Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Optimization

Discipline
Institution
Publication Year
Publication
Publication Type
File Type

Articles 1 - 30 of 656

Full-Text Articles in Physical Sciences and Mathematics

Efficient Phosphate Removal From Water Using Ductile Cast Iron Waste: A Response Surface Methodology Approach, Mai Hassan Dr., Nada Alkhashab Eng., Ahmed Osman Dr., Dalia A. Ali Eng Oct 2024

Efficient Phosphate Removal From Water Using Ductile Cast Iron Waste: A Response Surface Methodology Approach, Mai Hassan Dr., Nada Alkhashab Eng., Ahmed Osman Dr., Dalia A. Ali Eng

Chemical Engineering

Water scarcity is a critical issue worldwide. This study explores a novel method for addressing this issue by using ductile cast iron (DCI) solid waste as an adsorbent for phosphate ions, supporting the circular economy in water remediation. The solid waste was characterized using XRD, XRF, FTIR, and particle size distribution. Wastewater samples of different phosphate ion concentrations are prepared, and the solid waste is used as an adsorbent to adsorb phosphate ions using different adsorbent doses and process time. The removal percentage is attained through spectrophotometer analysis and experimental results are optimized to get the optimum conditions using Design …

Go to article

Groundwater Modeling Of The Ogallala Aquifer: Use Of Machine Learning For Model Parameterization And Sustainability Assessment, Tewodros Aboret Tilahun Aug 2024

Groundwater Modeling Of The Ogallala Aquifer: Use Of Machine Learning For Model Parameterization And Sustainability Assessment, Tewodros Aboret Tilahun

Dissertations and Doctoral Documents from University of Nebraska-Lincoln, 2023–

Addressing groundwater depletion problems in heterogeneous aquifer systems is a challenge. The heterogeneous Ogallala Aquifer, a critical source of groundwater in the central United States, has undergone decades of decline in water levels due to pumping. This project aims to build a robust groundwater model to evaluate optimal scenarios for sustainable use of the groundwater resource within a section of the Ogallala aquifer located in the Middle Republican Natural Resources District (MRNRD). This study follows a comprehensive approach involving parameterization, construction, and optimization. The model is parametrized using hydraulic conductivity and recharge values obtained from a random forest-based machine learning …

Go to article

Leveraging Generative Ai For Sustainable Farm Management Techniques Correspond To Optimization And Agricultural Efficiency Prediction, Samira Samrose Aug 2024

Leveraging Generative Ai For Sustainable Farm Management Techniques Correspond To Optimization And Agricultural Efficiency Prediction, Samira Samrose

All Graduate Reports and Creative Projects, Fall 2023 to Present

Sustainable farm management practice is a multifaceted challenge. Uncovering the optimal state for production while reduction of environmental negative impacts and guaranteed inter-generational assets supervision needs balanced management. Also, considering lots of different factors (cost, profit, employment etc), the agricultural based management technique requires rigorous concentration. In this project machine learning models are applied to develop, achieve and improve the farm management techniques. This experiment ensures the resultant impacts being environment friendly and necessary resource availability and efficiency. Predicting the type of crop and rotational recommendations will disclose potentiality of productive agricultural based farming. Additionally, this project is designed to …

Go to article

Optimization Of Learning Algorithms In Neuromorphic Computing Systems., Oyinpere S. Ameli Aug 2024

Optimization Of Learning Algorithms In Neuromorphic Computing Systems., Oyinpere S. Ameli

Masters Theses

Spiking Neural Networks (SNNs) are a type of artificial neural network that aim to more closely mimic the data processing processes observed in biological neural systems. However, one major challenge in training these networks has been their non-differentiable nature, which makes it difficult to apply traditional gradient-based learning techniques. Different approaches have been proposed to address this challenge, ranging from supervised learning - largely inspired by error backpropagation in Deep Neural Networks - to unsupervised learning, which closely emulates biological learning approaches such as spike-timing dependent plasticity (STDP). Neuromorphic hardware platforms such as Intel's Loihi offer programmable plasticity that allows …

