETDs from 2020-2029

This dissertation introduces topographical mobility as a quantitative framework for assessing off-road unmanned ground vehicle performance based on geometric interaction between the vehicle and terrain. Rather than relying on conventional discrete indices, the proposed formulation evaluates mobility directly from vehicle and terrain geometry, expressing vehicle capability in terms of radius constraints implied by its dimensions and suspension state. On the vehicle side, longitudinal and lateral mobility radii are derived analytically from vehicle geometry—wheelbase, track width, ground clearance, and lowest underbody point location—quantifying the minimum terrain radius negotiable without underbody interference. Suspension state is shown to alter longitudinal mobility radius by …

Centrifugally Spun Silica Fibers For Lithium-Ion Battery Anodes: Structure And Cycling Stability, Alejandra Guerrero, Valeria Tirado, Jason Parsons, Mataz Alcoutlabi

Mechanical Engineering Faculty Publications

Introduction: Silicon dioxide (SiO2) fiber structures have attracted attention as alternative anode materials for lithium-ion batteries because of their ability to improve cycling stability compared to commercial silicon particles.

Materials and methods: SiO2 composite fibers were prepared by centrifugal spinning of polyvinylpyrrolidone (PVP)/SiO2 precursor solutions followed by calcination at 500–700 ◦C for different holding times to produce short-fiber composites and micro-belt SiO2 fiber structures. The morphology and crystal structure of the SiO2 short fibers and micro-belts were characterized by scanning electron microscope (SEM), X-ray diffraction (XRD), and X-ray Photoelectron Spectroscopy (XPS). Electrochemical performance was evaluated using CR2032 half-cells.

Results: The …

Utilizing Waste Paper Ash As Partial Cement Replacement In Concrete, Karim Hassan

Thesis/ Dissertation Defenses

The concrete industry has a considerable environmental impact. The manufacture of ordinary Portland cement (OPC) emits a large amount of carbon dioxide, while the extensive extraction of virgin natural aggregates further burdens the environment during concrete production. This thesis is concerned with the development of low-carbon concrete through the combined utilization of waste paper ash (WPA), recycled aggregates, and accelerated carbonation curing. The main objective is to reduce the environmental footprint of concrete products, including masonry units, by enhancing their carbon sequestration potential, decreasing the use of cement, and alleviating reliance on virgin aggregates, while also maintaining adequate mechanical and …

Optimizing Graphene Oxide In Self-Compacting Concrete: A Sustainable Nano-Material Strategy For Enhanced Durability And Structural Performance, Mohammed Shakeebulla Khan, Vijaya G. S

Journal of Sustainable Construction Materials and Technologies

In order to reduce the environmental impact of the constructed world, advanced and sustainable construction materials are needed. This work is a summary of the comprehensive study on a novel self-compacting concrete with nano-engineered material (graphene oxide) modified self-compacting concrete (GO-SCC). The optimum dosage of GO was determined using Taguchi method, Analysis of Variance (ANOVA) and Response Surface Methodology (RSM) multi-objective statistical optimization method, and was found to be 0.10% by weight of cement (bwoc). This dosage of 0.10% GO led to the overall desirability score of 0.87, which confirmed that this was the optimum dosage for six response variables …

Deep Q Network For Adaptive Pelican Crossing Signal Optimization Balancing Pedestrian Safety And Vehicular Efficiency, Amalia Yasmin Chairunnisa, Andyka Kusuma, Jachrizal R. Sumabrata

Smart City

Static pelican crossing systems often fail to accommodate the stochastic arrival patterns prevalent in high-density transit-oriented development (TOD) zones, creating operational inefficiencies between pedestrian clearance and vehicular flow. At the Cikini Station transit hub in Jakarta, existing fixed signal cycles contribute to pedestrian delays and peak-hour congestion. This study evaluates an adaptive signal control model for mid-block pelican crossings using a Deep Q-Network (DQN) algorithm. To calibrate the simulation, empirical data were extracted from field CCTV footage using the YOLOv8 algorithm, accurately capturing 15-minute peak flow fluctuations and commuter surges. The system is formulated as a Markov Decision Process (MDP) …

