http://dspace.dtu.ac.in:8080/jspui/handle/123456789/40 2026-11-01T03:32:09Z 2026-11-01T03:32:09Z GUPTA, JITIKA Hasija, Yasha (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23363 2026-10-16T06:31:50Z 2026-05-01T00:00:00Z

Title: A MACHINE LEARNING-DATA DRIVEN ANALYSIS FOR NON ALCOHOLIC FATTY LIVER DISEASE Authors: GUPTA, JITIKA; Hasija, Yasha (SUPERVISOR) Abstract: Nonalcoholic fatty liver disease (NAFLD), and its progressiveness of disease, such as nonalcoholic steatohepatitis (NASH) and fibrosis, show worldwide challenge, solely due to the difficulty in achieving early diagnosis given the limited initial symptoms. This research explores the data-driven machine learning (ML) to ,enhance the accurateness of classification, prediction in fatty liver disease.[1] Workflow frequently uses datasets such as the Indian Liver Patient Dataset (ILPD), electronic health records (EHR), and multi-omics cohorts (transcriptomics and lipid omics)[2]. Data preprocessing is a initial step, often involving multivariate imputation or iterative imputation for missing values, applying transformations to correct skewedness,[3] .To optimize the model efficiency and performance, feature extraction and selection methods such as the spearmen coefficient correlation was applied not linear data and Pearson coefficient to liner data.[4] Stacking Ensemble Learners and Gradient Boosting algorithms (XGBoost), consistently exhibit higher performance in prediction tasks. But for primary level 6 basic algorithms were used for prognostics.[5], [6] Detection of stages of fibrosis and differentiation between NASH and NAFL was to find disease in early stage without invasive process. Key clinical factors identified as having significant predictive value for progression 3 include prior mean and maximum AST/ALT ratio , FIB4, and metabolic and liver marker levels, and prior mean and standard deviation[7] . Functional enrichment analysis also emphasized the significant accumulation of fat in liver, scarring and then converting it into cancer[8] . Collectively, these data-driven ML approaches offer efficient means to improve early detection, refine risk stratification, and elucidate the underlying pathogenesis of fatty liver disease.

2026-05-01T00:00:00Z PAL, MILSI Sharma, Jai Gopal (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23354 2026-10-16T06:30:55Z 2026-07-01T00:00:00Z

Title: CONSTRUCTION OF SHARED-SOIL STACKED PLANT MICROBIAL FUEL CELL USING NUTRIENT FILM TECHNOLOGY IN HYDROPONICS FOR BIOELECTRICITY PRODUCTION AND ITS PERFORMANCE EVALUATION Authors: PAL, MILSI; Sharma, Jai Gopal (SUPERVISOR) Abstract: The world is currently facing a critical power crisis, necessitating the urgent development of sustainable sources of energy. Among the various alternative energy solutions, Plant Microbial Fuel Cell (PMFC) technology has been explored as a potential means of electricity generation. However, the electricity output from traditional PMFC setups remains insufficient. In this research, we present an innovative approach by integrating microbial fuel cells with nutrient film channels, harnessing hydroponics technology. The proposed design incorporates carbon fibre cloth as an efficient conductor for the anode and the cathode, resulting in improved electrical conductivity. Additionally, from the wetlands of Tughlaqabad Biodiversity Park (New Delhi, India), containing electrochemically active facultative anaerobic bacteria, is introduced to enhance electron transfer processes. The novel PMFC design achieves tenfold higher efficiency compared to conventional PMFCs while occupying a smaller footprint. By connecting plants with diverse cathodes in series, a gradual increase in current was observed. Experimental analysis involved tomato and morning glory plants, with their respective performances assessed. The research demonstrates a remarkable maximum power generation of 28 W/m² within 50 days. Furthermore, the electricity generation can be further augmented by employing plants with fibrous root systems. A polarization curve analysis was used to thoroughly test the PMFC prototype, giving important information about its operating features. The findings from this research present significant progress in sustainable energy production, potentially transforming the future of bioelectricity generation through hydroponics technology.