Go to article

Optimization Of A Plate Beam System For Energy Harvesting Using A Piezoelectric Material, Jose Manuel Almendros Espantaleon Jul 2024

Optimization Of A Plate Beam System For Energy Harvesting Using A Piezoelectric Material, Jose Manuel Almendros Espantaleon

Doctoral Dissertations and Master's Theses

With a continuously growing demand for power, driven by the need to reduce our environmental footprint, this research provides an examination of the potential of energy harvesting with smart materials technology and its practical applications. The energy harvesting system considered here works on generating energy through vibrations of a piezoelectric material beam which will undergo sustained vibrations due to flow of air over its surface. It is assumed that sustained limit cycle oscillations of this system will occur at the flutter velocity. This research creates an optimization framework to obtain the best values of parameters that will result in the …

Go to article

Cellulosic Rich Biomass Production With Optimized Process Parameters By Using Glycerol Pretreatment For Biofuels Applications, Muhammad Sulaiman, Hamayoun Mahmood, Haris M. Khan, Tanveer Iqbal, Nehar U. Khan, Muhammad M. Abbas, Mohammad Nur-E-Alam, Manzoore E. M. Soudagar Jul 2024

Cellulosic Rich Biomass Production With Optimized Process Parameters By Using Glycerol Pretreatment For Biofuels Applications, Muhammad Sulaiman, Hamayoun Mahmood, Haris M. Khan, Tanveer Iqbal, Nehar U. Khan, Muhammad M. Abbas, Mohammad Nur-E-Alam, Manzoore E. M. Soudagar

Research outputs 2022 to 2026

In this work, we conduct acidified aqueous glycerol pre-treatment (AAG) on rice husks (RH) and utilize the response surface methodology (RSM) to assess the impact of pre-treatment parameters. The primary objective of this research is to optimize the parameters to maximize the cellulose content within RH. The parameters under consideration encompassed temperature (ranging from 80 to 110 °C), retention time (spanning 15 to 45 min), and biomass loading (varying from 5 to 10 wt. %). To achieve this optimization, we perform the Box-Behnken Design (BBD) within the framework of RSM. Additionally, we scrutinize the interactive effects of these parameters on …

Go to article

Functions Of Permanent Grassland In The Process Of Feed Base Optimization Of Dairy Farms From Great Poland Region, P Golinski Jun 2024

Functions Of Permanent Grassland In The Process Of Feed Base Optimization Of Dairy Farms From Great Poland Region, P Golinski

IGC Proceedings (1993-2023)

The objective of this paper was the determination of permanent grassland functions at optimization of the feed base of dairy farms in the region of Great Poland using linear programming against the background of newly developing conditions of market economy. The important factor leading to significant improvement of financial situation of farms was finding them a model of cattle feeding based on feed from permanent grasslands. However, permanent grasslands in Great Poland, when compared with arable lands, are characterized, in their models, by a low dual value. This can be attributed mainly to a low milk price and low productivity …

Go to article

Foxann: A Method For Boosting Neural Network Performance, Mahmood A. Jumaah, Yossra H. Ali, Tarik A. Rashid, S. Vimal Jun 2024

Foxann: A Method For Boosting Neural Network Performance, Mahmood A. Jumaah, Yossra H. Ali, Tarik A. Rashid, S. Vimal

Journal of Soft Computing and Computer Applications

Artificial neural networks play a crucial role in machine learning and there is a need to improve their performance. This paper presents FOXANN, a novel classification model that combines the recently developed Fox optimizer with ANN to solve ML problems. Fox optimizer replaces the backpropagation algorithm in ANN; optimizes synaptic weights; and achieves high classification accuracy with a minimum loss, improved model generalization, and interpretability. The performance of FOXANN is evaluated on three standard datasets: Iris Flower, Breast Cancer Wisconsin, and Wine. The results presented in this paper are derived from 100 epochs using 10-fold cross-validation, ensuring that all dataset …

