VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!

Browsing by Author "Lohani, Meena"

Now showing 1 - 2 of 2
  • Thumbnail Image
    DiagnoSym: Disease Prediction System Using the Symptoms
    Kambham, Naga Sekhar Reddy; Banka, Sindhuja; Vemulapalli, Yuva Sri; Palla, Akhil; Chakiri, Yaswanth; Lohani, Meena (2023-12-06)
    The rapid advancement of artificial intelligence (AI) has led to a significant transformation in healthcare, particularly in diagnostic development and personalized treatment approaches. This project introduces DiagnoSym, a web-based system harnessing the capabilities of machine learning to predict potential diseases and assess their severity based on user-provided self-reported symptoms. Beyond traditional diagnostic functionalities, DiagnoSym goes a step further by offering users valuable health information, personalized preventive measures, and details of medical experts. The integration of machine learning ensures accurate predictions, while the platform's holistic approach aims to enhance efficiency, effectiveness, and user experience in healthcare delivery. As AI continues to evolve, DiagnoSym exemplifies the potential for technology to positively impact healthcare outcomes, empowering individuals to play an active role in their well-being.
  • Thumbnail Image
    Effects of Stream Order and Data Resolution on Sinuosity Using GIS
    Lohani, Meena (Virginia Tech, 2008-04-29)
    This research focuses on estimation and analysis of stream sinuosity using GIS. Fifty-five streams including 13 streams of order 0, 17 streams of order 1, 15 streams of order 2 and 10 streams of order 3 in Virginia were considered. Several GIS datasets from various sources, including the Virginia Base Mapping Program (VBMP) and United States Geological Survey (USGS), were used to generate stream networks using GIS. Sinuosity was computed using GIS based on a technique comparable to the approach used in an Environmental Monitoring and Assessment Program's (EMAP's) field survey report. Field sinuosity data from EMAP report were used as reference data for analyzing the accuracy of sinuosity values from different GIS data sources and resolutions. The GIS technique was implemented for computing sinuosity for 55 streams in Virginia using vector data including the VBMP Hydro44 and National Hydrography Data (NHD). Insufficient statistical evidence was found to support the hypothesis that the computed sinuosity values using Hydro44 and NHD data are different from EMAP field data for all 55 streams. Sinuosity values computed using Hydro44 and NHD were found to increase with the increase in EMAP sinuosity (positive correlation) for all 55 streams. EMAP data on sinuosity, however, did not predict sinuosity values computed using Hydro44 (R² = 27%) and NHD (R² = 10%) sources well. It was found that the GIS technique of computing sinuosity using digital data such as Hydro44 (VBMP source) and NHD (USGS source 1:24,000) is better suited for stream orders 2 and 3. Insufficient statistical evidence was found that computed sinuosity values for streams derived using various resolutions (i.e., DTM 3m, DTM 10m, DTM 30m, DEM 10m and DEM 30m) are different from EMAP field data. Positive correlation was observed between sinuosity values for streams derived in all resolutions with EMAP field data. DTM 10m resolution data yielded best correlation value (75%) with EMAP field data.