Development Of An Adaptive Pelican Crossing Model Using Fuzzy Logic In Mixed Traffic Conditions, Manazil Adam, Andyka Kusuma, R. Jachrizal Sumabrata

Smart City

Traffic management at at-grade pedestrian crossing facilities (pelican crossings) in highly populated areas, such as the Universitas Indonesia Station, faces significant inefficiency challenges. During peak hours, the fixed-time system is frequently disabled and replaced with subjective manual control by security personnel, thereby triggering irregular stop-and-go cycles and a high accumulation of vehicle delays. This study aims to develop a hybrid adaptive control model integrating Computer Vision, Genetic Algorithm (GA), and Fuzzy Logic to optimize intersection performance under mixed traffic conditions. The research methodology begins with the extraction of traffic and pedestrian characteristic data, calculated manually through recorded field observations. This …

Past Present, & Future: Bushwick Inlet Redevelopment, Aaryan Nair

Publications and Research

This report examines how ecosystem structure, hydrology, and material flows in Williamsburg, Brooklyn have changed from pre-colonial conditions to the present and how they are expected to evolve under future climate change. Prior to European colonization, the landscape functioned as a forest–wetland mosaic with high infiltration capacity, slow water movement, and strong nutrient retention. These conditions supported stable aquatic ecosystems and minimized pollutant transport to the East River.

Modern urbanization has fundamentally altered this system. Impervious surfaces and engineered drainage systems have shifted hydrology from infiltration-dominated to runoff-dominated pathways, producing rapid “flashy” flows and reducing water residence time.

Storm events …

Processing Mechanism And Efficacy Maintenance Strategy Of Ginseng Active Ingredients Based On Spectroscopy Technology, Yang Hantong, Kong Linghui, Jiang Mengmeng, Wang Yingxiu, Li Xiangguo

Food and Machinery

Ginseng, as a medicinal and edible plant, has ginsenosides as its core active components, which are widely applied due to their physiological functions such as antioxidant and anti-inflammatory activities; however, their structures and activities are easily affected by food processing. During processing steps such as cleaning, steaming/boiling, and fermentation, temperature, pH, and microbial enzyme systems alter the types, contents, and stability of active components through reactions such as hydrolysis and oxidation. The intrinsic linkage mechanism of "component transformation-activity-bioavailability" constitutes a core focus and challenge in current research. This study, based on spectroscopic techniques including high-performance liquid chromatography (HPLC), nuclear magnetic …

Force-Feedback And Load Sharing Mechanisms In Cardiac Myosin Ii Ensembles Revealed By Motor-Specific Perturbations, Omayma Alazzam, Md. Amzadul Hoque Chowdhury, Heath M. Stevens

Faculty and Student Publications

Myosin II motors within ensembles exhibit emergent force-generating behavior that varies based on ensemble size and makeup. However, the mechanisms by which myosins within ensembles sense and modulate behavior due to local and systemic changes in motor behavior, and concomitantly mechanics, remains unclear. To understand how myosin kinetics alter ensemble-level force generation, we employ myosin inotropes, specifically Mavacamten (MAVA) and Omecamtiv Mecarbil (OM), to pointedly alter myosin behavior in a concentration-dependent manner. MAVA has been shown to reduce the number of active myosin heads participating in crossbridge formation and force generation, while OM is recognized for prolonging motor attachment to …

Use Of Smart Safety Devices And Artificial Intelligence And Its Impact On Workplace Injury Reduction In High-Risk Industries In Cameroon: A Qualitative Exploration Of Worker And Management Perspectives, John Atabong Zifac

Doctoral Dissertations and Projects

Workplace injury has been a significant concern within high-risk industries in Sub-Saharan Africa, especially Cameroon, with weak worker safety standards, poor infrastructure, lack of compliance with regulatory requirements, and a limited level of digital infrastructure contributing to a high risk of worker injury. While artificial intelligence (AI) supported smart safety technologies have revolutionized the way companies conduct workplace safety management in developed nations, little research exists on the perception of these technologies and practicality among low-resource industrial operators in Sub-Saharan Africa. This qualitative phenomenological study investigated management and employee perceptions regarding the use of AI-based smart safety devices to reduce …