Go to article

Implementing Selective Signature Scanning To Optimize Malware Detection, Lucas Gray Wilbur Jun 2024

Implementing Selective Signature Scanning To Optimize Malware Detection, Lucas Gray Wilbur

Computer Science Senior Theses

Signature scanning is one of the oldest types of malware detection, and it remains an essential lightweight detection method for many antivirus programs. However, signature scanning has unavoidable limitations, including an inevitably increasing runtime as malware signature databases continually expand. In this paper, we discuss the current state of signature scanning, including usage of the open-source signature scanning tool YARA. We test Zemlyanaya et al’s assertion that scanning only the beginning and end of files can reduce the runtime cost of signature database expansion — while maintaining a high level of accuracy — and find it inaccurate in the case …

Go to article

Exploring A Fly Ash-Based Grouting Material For Toughening Through In Situ Polymerization Of Acrylamide, Zhang Yuehong, Wang Xiaodong, Wang Hai, Wu Boqiang, Ji Zhongkui, Zhu Shibin, Han Le, Feng Longfei May 2024

Exploring A Fly Ash-Based Grouting Material For Toughening Through In Situ Polymerization Of Acrylamide, Zhang Yuehong, Wang Xiaodong, Wang Hai, Wu Boqiang, Ji Zhongkui, Zhu Shibin, Han Le, Feng Longfei

Coal Geology & Exploration

Efficiently controlling the water inflow (loss) of burnt rocks in the roof of coal mining faces requires grouting reinforcement materials with excellent compressive toughness. Silicate cement-based grouting materials, characterized by low costs, have been extensively applied to grouting reinforcement in coal mines. However, their hardened grout is susceptible to deformation, exhibiting poor toughness. By employing the in-situ polymerization of acrylamide (AM) for toughening, this study investigated the effects of AM, cross-linking agent, initiator, and water-cement ratio on the setting time, swelling capacity, compressive strength, and toughness index of the fly ash-based grouting materials. Furthermore, the microstructures of the hardened grout …

Go to article

Sequential Optimization For Stressor-Informed Test Planning Through Integration Of Experimental And Simulated Data, Jacob Brecheisen May 2024

Sequential Optimization For Stressor-Informed Test Planning Through Integration Of Experimental And Simulated Data, Jacob Brecheisen

Data Science Undergraduate Honors Theses

This technical report details an innovative approach in reliability engineering aimed at maximizing system durability through a synergistic use of physical experimentation and computer-based modeling. Our methodology explores the efficient design and analysis of computer experiments and physical tests to facilitate accelerated reliability growth, while leveraging a sequential integration of data from these two distinct sources: costly physical experiments, characterized by random errors, and inexpensive computer simulations, marked by inherent systematic errors. The key innovation lies in the adoption of a closed-loop design and analysis method. This method begins by identifying a viable subset of important environmental stressors—such as temperature, …

Go to article

Genetic Algorithm Optimization Of Experiment Design For Targeted Uncertainty Reduction, Alexander Amedeo Depillis May 2024

Genetic Algorithm Optimization Of Experiment Design For Targeted Uncertainty Reduction, Alexander Amedeo Depillis

Masters Theses

Nuclear cross sections are a set of parameters that capture probability information about various nuclear reactions. Nuclear cross section data must be experimentally measured, and this results in simulations with nuclear data-induced uncertainties on simulation outputs. This nuclear data-induced uncertainty on most parameters of interest can be reduced by adjusting the nuclear data based on the results from an experiment. Integral nuclear experiments are experiments where the results are related to many different cross sections. Nuclear data may be adjusted to have less uncertainty by adjusting them to match the results obtained from integral experiments. Different integral experiments will adjust …

