Welcome to TUCL Repository
- Access to a vast collection of academic theses and dissertations
- Wide range of scholarly journals and articles
- Search and browse functionalities for easy discovery of resources
- Accessibility to digital resources anytime, anywhere
- Facilitates research and learning endeavors of TUCL community
- Promoting open access to knowledge and research findings
- User-friendly interface, ensuring ease of navigation and accessibility for users of all levels of expertise
- unique persistent identifier (such as DOI or Handle) to facilitate citation, tracking, and long-term preservation, ensuring the integrity and longevity of scholarly contributions
Communities in DSpace
Select a community to browse its collections.
Recent Submissions
Comparative Analysis of ResNet50 and Vision Transformer on Paddy Disease Classification
(2025) Bhattarai, Bhawana; Bikash Balami
Plant diseases seriously affect our food supply, thereby affecting farmers, those dependent
on farming, and global food security. Early detection of plant disease is critical for effective
treatment and minimized yield losses. One of the useful uses of computer vision is the
identification of plant diseases by analyzing leaf images. This study compares the ResNet50
model and the ViT model on the paddy disease classification task. Specifically, it trains
these models using the Paddy Doctor dataset to evaluate their performance by modifying
the learning rate and the number of training epochs.
The Paddy Doctor dataset, which contains 16,225 images categoried into 13 different
classes, was used to train and test the models. The ResNet50 model achieved a high training
accuracy of 0.98. However, when evaluated on the test dataset, the model's performance
decreased, achieving an accuracy of 0.92. On the other hand, the ViT model achieved a
remarkably high training accuracy of 0.99. When evaluated on the test dataset, the ViT
model maintained strong performance, with an accuracy of 0.93. These results indicate that
the ResNet50 model outperforms the ViT model in terms of both training and test accuracy
for the paddy disease classification task using the Paddy Doctor dataset.
Keywords: Classification, Deep Learning, CNN, ResNet50, Disease, Paddy, Vision
Transformer
In Vitro Seed Germination and Callus Induction of Aconitum spicatum (Bruhl) Stapf
(2024) Gautam, Pooja; Krishna Kumar Pant
Aconitum spicatum (Bruhl) Stapf commonly known as ‘Bikh’ is an herbaceous perennial plant
belonging to the family Ranunculaceae. It is one of the highly poisonous plants but
characterized by significant and valuable medicinal uses. Low seed germination in nature
and uncontrolled harvesting practices, as well as a lack of concerned conservation efforts,
lead to the rapid declination of this vital plant species; however, no comprehensive and
reliable protocol has been developed till date to produce plant materials for conservation
as well as for pharmaceutical purposes. Therefore, this study was designed to develop an
efficient, simple, and reproducible in vitro seed germination, direct shoot-roots
organogenesis as well callus induction protocol using seed as an explant. The highest seed
germination percentage was recorded on Murashige and Skoog’s (MS) basal medium, with
a germination rate of 77.78% in a mean germination time of 14 days. Among the various
plant growth regulators examined, 1.5 mgL-1 BAP proved to be effective for maximum
shoots and root induction after 42 days, The maximum callus was induced in MS medium
supplemented with 1.0 mgL-1 NAA within 49-60 days. To our knowledge, this is the first
study on in vitro seed germination and callus induction of this plant. This study could
provide a basis for germplasm conservation and sustainable utilization, with implications
for the isolation of unique and pharmacologically active compounds from callus or
regenerated plantlets.
The Study of Fire Disaster in Fungling Municipality of Taplejung
(2022) Singh, Santosh Bahadur; Ramesh Raj Kunwar
A disaster is a serious problem occurring over a short or long period of time that causes
widespread human, material, economic or environmental loss which goes beyond the ability
of the affected community or society to cope using its own resources. Disasters are routinely
divided into either "natural disasters" caused by natural hazards or "human-instigated
disasters" caused from anthropogenic hazards.
Nepal, most disaster prone South Asian country is exposed to a variety of natural hazards that
cause disastrous damage to the built environment and result in loss of lives and properties.
The most destructive natural hazards in Nepal are floods, landslides, earthquakes, and urban
fire. Among different districts of Nepal, Fungling municipality of Taplejung is one of the
most affected local level by fire-induced disaster. Fungling municipality recurrently is facing
a Fire induced disaster till the date. The community efforts, government endeavor and current
practice is not working properly to mitigate the risk mitigation of Fungling municipality.
This study mainly focuses on the status of fire disaster in Nepal in general and cause and
effect of Fungling Municipality of Taplejung in specific. So, to find the solution of given
question, the study was focused on: To find the major causes of the repeated Fire disaster in
Fungling Municipality of Taplejung, To find out the key factors that reduce or mitigate the
Fire disaster in Fungling Municipality of Taplejung and To support to develop the roles and
responsibility of local government and community people in risk reduction of Fire disaster in
Fungling Municipality.
For the research, the researcher have adopted qualitative research approach and adopted
primary and secondary data as the source of information. The total respondent are taken to 30
community people and FGD/KII to key focal person of government offices. The finding
reveals that the major causes of Fire disaster in Fungling municipality are negligence of
community people, lack of proper planning by government, capacitated team for fire control,
unplanned urban settlement, lightening and low quality of house wiring etc.
Keywords: Disaster, Fungling, Recovery, hazards, negligence, settlement