Quantifying The Impacts Of The Covid-19 Pandemic And Water Tariff Reforms On Domestic Water Consumption In The Emirate Of Abu-Dhabi, Darin Ibrahim Khedr

Thesis/ Dissertation Defenses

The study of domestic water consumption is of critical importance, particularly in hot and arid regions where limited natural water resources and growing demand place increasing pressure on water supply systems. The Emirate of Abu Dhabi, represents an important case study, as domestic water demand is a major concern for policymakers and water resource managers. The emirate experiences an extremely arid climate and depends heavily on desalination to satisfy water requirements across all sectors. The primary objective of this study is to investigate the impacts of the COVID-19 pandemic on domestic water consumption in the Emirate of Abu Dhabi and …

Adaptive Intervention Strategies In Co-Evolving Multiplex Networks: A Reinforcement Learning Approach To Real-Time Misinformation Containment, Anjali Ashokrao Bhadre Dr., Harshvardhan Prabhakar Ghongade Dr.

Northeast Journal of Complex Systems (NEJCS)

The growing transmission of misinformation via social media creates serious challenges to public health, democracy and social cohesion. To date, methods used to contain misinformation rely upon static representations of networks and set rules for interventions. In contrast, this study presents the first Multiplex Adaptive Reinforcement Intervention Network (MARIN), a framework for real-time adaptive intervention in the context of dynamic misinformation transmission using co-evolving multiplex networks and deep reinforcement learning. Unlike past studies that have assumed static network structures, MARIN has the ability to allow for dynamic changes in network topology as a result of both misinformation transmission and intervention …

Tinyvgg-Based Real-Time Degradation Classification For Adverse Driving Scenes Using A Newly Collected Iraqi Driving Dataset, Yousif N. Abbas, Matheel E. Abdulmunim, Nada H. Ali, Ismail A. Mageed

Journal of Soft Computing and Computer Applications

Environmental conditions such as low-light at night, fog scattering, glare artifacts, rain streaks, and rain smear distortions are significant issues of camera-based perception in Autonomous Vehicles (AVs). These degradations alter the statistics of the scene, mask structure, introduce non-uniform noise, and adversely affect downstream vision processes, including detection and tracking. To overcome this shortcoming, this paper presents a lightweight TinyVGG-based degradation classification system that runs in real time. The network extracts discriminative spatial features with hierarchical convolutional encoding and projects them to a lower-dimensional semantic representation with fully connected layers and a multi-class predictor based on SoftMax. In addition, a …

Improving Approach Of Evolutionary Strategies For Clustering Technique Enhancement, Duaa Mahde Saleh, Hasanen S. Abdullah, Ahmad Zamsuri

Journal of Soft Computing and Computer Applications

The existence of the information has been the essential aspect of the whole society. Information is concentrated in all forms to be effectively utilized. Clustering — an unsupervised learning technique. It is based on data similarity that gives rise to issues in collection, challenges and instability in data structure. It proposes an advanced evolutionary method by combining two approaches. Firstly, it adopts the evolutionary approach and integrates the advantages between two methods to design one. Among them are Differential Evolution (DE) and Genetic Algorithm (GA), Evolutionary Strategy (ES) and Genetic Programming (GP), and Evolutionary Programming (EP) and Particle Swarm Optimization …

A Comprehensive Review Of 1d Deep Learning Approaches In Facial Analysis: Face Recognition, Landmark Detection, And Mesh Modeling, Duaa J. Al Hammami, Rehab F. Hassan

Journal of Soft Computing and Computer Applications

Facial Analysis has progressed rapidly with deep learning and its 2D image-based models, especially Convolutional Neural Networks (CNNs), which have been the most popular methods. In recent years, 1D deep learning models have gained traction in the search for efficient solutions for face recognition, facial landmark detection, and 3D face mesh modeling. 1D models encode the facial structure as sequences, curves, or temporal signals, resulting in high computational efficiency, a small memory footprint, and good interpretability, making them well-suited for real-time and edge devices. This review is a step-by-step, organized exploration of 1D deep learning analysis of the face, its …