Go to article

Multi-Objective Radiological Analysis In Real Environments, David Raji May 2024

Multi-Objective Radiological Analysis In Real Environments, David Raji

Doctoral Dissertations

Designing systems to solve problems arising in real-world radiological scenarios is a highly challenging task due to the contextual complexities that arise. Among these are emergency response, environmental exploration, and radiological threat detection. An approach to handling problems for these applications with explicitly multi-objective formulations is advanced. This is brought into focus with investigation of a number of case studies in both natural and urban environments. These include node placement in and path planning through radioactivity-contaminated areas, radiation detection sensor network measurement update sensitivity, control schemes for multi-robot radioactive exploration in unknown environments, and adversarial analysis for an urban nuclear …

Go to article

The Mathematics Of Financial Portfolio Optimization Incorporating Environmental, Social, And Governance Score Information, Ian Driskill May 2024

The Mathematics Of Financial Portfolio Optimization Incorporating Environmental, Social, And Governance Score Information, Ian Driskill

Master's Theses

We numerically investigate the effects that Environmental, Social, and Governance (ESG) scores have on portfolio optimization with Modern Portfolio Theory assumptions and how ESG scores correlate with the market returns of a rated company's stock. Additionally, we review and analyze a research paper published in the Journal of Financial Economics regarding ESG investing titled “Responsible investing: The ESG-efficient frontier” by Pedersen, Fitzgibbons, and Lukasz. Our overall goal is provide insight for socially responsible inclined investors, to help them understand what ESG scores tell us and how those scores may effect their overall investment returns."

Go to article

Optimization Of Xrf Experimental Protocol For Bruker Picofox, Tyler Ashcraft May 2024

Optimization Of Xrf Experimental Protocol For Bruker Picofox, Tyler Ashcraft

Undergraduate Honors Theses

The research performed was to improve the precision and accuracy of sample measurements made with the Bruker Picofox X-ray fluorescence spectrometer. The initial method of sample preparation using a 10 μL drop spotted onto an acrylic plate and then drying in an oven at 80˚C produced inconsistent results even when processing replicates or the same sample multiples times. Multiple experiments were conducted to determine the effects of different sample preparation conditions on the resulting accuracy. The conditions tested were drop size, plate composition, and drying temperature. For each experiment an internal standard (gallium) was used at concentrations similar to that …

Go to article

Assessing Extant Methods For Generating G-Optimal Designs And A Novel Methodology To Compute The G-Score Of A Candidate Design, Hyrum John Hansen May 2024

Assessing Extant Methods For Generating G-Optimal Designs And A Novel Methodology To Compute The G-Score Of A Candidate Design, Hyrum John Hansen

All Graduate Theses and Dissertations, Fall 2023 to Present

Experimental designs are used by scientists to allocate treatments such that statistical inference is appropriate. Most traditional experimental designs have mathematical properties that make them desirable under certain conditions. Optimal experimental designs are those where the researcher can exercise total control over the treatment levels to maximize a chosen mathematical property. As is common in literature, the experimental design is represented as a matrix where each column represents a variable, and each row represents a trial. We define a function that takes as input the design matrix and outputs its score. We then algorithmically adjust each entry until a design …

Go to article

Cost-Risk Analysis Of The Ercot Region Using Modern Portfolio Theory, Megan Sickinger May 2024

Cost-Risk Analysis Of The Ercot Region Using Modern Portfolio Theory, Megan Sickinger

Master's Theses

In this work, we study the use of modern portfolio theory in a cost-risk analysis of the Electric Reliability Council of Texas (ERCOT). Based upon the risk-return concepts of modern portfolio theory, we develop an n-asset minimization problem to create a risk-cost frontier of portfolios of technologies within the ERCOT electricity region. The levelized cost of electricity for each technology in the region is a step in evaluating the expected cost of the portfolio, and the historical data of cost factors estimate the variance of cost for each technology. In addition, there are several constraints in our minimization problem to …

Go to article

Uconn Baseball Reliever Lane Optimization Tool, Jason Bartholomew Apr 2024

Uconn Baseball Reliever Lane Optimization Tool, Jason Bartholomew

Honors Scholar Theses

The building of a tool to be utilized by UConn’s Division I baseball team that will generate a game plan for when different relievers should be used against different parts of the opponent’s lineup to achieve the lowest total expected value of runs allowed for the remainder of the game based on game situations and matchup probabilities. The tool will also examine and determine situations that may be vital enough to the outcome of the game to bring in a better reliever normally saved for later in the game.

