Hiking trail maps are typically created manually by survey, a time-consuming process. This process is expensive and must be repeated over time to improve accuracy. This paper proposed an inexpensive, automatic, and accurate trail network generation method from anonymous public GPS data utilizing a growing self-organizing map (GSOM). This technique does not rely on sequential GPS traces to learn network topology, unlike other approaches. Tuning several hyper-parameters can adjust this process for datasets and networks with unique characteristics. Reconstruction and adaption are also possible based on newly acquired data sources. Constructed trail maps, trained on publicly available GPS data, are compared against a ground truth map from Open Street Map (OSM). Performance is evaluated based on completeness, accuracy, and topological correctness. Testing on sparse networks with minimal GPS noise suggests favorable performance.
The Mississippi Delta encompasses 3.0 million acres, of which 2.2 million are irrigated for staple crops such as corn, soybeans, rice, and catfish. The Mississippi River Valley Alluvial Aquifer (MRVAA) is used to irrigate this area; over the past 30 years, it has decreased 20 feet in depth, requiring efforts to increase aquifer recharge and surface water availability for agriculture demands. A weir constructed in a river pools water upstream, promoting aquifer recharge through infiltration and increasing the availability of surface water withdrawals. Weir placement is important to the success of aquifer recharge. In partnership with the Yazoo Mississippi Delta Joint Water Management District (YMD), we created a scalable weir design guide that will allow for broad implementation and increased water availability across the Delta region. The site for the first weir was selected as an area characteristic of the Delta region and will serve as an example for subsequent designs. The supplemental design guide will allow for further weir implementation in the Delta region by providing the necessary steps for a weir design process. Inputs will be easily accessible for non-engineers and the outputs will be designs for Professional Engineer approval. By providing YMD with this weir guide, they will be able to design and install weirs more quickly and cheaply than before, supporting agriculture and groundwater resources in the Mississippi Delta.
The objective of the Car Wash Project is to prevent people from using self serve open wash bays for long periods of time without payment, which costs car wash owners considerable revenue. The solution proposed by the team is designing a universal car wash deterrent system that can be customized to multiple different car wash designs and bay layouts. The deliverable is an installation kit that can be shipped and self-installed. The packaged kit will include an ultrasonic vehicle-detection sensor, an LED strobe light, an LED display board, and a water solenoid valve. If customers stay too long without paying, the strobe light will light up, and after a set countdown, the water valve will open and the sprinklers will turn on.Everything needed for the system will be included in the installation kit other than piping, cables, and wires. The team has successfully combined all the separate components into one operational circuit as well as getting the most suitable products for the device so it can run at optimal efficiency. We will display the installation kit, how the system operates, along with a schematic of electronics.
Early cancer detection remains an important problem in healthcare today. Since the mid-1990s, Optical Coherence Tomography (OCT) has been explored as a cancer detection instrument. Previous studies have shown connections between tissue porosity, cell behavior, cell topology, and their relation to cancer and disease progression. Previous researchers have found that in a healthy cell, the pore size of the surrounding extracellular matrix (ECM) is homogenous. However, in a cancerous cell, heterogeneous pores appear. Additionally, as cancer progresses, pore size decreases. Herein, we propose a new method of improving cancer detection using OCT. In a study utilizing an artificial ECM, a connection between pore size and gold nanorod (GNR) diffusion was established such that smaller pores lead to less diffusion, and vice versa. Cell behavior is measured by cell motility, which refers to the rapid, in-place motions of intracellular parts that can be used to assess cell response to therapy, their surrounding environment, and potentially reveal premalignant behavior. Previous investigators have defined two metrics of cell movement, alpha, and motility, which correspond to signal auto-decorrelation and signal amplitude, respectively. Cell topology refers to the 3D structure and shape of cells and cell clusters, which has been shown to mutate in diseases such as cancer. By quantifying cell topology, cellular health can be examined. Techniques using OCT have also been used to monitor the response of diseased tissue to treatment. These studies have been largely independent of each other, and the need for a more holistic measuring system has been called for. This research aims to create a custom OCT system capable of obtaining these metrics simultaneously and with improved imaging depth and comparable resolution. Through an integration of a near-infrared (NIR) laser, interferometer, and LabVIEW control of the system, a new Deep-Imaging, Multi-Parameter OCT (DIMP-OCT) is being created. The system bodes a 4.6µm resolution and 5.4mm imaging depth. This is made possible by a 50-50 fiber optic beam splitter using a 1300nm wavelength laser with 160nm bandwidth, and 2048-pixel spectrometer with a 140kHz linerate. Here, we report the design of the system being built, the techniques used to build and test the hardware, and the approach to developing the graphical user interface. We also will report results from tests to assess DIMP-OCT subsystems.
This paper details an approach to identify multiple-choice questions that are most effective in discriminating deficiencies in mathematics competencies of incoming first-year engineering students who are graduates of the K-12 program that was recently implemented in the Philippines. To achieve this objective, machine learning algorithms such as the k-Nearest Neighbors (kNN), Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Gradient Boosting Machines (GBM) were implemented. From a question bank containing 1,300 questions covering Algebra (A), Advanced Algebra (AA), Plane and Spherical Trigonometry (T), Analytic Geometry (AG), and Solid Mensuration (SM), five domain experts identified the suitability of the questions as part of a diagnostic examination in mathematics. Specifically, using a 5-point Likert scale (5 being the highest), the experts rated the suitability of each question to test the proficiency of a student in 23 mathematics competencies based on what is prescribed by the Commission on Higher Education (CHED). The collected survey data were then used to train the machine learning models, which extracted patterns to identify the questions that would be most suitable to test the mathematics competencies of incoming first-year engineering students. With a precision recall score of 99.90%, the LR model was selected as the best performing model and analysis of how the LR model predicts the labels through the use of shap values revealed that the preference was given towards questions which test student proficiency in foundational mathematics competencies like that of Algebra and Analytical Geometry. Overall, these findings provided a better understanding of the questions that are most effective in discriminating student deficiencies in mathematics subjects.
