A5016395673- Risk and Portfolio Optimization
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Robotics and Sensor-Based Localization
- Security in Wireless Sensor Networks
- Advanced Image and Video Retrieval Techniques
- Smart Agriculture and AI
- Energy Efficient Wireless Sensor Networks
- Graph theory and applications
- Mobile Ad Hoc Networks
- Complex Network Analysis Techniques
- Vehicle Routing Optimization Methods
- Advanced Vision and Imaging
- Bayesian Modeling and Causal Inference
- Advanced Graph Theory Research
- Fuzzy Systems and Optimization
- Reservoir Engineering and Simulation Methods
- Hydrological Forecasting Using AI
- Multi-Criteria Decision Making
- Soil Moisture and Remote Sensing
- Electrowetting and Microfluidic Technologies
- Graphene research and applications
- Robotic Path Planning Algorithms
- Data Visualization and Analytics
- Forest Biomass Utilization and Management
- Quantum-Dot Cellular Automata
Miami University
2019-2024
University of Florida
2018-2021
Eglin Air Force Base
2016-2017
National Academies of Sciences, Engineering, and Medicine
2016-2017
University of Iowa
2008-2015
This paper presents a comprehensive approach to SAR image retrieval for navigation in GPS-denied areas. It explores the utilization of images develop techniques, assuming system can generate real-time images. The process involves retrieval, where query is compared stored database identify most similar ones. selected serve as reference points extracting precise location coordinates. We propose model leveraging on notion siamese artificial neural networks, inspired by SqueezeNet architecture,...
We present an efficient scenario decomposition algorithm for solving large-scale convex stochastic programming problems that involve a particular class of downside risk measures. The considered functionals encompass coherent and measures can be represented as infimal convolution certainty equivalent, include well-known measures, such conditional value-at-risk, special cases. resulting structure the feasible set is then exploited via iterative relaxed problems, it shown number iterations...
We propose a two-stage stochastic programming framework for designing or identifying "resilient," "reparable" structures in graphs whose topology may undergo transformation. The reparability of subgraph satisfying given property is defined terms budget constraint, which allows prescribed number vertices to be added removed from the so as restore its structural properties after observation random changes graph's set edges. A model formulated and shown -complete broad range graph-theoretical...
We introduce a stochastic extension for the problem of finding nonhereditary subgraphs maximum size in randomly changing graphs. The proposed formulation utilizes two-stage optimization framework identifying whose structural properties can be preserved and repaired whenever underlying graph's topology changes randomly. Particular focus is placed on that represent diameter-based clique relaxation known as an s-club. A combinatorial branch-and-bound algorithm developed demonstrated to...
To improve commercial feasibility of robotic harvesters, it is utmost important to reduce and be able guarantee harvesting times. A significant portion this responsibility on the control system. Current visual servo methods can at best achieve exponential regulation a robot (i.e., theoretically infinite convergence time), making impossible predict harvest time. The aim paper introduce new finite-time approach that guarantees finite bounded) computable end, continuous terminal sliding mode...
Autonomous systems operating in unstructured and complex agricultural environments are susceptible to errors leading uncertain losses the efficiency of system. In robotic harvesting, these would translate into lower harvesting efficiency. To this end, it is desirable improve through human collaboration. The added labor costs associated with involvement could be a concern since expected reduce costs. Therefore, objective work develop optimal human-robot collaboration policies that minimize...
<b><sc>Abstract.</sc></b> <b>Many developed and rapidly developing countries around the world are exploring autonomous robotic solutions for harvesting fruit due to their potential increased productivity over manual harvesting. However, economic feasibility of depends at large on two factors: efficiency, which is a quantitative measure successful harvest, harvest time. To maintain advantage, it imperative that system achieves high efficiency time operation should be comparable its...
<p style='text-indent:20px;'>Navigating unmanned aerial vehicles in precarious environments is of great importance. It necessary to rely on alternative information processing techniques attain spatial that required for navigation such settings. This paper introduces a novel deep learning-based approach navigating exclusively relies synthetic aperture radar (SAR) images. The proposed method utilizes neural networks (DNNs) image matching, retrieval, and registration. To this end, we introduce...