Go to article

Modeling And Numerical Analysis Of The Cholesteric Landau-De Gennes Model, Andrew L. Hicks Apr 2024

Modeling And Numerical Analysis Of The Cholesteric Landau-De Gennes Model, Andrew L. Hicks

LSU Doctoral Dissertations

This thesis gives an analysis of modeling and numerical issues in the Landau-de Gennes (LdG) model of nematic liquid crystals (LCs) with cholesteric effects. We derive various time-step restrictions for a (weighted) $L^2$ gradient flow scheme to be energy decreasing. Furthermore, we prove a mesh size restriction, for finite element discretizations, that is critical to avoid spurious numerical artifacts in discrete minimizers that is not well-known in the LC literature, particularly when simulating cholesteric LCs that exhibit ``twist''. Furthermore, we perform a computational exploration of the model and present several numerical simulations in 3-D, on both slab geometries and spherical …

Go to article

Milp Modeling Of Matrix Multiplication: Cryptanalysis Of Klein And Prince, Murat Burhan İlter, Ali Aydın Selçuk Feb 2024

Milp Modeling Of Matrix Multiplication: Cryptanalysis Of Klein And Prince, Murat Burhan İlter, Ali Aydın Selçuk

Turkish Journal of Electrical Engineering and Computer Sciences

Mixed-integer linear programming (MILP) techniques are widely used in cryptanalysis, aiding in the discovery of optimal linear and differential characteristics. This paper delves into the analysis of block ciphers KLEIN and PRINCE using MILP, specifically calculating the best linear and differential characteristics for reduced-round versions. Both ciphers employ matrix multiplication in their diffusion layers, which we model using multiple XOR operations. To this end, we propose two novel MILP models for multiple XOR operations, which use fewer variables and constraints, proving to be more efficient than standard methods for XOR modeling. For differential cryptanalysis, we identify characteristics with a probability …

Go to article

Optimal Algorithm For Managing On-Campus Student Transportation, Youssef Harrath Dr. Jan 2024

Optimal Algorithm For Managing On-Campus Student Transportation, Youssef Harrath Dr.

Research & Publications

This study analyzed the transportation issues at the University of Bahrain Sakhir campus, where a bus system with an unorganized and fixed number of buses allocated each semester was in place. Data was collected through a survey, on-site observations, and student schedules to estimate the number of buses needed. The study was limited to students who require to move between buildings for academic purposes and not those who choose to ride buses for other reasons. An algorithm was designed to calculate the optimal number of buses for each time slot, and for each day. This solution could improve transportation efficiency, …

Go to article

Classification In Supervised Statistical Learning With The New Weighted Newton-Raphson Method, Toma Debnath Jan 2024

Classification In Supervised Statistical Learning With The New Weighted Newton-Raphson Method, Toma Debnath

Electronic Theses and Dissertations

In this thesis, the Weighted Newton-Raphson Method (WNRM), an innovative optimization technique, is introduced in statistical supervised learning for categorization and applied to a diabetes predictive model, to find maximum likelihood estimates. The iterative optimization method solves nonlinear systems of equations with singular Jacobian matrices and is a modification of the ordinary Newton-Raphson algorithm. The quadratic convergence of the WNRM, and high efficiency for optimizing nonlinear likelihood functions, whenever singularity in the Jacobians occur allow for an easy inclusion to classical categorization and generalized linear models such as the Logistic Regression model in supervised learning. The WNRM is thoroughly investigated …

Go to article

Improved Binary Differential Evolution With Dimensionality Reduction Mechanism And Binary Stochastic Search For Feature Selection, Behrouz Ahadzadeh, Moloud Abdar, Fatemeh Safara, Leyla Aghaei, Seyedali Mirjalili, Abbas Khosravi, Salvador García, Fakhri Karray, U. Rajendra Acharya Jan 2024

Improved Binary Differential Evolution With Dimensionality Reduction Mechanism And Binary Stochastic Search For Feature Selection, Behrouz Ahadzadeh, Moloud Abdar, Fatemeh Safara, Leyla Aghaei, Seyedali Mirjalili, Abbas Khosravi, Salvador García, Fakhri Karray, U. Rajendra Acharya

Machine Learning Faculty Publications

Computer systems store massive amounts of data with numerous features, leading to the need to extract the most important features for better classification in a wide variety of applications. Poor performance of various machine learning algorithms may be caused by unimportant features that increase the time and memory required to build a classifier. Feature selection (FS) is one of the efficient approaches to reducing the unimportant features. This paper, therefore, presents a new FS, named BDE-BSS-DR, that utilizes Binary Differential Evolution (BDE), Binary Stochastic Search (BSS) algorithm, and Dimensionality Reduction (DR) mechanism. The BSS algorithm increases the search capability of …

Go to article

Energy Consumption Optimization Of Uav-Assisted Traffic Monitoring Scheme With Tiny Reinforcement Learning, Xiangjie Kong, Chenhao Ni, Gaohui Duan, Guojiang Shen, Yao Yang, Sajal K. Das Jan 2024

Energy Consumption Optimization Of Uav-Assisted Traffic Monitoring Scheme With Tiny Reinforcement Learning, Xiangjie Kong, Chenhao Ni, Gaohui Duan, Guojiang Shen, Yao Yang, Sajal K. Das

Computer Science Faculty Research & Creative Works

Unmanned Aerial Vehicles (UAVs) can capture pictures of road conditions in all directions and from different angles by carrying high-definition cameras, which helps gather relevant road data more effectively. However, due to their limited energy capacity, drones face challenges in performing related tasks for an extended period. Therefore, a crucial concern is how to plan the path of UAVs and minimize energy consumption. To address this problem, we propose a multi-agent deep deterministic policy gradient based (MADDPG) algorithm for UAV path planning (MAUP). Considering the energy consumption and memory usage of MAUP, we have conducted optimizations to reduce consumption on …

Go to article

Preliminary Study On The Effects Of Vinegar As Pre- Treatment For The Oven-Drying Of Pacific Yellowtail Emperor (Lethrinus Atkinsoni) Fillets, Nurisa A. Suhaili, Rafael S. Jamih, Normina A. Abubakar, Jaro O. Ajik, Merilyn Q. Amlani Jan 2024

Preliminary Study On The Effects Of Vinegar As Pre- Treatment For The Oven-Drying Of Pacific Yellowtail Emperor (Lethrinus Atkinsoni) Fillets, Nurisa A. Suhaili, Rafael S. Jamih, Normina A. Abubakar, Jaro O. Ajik, Merilyn Q. Amlani

ASEAN Journal on Science and Technology for Development

This study aimed to assess the impact of various vinegar compositions used as pre-treatment for Pacific Yellowtail Emperor (PYE) fillets during the oven-drying process, with a focus on moisture content and optimal drying conditions. Two types of commercially available vinegar, Superior Vinegar and Datu Puti Vinegar, were compared, and different drying temperatures were evaluated. The investigation revealed that the drying temperature significantly influenced the moisture content of the dried PYE fillets. Among the tested temperatures (40°C, 60°C, and 80°C), the most favorable outcome in terms of moisture content was achieved when fillets were dried at 80°C for a duration of …

Go to article

Basins Of Attraction And Metaoptimization For Particle Swarm Optimization Methods, David Ma Jan 2024

Basins Of Attraction And Metaoptimization For Particle Swarm Optimization Methods, David Ma

Honors Projects

Particle swarm optimization (PSO) is a metaheuristic optimization method that finds near- optima by spawning particles which explore within a given search space while exploiting the best candidate solutions of the swarm. PSO algorithms emulate the behavior of, say, a flock of birds or a school of fish, and encapsulate the randomness that is present in natural processes. In this paper, we discuss different initialization schemes and meta-optimizations for PSO, its performances on various multi-minima functions, and the unique intricacies and obstacles that the method faces when attempting to produce images for basins of attraction, which are the sets of …