Comparative Study On Throughput Optimization In Nfv: Traditional Dissemination Techniques Vs. Swarm Intelligence Approaches, Sanaa Salih Alwan, Asia Ali Salman, Wulfrano Arturo Luna Ramírez

Journal of Soft Computing and Computer Applications

Network Functions Virtualization (NFV) modernizes networks by replacing hardware with software, creating a more flexible network architecture and offering flexibility in dynamic network environments. This foundational technology is essential for creating the networks of the future, including the Internet of Things (IoT) and cellular services. NFV does provide flexibility, but it struggles to maintain system throughput during high traffic loads while achieving high resource utilization efficiency and dynamic packet routing. The problem lies in the fact that traditional request distribution mechanisms, such as flooding and gossip, fail to operate efficiently in complex network topologies (scale-free networks), leading to: (a) random …

A Comprehensive Review Of The A* Algorithm: Evolution, Applications, And Future Trends In Path Planning, Saleel H. Abood, Hussein M. H. Al-Khafaji, Mohanned M. H. Al-Khafaji

Journal of Soft Computing and Computer Applications

Despite being a fundamental problem to autonomous robotics and intelligent navigation systems, path planning is still a challenge. The A^* algorithm is often used among search-based techniques for optimal search performance, as it's a tradeoff of computation. The above techniques have been developed for various applications as many versions of A^* Dynamic A^* (D^*), D^* Lite, Hybrid A^*, and Anytime A^* are suggested to deal with dynamic environments, real-time constraints, and kinematic restrictions. This paper comprehensively and structurally reviews the A^* algorithm and its major extensions, encompassing historical development, methodological …

Skin Lesion Classification Using Cnn Model And Augmented Dataset, Mohammed Nawzad Mohammed-Ramzi, Aso M. Aladdin

Journal of Soft Computing and Computer Applications

Skin cancer is a deadly disease. Skin lesion classification is a critical challenge due to its prevalent and deadly nature. Skin lesions are difficult for dermatologists to detect using eye examination, which is time-consuming and variable. A deep learning model of skin lesions classification has been proposed using a Convolutional Neural Network (CNN) trained on the HAM10000 dataset of 10,015 dermatoscopies. To improve resilience and address the dataset's extreme class imbalance, data augmentation techniques such as geometric transformations, brightness/contrast adjustments, blurring, noise addition, histogram equalization, color space alterations, and elastic deformations are used. With a carefully balanced 10% test set, …

Comparative Analysis Of Random Forest And Artificial Neural Networks For Predicting In-Situ Soil Density, Eng. Jinan Ali Abd Al-Kareem Al-Maliki, Dr Ammar Salman Dawood, Dr. Ihsan Al-Abboodi

HBRC Journal

This study suggests that RF and ANN are proven to be robust algorithms in predicting in-situ soil density, which is considered a significant geotechnical parameter. The research is based on 86 soil samples and focuses on five main input parameters: Gravel Percentage (G%), Plastic Limit (PL%), Sand Percentage (S%), Fines Percentage (F%), and Liquid Limit (LL%). The models developed here utilize five commonly recorded index properties (G%, S%, F%, LL, and PL) for all field samples taken from the Basra-Faw Road project. The influence of moisture content and compressive energy was ignored, as all field samples acquired the same moisture …

Beneficial Investigation Of Sustainable Recycled Waste Plastic In Treating The Consolidation Behavior Of Fine Soil, Aram Mohammed Raheem, Cumaraswamy Vipulanandan, Mohammed Hiwa Abdullrahman, Ali Tariq Omer

Journal of Sustainable Construction Materials and Technologies

Recycled waste plastic is one of the regular garbage utilized as a sustainable material in soil remediation. This study examines the efficacy of utilizing local recycled waste plastic as an ecological quantifiable along with soil containing fine particles to analyze the consolidation behavior. Various recycled waste plastic contents ranging from 2% to 10% were employed experimentally in two patterns where in the first pattern the recycled waste plastic were mixed as dry material with the fine soil particles while in the second pattern a sandwich layer of 10% of the recycled waste plastic was placed in the middle of the …