2026-07-01T00:00:00Z KUMAR, MANEESH Bharadvaja, Navneeta (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23351 2026-10-16T06:30:36Z 2026-05-01T00:00:00Z

Title: BIOCHAR-BASED NANOCOMPOSITE AND NANO BIOCHAR ADVANCES, APPLICATION AND FUTURE PROSPECTS FOR SUSTAINABLE AGRICULTURE ENVIRONMENTAL REMEDIATION Authors: KUMAR, MANEESH; Bharadvaja, Navneeta (SUPERVISOR) Abstract: Sustainable and environmentally related remediation technologies are desolately needed due to the sharp rise in environmental pollution brought on by urbanization, industrialization, and concerted agricultural practices. Green-synthesised biochar nanocomposites derived from plants have become a rising class of advanced functional materials for useful in environmental applications. Biochar has a biggest surface area, a porous structure, and a potent adsorption capacity. It is pyrolyzing plant biomass in low oxygen environments. Biochar's physicochemical qualities are improved while maintaining environmental safety and biocompatibility when it is combined with green-based nanoparticles that use plant extracts as reducing and stabilisingagents.The green synthesis, characterization, and environmental uses of biochar nanocomposites basedfrom plants are the main topics of this work. To known the formation of nanoparticles, surface functionalization, and structural stability, characterization processes like FTIR, XRD, SEM, BET, and UV–Vis spectroscopy are come in. Heavy metals, dyes, pesticides, and organic pollutants are all effectively cut from water and soil by the synthesized nanocomposites. The study suggests the potential of these environmentally friendly nanocomposites as long-term substitutes for chemically synthesized materials in the areas of soil remediation, water purification, pollution control, and climate change mitigation.

2026-05-01T00:00:00Z DIXIT, ANJALI KUMAR, Pravir (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23336 2026-10-16T06:26:34Z 2026-05-01T00:00:00Z

Title: TRANSCRIPTOMICS ANALYSIS OF PARKINSON’S DISEASE USING GSE68719 Authors: DIXIT, ANJALI; KUMAR, Pravir (SUPERVISOR) Abstract: Parkinson's disease (PD) is a neurodegenerative disorder which mainly affects voluntary movement control. This disease is identified by gradual degradation of dopaminergic neuron in substantia nigra i.e. lowering dopamine signaling in neural circuit. Less dopamine availability leads to disturbances on basal ganglia signaling which causes cardinal motor symptoms like posture instability, bradykinesia, muscular rigidity. Along with motor some non-motor symptoms like sleep disturbances, anxiety, depression, cognitive impairment and dementia etc. can also be seen in the advance stage of the disease. The defining feature of PD is aggregation of misfolded alpha-synuclein in intracellular inclusion which then leads to neuronal dysfunction and cell death by the mechanisms like mitochondrial impairment, neuroinflammation, oxidative stress etc. In PD neuronal degradation occurs due to combined effects of genetic susceptibility, environmental exposure, mitochondrial dysfunction, Oxidative stress and neuroinflammation. Some familial and sporadic form of this disease occurs due to genes like SNCA, LRRK2, PARK2, PINK1, and DJ-1. While environmental factors like heavy metals, pesticides increases neuronal injury due to oxidative and mitochondrial stress. By profiling messenger RNA expression, transcriptomic analysis gives insight of cellular pathways, regulatory networks, and disease progression, and it has become an important and efficient approach in modern molecular biology and disease research . Transcriptomic analysis is now more critical in Parkinson’s disease investigations, because for an early diagnosis, there are not enough dependable biomarkers, so people do not need to use invasive methods. By using the public resources like GSE68719, scientists are able to do bioinformatics analyses again on gene expression about Parkinson's. Differential expression tests can see if genes became more or less expressed due to this disease, and then pathway analysis tries to explain which signaling and biological processes are impacted most largely in such datasets. Volcano Plots are used to check the genes with larger fold change whereas Enrichment methods used to check biological roles and cell pathways. Overall, the main goals in analysing the DEGs with GSE68719 are to get better inside PD molecular processes, find possible biomarkers, locate disturbed functional pathways, and give a push for later research for diagnosis and treatment.

2026-05-01T00:00:00Z