Go to article

A Multi-Objective Grey Wolf Optimizer For Energy Planning Problem In Smart Home Using Renewable Energy Systems, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Feras Al-Obeidat, Osama Ahmad Alomari, Ammar Kamal Abasi, Mohammad Tubishat, Zenab Elgamal, Waleed Alomoush Jan 2024

A Multi-Objective Grey Wolf Optimizer For Energy Planning Problem In Smart Home Using Renewable Energy Systems, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Feras Al-Obeidat, Osama Ahmad Alomari, Ammar Kamal Abasi, Mohammad Tubishat, Zenab Elgamal, Waleed Alomoush

All Works

This paper presents the energy planning problem (EPP) as an optimization problem to find the optimal schedules to minimize energy consumption costs and demand and enhance users’ comfort levels. The grey wolf optimizer (GWO), One of the most powerful optimization methods, is adjusted and adapted to address EPP optimally and achieve its objectives efficiently. The GWO is adapted due to its high performance in addressing NP-complex hard problems like the EPP, where it contains efficient and dynamic parameters that enhance its exploration and exploitation capabilities, particularly for large search spaces. In addition, new energy and real-world resources based on solar …

Go to article

Segac: Sample Efficient Generalized Actor Critic For The Stochastic On-Time Arrival Problem, Honglian Guo, Zhi He, Wenda Sheng, Zhiguang Cao, Yingjie Zhou, Weinan Gao Jan 2024

Segac: Sample Efficient Generalized Actor Critic For The Stochastic On-Time Arrival Problem, Honglian Guo, Zhi He, Wenda Sheng, Zhiguang Cao, Yingjie Zhou, Weinan Gao

Research Collection School Of Computing and Information Systems

This paper studies the problem in transportation networks and introduces a novel reinforcement learning-based algorithm, namely. Different from almost all canonical sota solutions, which are usually computationally expensive and lack generalizability to unforeseen destination nodes, segac offers the following appealing characteristics. segac updates the ego vehicle’s navigation policy in a sample efficient manner, reduces the variance of both value network and policy network during training, and is automatically adaptive to new destinations. Furthermore, the pre-trained segac policy network enables its real-time decision-making ability within seconds, outperforming state-of-the-art sota algorithms in simulations across various transportation networks. We also successfully deploy segac …

Go to article

Complete Solution Of The Lady In The Lake Scenario, Alexander Von Moll, Meir Pachter Jan 2024

Complete Solution Of The Lady In The Lake Scenario, Alexander Von Moll, Meir Pachter

Faculty Publications

In the Lady in the Lake scenario, a mobile agent, L, is pitted against an agent, M, who is constrained to move along the perimeter of a circle. L is assumed to begin inside the circle and wishes to escape to the perimeter with some finite angular separation from M at the perimeter. This scenario has, in the past, been formulated as a zero-sum differential game wherein L seeks to maximize terminal separation and M seeks to minimize it. Its solution is well-known. However, there is a large portion of the state space for which the canonical solution does not …

Go to article

An Unsupervised Machine Learning Algorithm For Clustering Low Dimensional Data Points In Euclidean Grid Space, Josef Lazar Jan 2024

An Unsupervised Machine Learning Algorithm For Clustering Low Dimensional Data Points In Euclidean Grid Space, Josef Lazar

Senior Projects Spring 2024

Clustering algorithms provide a useful method for classifying data. The majority of well known clustering algorithms are designed to find globular clusters, however this is not always desirable. In this senior project I present a new clustering algorithm, GBCN (Grid Box Clustering with Noise), which applies a box grid to points in Euclidean space to identify areas of high point density. Points within the grid space that are in adjacent boxes are classified into the same cluster. Conversely, if a path from one point to another can only be completed by traversing an empty grid box, then they are classified …

Go to article

Next Last