Communities in Avinashilingam Institute for Home Science and Higher Education for Women - AULIB-IR Central Library
Select a community to browse its collections.
Recent Submissions
Classification of Diabetic Retinopathy Stages Using Deep Learning Architectures
(Avinashilingam, 2025-08) Santhiya Lakshmi K; Guide - Dr. B. SARGUNAM
Diabetic Retinopathy (DR) is a progressive microvascular complication of diabetes and a leading cause of vision impairment and blindness worldwide. Early detection and accurate classification of DR are essential for timely medical intervention and prevention of severe visual deterioration. Traditional diagnostic approaches rely on manual grading by ophthalmologists, which is time-consuming, labor-intensive, and susceptible to inter- observer variability. Recent advancements in Deep Learning (DL) have demonstrated significant potential in automating DR classification; however, existing models face challenges related to overfitting, computational complexity, and generalization across diverse datasets. This research aims to develop a robust and computationally efficient DR classification system capable of accurately detecting all four stages of DR like normal, mild, moderate and severe while addressing these challenges. The proposed methodology follows a three step approach to enhance model performance and adaptability. In the first phase, Transfer Learning (TL) is employed to fine-tune state-of-the-art pretrained models, particularly EfficientNetV2L, using the Asia Pacific Tele-Ophthalmology Society (APTOS) dataset. The objective is to utilize deep feature extraction capabilities while ensuring improved generalization. Data augmentation and scaling techniques are incorporated to mitigate overfitting and enhance model robustness. In the second phase, a custom Convolutional Neural Network (CNN) architecture is designed to optimize feature extraction and computational efficiency. The architecture incorporates structured convolutional layers, batch normalization, and dropout mechanisms to enhance learning stability while reducing the risk of overfitting. In the third phase, a hybrid model is developed by integrating the EfficientNetV2L with the custom CNN architecture, thereby utilising the strengths of both architectures. Extensive hyperparameter tuning is performed, including learning rate scheduling, dropout regularization, batch size optimization, and adaptive optimization using Adam optimizer, to ensure efficient training and convergence. The hybrid model is designed to provide a balance between high classification accuracy and computational feasibility, facilitating its deployment in clinical applications.The proposed system is evaluated using key performance metrics, including accuracy, precision, recall, F1-score, and computational complexity (trainable parameters).The hybrid model (EfficientNetV2L + Custom CNN Model) achieves the highest classification accuracy of 94%, with a precision of 94%, recall of 93%, and F1-score of 94%, utilizing 441,087 trainable parameters. Comparative analysis with benchmark models demonstrates the superiority of the proposed approach, with EfficientNetV2L achieving 92% accuracy, the Custom CNN Model reaching 88% accuracy, while conventional architectures such as VGG16 (85%), ResNet-50 (87%), InceptionV3 (89%), and DenseNet121 (90%) exhibit relatively lower performance. These findings confirm the effectiveness of the hybrid approach in achieving state-of-the-art classification accuracy while maintaining computational performance. The developed hybrid model is evaluated against an existing architecture that integrates DenseNet121, Xception, and EfficientNetB3, comprising 2,361,860 trainable parameters. The existing model achieves an accuracy of 75%, precision of 73%, recall of 75%, and an F1 score of 71%. In contrast, the proposed model, with only 441,087 parameters, demonstrates superior performance achieving a 19% increase in accuracy, 21% in precision, 18% in recall, and 23% in F1 score highlighting its effectiveness despite a significantly reduced parameter count. This research contributes to the advancement of automated DR classification by integrating fine-tuned pretrained models with a lightweight custom CNN, resulting in a scalable, efficient, and clinically viable diagnostic framework. The system is validated using clinical data to ensure its applicability in practical healthcare settings, particularly in resource-constrained environments where access to high-end computational resources is limited. The proposed model has the potential to significantly enhance early DR detection, improve diagnostic consistency, and ultimately contribute to better patient outcomes in ophthalmic disease management.
Creating Awareness on Organic Waste Management Practices among Selected Rural Households
(Avinashilingam, 2024-07) Vinothini R; Guide - Manimozhi K
This study investigates the impact of a training program on organic farming practices among rural households in selected areas, aiming to enhance health, reduce environmental pollution, and promote sustainable agricultural practices. The research methodology involved conducting household surveys, implementing training sessions, and evaluating the program's outcomes. The household survey gathered demographic data and insights into current agricultural practices and organic waste management. Findings highlighted diverse farming practices and challenges such as pest attacks and diseases, exacerbated by the heavy use of chemical fertilizers and pesticides. Organic waste management practices also revealed significant gaps in disposal methods and environmental awareness among rural communities. The training program focused on educating farmers about organic farming techniques, including composting and natural pest control methods. Evaluation of the training's impact showed notable improvements in farmers' knowledge and attitudes towards organic farming. Statistical analysis indicated significant changes in knowledge scores post-training, suggesting a substantial increase in understanding organic practices among participants. The adoption of organic practices post-training was another key outcome assessed. Results demonstrated a marked increase in the adoption of composting, organic growth boosters, and natural pest and disease management methods. This adoption was supported by economic benefits derived from reduced input costs and improved crop yields, contributing to rural household prosperity. Challenges identified during the study included logistical constraints in conducting widespread training and limitations in transportation for field visits. Despite these challenges, the training program succeeded in reaching a significant number of farmers and effecting meaningful changes in agricultural practices. The findings underscore the importance of targeted training programs in promoting sustainable agriculture and improving rural livelihoods. The study contributes valuable insights into the efficacy of educational interventions in transitioning farmers towards organic farming practices. Recommendations include scaling up similar training initiatives, addressing logistical barriers, and enhancing community awareness on environmental stewardship and waste management.
Seen on the shelf
(The Hindu, 2026-01-30) Nidhi Adlakha
A paper a day
(The Hindu, 2026-02-09) Elango K
மகாகவியும் ஏ.ஐ. தொழில்நுட்பமும்
(தினமணி, 2026-02-07) தினமணி
A Hybrid Machine Learning approach for Detecting Intentional and Unintentional Insider Threats with Mitigation through Behavioral Biometrics and User Profiling Mechanism
(Avinashilingam, 2025-07) