TIET Digital Repository Thapar Institute of Engineering & Technology
Not a member yet
6889 research outputs found
Sort by
Development of New Framework for Medical Image Analysis
No full textHealthcare is a cornerstone of human welfare, encompassing the prevention, diagnosis, and
treatment of diseases. However, challenges such as exorbitant expenses, limited resources, and
insufficient infrastructure hinders its accessibility and efficiency. Integrating artificial intelligence
(AI) into medical sciences has the potential to revolutionize healthcare by improving precision,
efficiency, and personalization. This thesis explores AI-driven diagnostic systems to address
critical gaps in the early detection of cancers and blood disorders, presenting innovative
approaches to automate and enhance diagnostic workflows.
The thesis consists of six chapters. The introductory chapter establishes the theoretical
foundations, highlights research gaps, and defines the overarching goal: developing robust
diagnostic frameworks capable of effectively and precisely categorizing medical images as
healthy or diseased.
Attention is then paid to haematological malignancy, particularly diffuse large B cell lymphoma
(DLBCL), a type of blood cancer that requires timely detection and intervention in mitigating the
morbidity and mortality. To overcome the limitations of traditional diagnostic techniques, an AI-
powered deep discriminative learning model (DDLM) with calibrated attention maps (CAM) is
proposed. This system employs histopathological image analysis to differentiate DLBCL from
non-DLBCL, effectively addressing inter-class variability and intra-class similarities. A
comparative evaluation demonstrates the model’s efficacy, with its utility and adaptability in
diverse clinical scenarios also highlighted.
Next focus is given on breast cancer (BC)- a prevalent malignancy in female population ranking
2nd in terms of lethality. Conventional treatment protocols often involve partial or complete
removal of breast tissue along with surgical excision of the tumor. However, these interventions
frequently fail to achieve complete eradication of the tumor. Histological assessment of breast
tissue, while widely recognized as the gold standard for diagnosis, is labor-intensive, time-
consuming, and impractical for real-time use during surgery. To address these limitations, this
study introduces a cutting-edge imaging system based on full-field polarization-sensitive optical
coherence tomography (FF-PS-OCT) integrated with an ensemble learning model, optimized
using the technique for order preference by similarity to ideal solution (TOPSIS) ranking method.
This approach offers a rapid and accurate ex-vivo alternative to traditional histology, enhancing
intraoperative decision-making and reducing recurrence rates.
The next chapter presents a high-resolution intelligent system designed for diagnosing sickle cell
disease (SCD), a hereditary blood disorder that is highly prevalent in the Caribbean as well as in
Western and Central sub-Saharan Africa. Ranked as the 12th leading cause of death globally,
SCD presents significant diagnostic challenges, particularly in resource-limited settings. This
study proposes an automated solution using a 3D intelligent quantitative phase microscope to
detect sickle cells in blood smears. The system enhances diagnostic efficiency by significantly
improving speed and accuracy while reducing reliance on expert resources.
The ensuing chapter deals with the enhanced and explainable renal histopathology image
classification using a model that incorporates advanced techniques. Renal cancer- ranked as the
9th most common ailment, poses significant diagnostic challenges due to its diverse subtypes and
asymptomatic progression. This study proposes a novel end-to-end learning approach for
classifying clear cell renal cell carcinoma using a deep discriminative model which incorporates a
global- local attention network. The integration of SHapley Additive exPlanations for explainable
AI plays a crucial role in enhancing the interpretability of model predictions. The model
effectively tackles class ambiguities and achieves high accuracy in histopathological image
classification.
The concluding chapter encapsulates the key findings of this thesis and highlights future
directions for advancing AI in medical imaging. While AI has undeniably transformed healthcare
by enhancing diagnostic accuracy and efficiency, significant challenges persist, such as the
necessity for large, diverse datasets and improved model explainability. Future efforts will focus
on addressing these obstacles to ensure the broader adoption of AI across varied populations and
building trust through greater transparency and explainability.
This thesis underscores the transformative potential of AI in revolutionizing healthcare, offering
innovative solutions to critical challenges in disease detection. By advancing precision, efficiency,
and accessibility, the work paves the way for a future where AI-driven diagnostics are seamlessly
integrated into global healthcare systems, reshaping clinical practices and improving patient
outcomes
Exploring the Impact of Social Comparison on Body Image and Social Media Addiction
No full textIn today’s modern digital era, social media serves a significant role in shaping perceptions of
body image, influencing self esteem, and reinforcing societal beauty standards. Platforms such as
Instagram, Snapchat, Twitter/X and Facebook feature curated images, beauty trends, and fitness
influencers, which can lead to both positive and negative self perception among the users. Some
individuals could find satisfaction in these trends, while some experience body dissatisfaction
and face mental well - being challenges. Conversely, the rise of body movements seek to
counteract these effects by promoting self acceptance and diverse representations of beauty. This
study examines the intricate dynamics revolving social media engagement, body image, and
social comparison, analyzing how different types of content consumption affects self perception.
Using a sample size of 121 participants, the research investigates social media habits,
engagement levels, and demographic influences to assess the psychological influences of social
media on body image. Furthermore, it evaluates the effectiveness of body positive initiatives in
fostering self acceptance. The findings aim to provide deeper understanding into the dual role of
social media in both perpetuating unrealistic beauty standards and supporting body diversity,
contributing discussions on mental health and digital well - being.
Key words: social media, social comparison, body - image, self - perception, mental well being,
beauty standards
The Role of Cognitive Flexibility, Self- Efficacy and Emotional Intelligence in Predicting Attitude Towards AI and Job Satisfaction: A Moderated Mediation Analysis
No full textWith the dynamic nature of the present-day workforce, soft skills have become as important as
technical skills, if not more. The rapid changes in the working environment and increasing
technological adaptations like Artificial Intelligence highlights the need to understand the
employee’s attitudes towards advancements like the use of AI and how satisfied they are with
their present jobs, while also tap into the role of psychological resources such as emotional
intelligence and self- efficacy in the process The present study aims to find whether cognitive
flexibility influences an employee’s job satisfaction and attitude towards artificial intelligence
when it is mediated by emotional intelligence and whether the level of self- efficacy has a role to
play in the relationship using a sample of 110 working professionals employed in organizations
making use of AI. Moderated Mediation Model was employed to conduct the analysis. Result
showed that cognitive flexibility is a valuable skill with a positive relationship with emotional
intelligence, depending on the degree of self-efficacy. Mediation analysis also identified that
emotional intelligence is an essential mechanism accounting for the relationship between
cognitive flexibility and job satisfaction and attitude towards artificial intelligence. Additionally,
the analysis of moderated mediation showed strong evidence that self-efficacy is an important
factor in furthering the influence of cognitive flexibility on emotional intelligence and, as such,
highlighting their significance in enabling an employee's mindset towards artificial intelligence
in evolving work environments and encouraging positive workplace results such as job
satisfaction
Comparative Study of Stress and Strain Analysis on a Hip End Effector for Orthopedic Surgical Applications Using Different Materials
No full textRobotic-assisted total hip arthroplasty (THA) has rapidly advanced as a transformative technology
in orthopedic surgery. This innovative approach integrates navigation, minimally invasive
techniques, and precise robotic arm control to enhance the accuracy of preoperative planning,
implant selection, osteotomy, and artificial joint placement. The inherent accuracy and stability of
robotic systems have led to their increasing adoption, particularly in hip and knee arthroplasty, and
are recognized for improving implant positioning and reducing limb length discrepancies
compared to conventional manual techniques. The precision offered by these systems in achieving
planned acetabular positioning and restoring the center of hip rotation is well-documented. While
initial clinical outcomes appear largely comparable to traditional methods, the long-term benefits,
implant survivorship, time to revision surgery, and cost-effectiveness of robotic THA continue to
be areas of active investigation and require further high-quality studies.
A pivotal component underpinning the precision and efficacy of robotic THA is the surgical end
effector. This instrument directly engages with bone and tissue during critical surgical phases, such
as reaming, cutting, and implant impaction. The structural integrity, mechanical performance, and
long-term durability of these end effectors are of paramount importance, directly influencing
patient safety and the overall success of the surgical procedure. This thesis undertakes a
comprehensive investigation into the stress, strain, and material analysis of a hip end effector
specifically designed for orthopedic surgical applications within robotic-assisted platforms.
This study focuses on the mechanical behavior of the hip end effector when fabricated from three
distinct and commonly employed biocompatible materials known for their applications in surgical
implants and instruments: 17-4 PH stainless steel, Cobalt alloys, and Titanium alloys.
Through detailed computational modeling, specifically employing Finite Element Analysis (FEA),
this research aims to meticulously analyze the stress and strain distributions within the end effector
design for each chosen material. The analysis will simulate various realistic surgical loading
conditions encountered during THA procedures, such as impaction forces, torsional loads, and
bending moments, with specific attention to applied loads of 5000 N and 7500 N. The primary
objective is to identify and characterize critical stress concentration points within the end effector
structure. This involves determining von Mises stresses, and the corresponding elastic and plastic
strains experienced by the device under these loads.
iv
Understanding these critical regions and the magnitudes of stress and strain will provide invaluable
insights into the potential areas of mechanical weakness, susceptibility to plastic deformation, and
susceptibility to fatigue crack initiation and propagation. This knowledge is crucial for predicting
the fatigue life and potential failure modes of the end effector, which in turn will inform material
selection, guide structural design optimizations, and enhance the overall reliability and safety of
the instrument. The findings from this research are expected to contribute significantly to the
ongoing development of more robust, durable, and reliable robotic surgical instruments, thereby
playing a vital role in advancing the capabilities and widespread adoption of robotic-assisted
arthroplasty, ultimately benefiting patient outcomes
Understanding the Psychological Profiles of Dementia Patients through Rorschach Inkblot Analysis
No full textDementia is a long-term neurodegenerative disorder accompanied with cognitive, linguistic and
behavioral impairment. Hence, the objective of this study was to explore the psychological and
cognitive profiles of dementia patients with the help of a battery of tests, including the Rorschach
inkblot test, dementia severity rating scale (DSRS), mini-mental state examination (MMSE), and
clock drawing test. A total of 40 subjects were enrolled, with 20 being diagnosed with dementia
and the other 20 matched as controls without dementia.
It was found that the responses in Rorschach were different in the dementia group, significant
linguistic errors such as reduced verbal fluency and semantic distortions, and figurative
inaccuracies denoting visuospatial and cognitive deficits. The DSRS scores correlated strongly
with the severity of impairment in the results of MMSE. Compared to the controls, dementia
patients had marked deficits in all assessments, including memory, executive function, and
visuospatial abilities.
The present research advocates for the addition of Rorschach in the classical cognitive battery
towards a better understanding of dementia's multifaceted impact. Findings here bear significant
relevance to improving the diagnosis and tailoring interventions toward the needs of dementia
patients
Automatic Text Summarization and Question-Answer Generation Using Deep Learning Techniques
No full textAutomatic text summarization and question-answer generation are integral components of natural
language processing (NLP) that facilitate efficient information retrieval and enhance educational
tools. Automatic text summarization techniques aim to capture the essence of a document, article,
or passage and provide a condensed version that highlights the key points and main ideas. The
ever-growing ocean of text can be overwhelming, making text summarization a crucial tool for
navigating information efficiently. The question-answer generation approach involves generating
questions and their corresponding answers from a user given source text or knowledge base by
directly selecting and rephrasing existing sentences or phrases. This approach is beneficial when
the goal is to generate questions and answers quickly and accurately from existing content, and the
answers are readily available in the source material, such as factual questions. This thesis
investigates the utilization of deep learning techniques to advance the capabilities of these tasks,
focusing on developing, implementing, and evaluating novel models and methodologies.
The research work presented in this thesis provides a framework for question-answer generation
and summarization. A system has also been developed to generate and summarize question
answers using deep learning techniques. The developed system is capable of effectively addressing
the challenges posed by the ever-expanding volume of textual data. The question-and-answer
generation model generates different question-answer pairs, including subjective and objective
type questions over a given text. The questions generated by our approach are grammatically and
contextually correct, and the answers generated match the questions in the textual context. A
query-based answer summarization system has been proposed for question-answer summarization.
The query-focused answer summarization model produces a summarized answer relevant to the
given query question. This approach saves a significant amount of user time by tailoring the
summary to answer the user’s query directly rather than condensing the entire document.
The study begins by reviewing the evolution of text summarization and question-answer
generation, highlighting the transition from traditional rule-based approaches to contemporary
deep learning models. A systematic taxonomy for text summarization and question-answer
generation has been given that provides a structured framework to categorize and comprehend the
multifaceted nature of approaches and techniques, along with the nature of output and input.
Central to this research are advanced architectures such as sequence-to-sequence models,
transformers, and attention mechanisms, which have revolutionized the field by improving the
coherence and relevance of generated summaries and question-answers. Additionally, the thesis
investigates the current landscape of the available tools in the field, and the publicly available
datasets for conducting the research within the corresponding domains are also discussed. The
latest research studies and commonly used evaluation parameters are discussed, and research gaps
have been identified. In order to bridge the gap, the research presented a framework for question
answer generation and summarization. The automatic question-answer generation and
summarization facilitate extracting relevant information and insights from extensive textual
content, enhancing accessibility and comprehension for users.
The automatic question-answer generation greatly benefits users by saving time, repeating core
concepts for reinforcement learning, and motivating learners to engage in learning activities. The
question-answer summarization framework helps those who urgently need information by
providing the user with condensed relevant information in real-time while minimizing redundancy,
thus enhancing user experience. The framework briefs various phases and sub-phases involved in
generating and summarizing question-answers along with the input and output of these phases.
The work also mentions the approaches, models, and datasets used in the framework phases for
training or fine-tuning the computationally intense architectures. The methodologies employed in
this thesis include the application of pre-trained language models like T5, BART, PEGASUS, and
GPT for optimizing generation quality and the training of models on large-scale datasets such as
Stanford Question Answering Dataset (SQuAD), Question Answering in Context (QuAC), and
Boolean Questions (BoolQ) for question-answer generation and Quora question pairs dataset,
Microsoft Machine Reading Comprehension (MS-MARCO) dataset, and CNN/DailyMail dataset
for summarized answer generation. It has been found that the system outperforms the existing
baseline question-answer generation models over BLEU-4 and METEOR evaluation metrics with
a score of 18.87 and 25.24, respectively. This question-and-answer generation system acts as a
one-stop destination for generating subjective and objective-type questions and is capable of
generating fill-in-the-blank, multiple-choice, boolean, and long/short answers. As an outcome, this
paves an automatic way for fulfilling the need for a persistent supply of question-answers for the
tutors and self-evaluators, thus enabling users to save their effort, resources, and time.
The question-answer summarization model produces a summarized answer relevant to the given
query question. A query-focused answer summarization architecture utilizing a keyword extraction
mechanism (QFAS-KE) is presented for this model. This QFAS-KE is a four-phased framework.
The first phase normalizes the input text by eliminating irrelevant details. The second phase
retrieves semantically similar questions to the asked query, the third phase extracts candidate
answers relevant to the query question, and the fourth phase generates a summary of selected
candidate answers. A BERT-based bi-encoder and cross-encoder siamese structure have been
utilized with FAISS indexing to identify semantic similarity between query-to-questions and
question-to-answers. For answer summarization, fine-tuning of BART, T5, and PEGASUS has
been performed on summarization datasets with keyword guidance by applying a keyword
extractor such as KeyBERT. QFAS-KE (BART) outperforms baseline models, showing
superiority in terms of ROUGE-1, ROUGE-2, and ROUGE-L with 46.2%, 24.8%, and 42.3%
respectively. QFAS-KE (PEGASUS) achieves superior results compared to the baseline models
in ROUGE-1 and ROUGE-2. QFAS-KE (T5) surpasses baseline models, demonstrating the best
performance in ROUGE-1 and ROUGE-L. The results indicate significant improvements in both
summarization and question-answer generation tasks, with models producing more concise and
accurate summaries and generating questions that closely align with human-crafted ones.
The future scope of this work lies in exploring additional modalities to extend the proposed
system’s applicability and effectiveness in information comprehension for multimodal
information, customization of models for specific domains, such as healthcare, finance. The
findings and methodologies presented in this thesis provide a foundation for future research and
development, aiming to make these technologies more robust, versatile, and widely applicable
Role of Self-Compassion in Transition from School to College
No full textMaster thesisTransitioning from school to college can be a significant time in a student’s life, during which
emotional, academic, and social disruption often occurs. Successfully making this leap can depend
on a host of psychological resources, including self-compassion, which appears to be a potential
buffer to stress and a facilitator for positive psychological adjustment. This quantitative study
looks at how self-compassion operates in facilitating this transition by examining self-compassion
concerning perceived stress and optimism in first-year undergraduate students. One hundred
thirteen undergraduate first-year students from three streams of study - engineering, commerce,
and humanities - made up the sample. Standardized instruments were used to measure the
constructs of interest: the Self-Compassion Scale (SCS) as a measure of self-compassion; the
Perceived Stress Scale (PSS) as a measure of stress; and the Optimism Scale to measure
dispositional optimism. The demographic variables of gender and academic stream were included
as independent variables to explore group differences in the level of self-compassion, perceived
levels of stress, and optimism levels. The ultimate goal of this study was to see if higher selfcompassion was associated with lower perceived stress and higher optimism levels at the onset of
college life, and to explore how these relationships might differ based on gender and academic
stream. The findings are expected to offer insights into the psychological mechanisms underlying
student adjustment and contribute to developing targeted interventions and support systems that
enhance student well-being during the transition to higher education
Development of concrete composites using blended cements for repair of heat damaged concrete
No full textFire incidents pose a significant threat to life and property, with residential and commercial structures being particularly vulnerable. Recent reports highlight an alarming rise in fire-related fatalities and structural failures, emphasizing the urgent need for effective, high-performance, fire-resistant repair materials. Concrete, a widely used construction material, degrades severely under fire due to thermal expansion, spalling, and reduced load-bearing capacity. While concrete outperforms steel in fire resistance, its mechanical properties deteriorate rapidly beyond 400°C exposures, necessitating advanced repair solutions.
This study aims to bridge this gap by developing a sustainable, thermally resilient concrete repair material. The research optimizes cementitious blends of Ordinary Portland Cement (OPC), Limestone Calcined Clay Cement (LC3), Calcium Aluminate Cement (CAC), and hybrid fibers (Polypropylene and Steel Fibers). Through an extensive experimental program, the study evaluates these composites' thermal, mechanical, durability, and bond behavior under varying heating-cooling regimes. Key objectives include. (1) Analyzing workability, color change, crack propagation, and mass loss; (2) Assessing residual compressive strength using destructive and non-destructive testing methods (3) Examining durability properties, including chloride penetrability, sorptivity, thermal conductivity, and microstructural changes via X-ray diffraction (XRD) and thermogravimetric analysis (TGA); (4) Evaluating the bond strength between the newly developed mix and heat-affected substrate concrete.
The research adopts a two-phase experimental approach. In Phase 1, forty-five concrete mixes (1350 samples) were subjected to elevated temperatures (200°C, 400°C, 600°C & 800°C) under air cooling and water quenching. Their performance was assessed using non-destructive (rebound hammer, ultrasonic pulse velocity) and destructive (compressive strength) tests, supplemented by microstructural analysis (XRD and TGA) to identify phase transformations and degradation mechanisms. Phase 2 (85 samples per mix) focused on the top-performing mix (selected from Phase 1), evaluating its durability (chloride penetrability, sorptivity, void spaces, and thermal conductivity) and bond strength with fire-damaged substrate concrete.
The results indicate that replacing 20% of OPC with LC3 or CAC individually, or 15% in combination, optimally enhances residual strength. Hybrid fibre-reinforced LC3 mixes (Mix-3) demonstrated superior performance, retaining 8.42% higher compressive strength at 200°C and 44.56% higher splitting tensile strength at ambient temperatures than conventional OPC. Ambient cooling proved less detrimental than water quenching, while non-destructive tests (NDT) correlated well with mechanical outcomes, albeit with a 20–30% underestimation. At higher temperatures (600°C–800°C), the LC3 mix with hybrid fibers performed exceptionally well. Microstructural analysis confirmed that LC3 densifies concrete, reduces permeability, and improves chloride resistance up to 400°C. The proposed repair mix also exhibited low thermal conductivity and strong substrate bonding, making it a viable solution for rehabilitating fire-damaged structures.
In conclusion, this study presents a sustainable, high-performance composite that addresses fire-induced concrete degradation, offering enhanced durability, thermal resistance, and mechanical strength restoration. The findings advocate for adopting limestone calcined clay cement-fibre blends in fire-prone constructions. Future refinements through broader statistical modelling and field validations are recommended to optimize performance further. The practical applications of this research are extensive, providing valuable insights for producing fire-resistant concrete in construction sites, precast members, concrete blocks, power plants, and other critical infrastructure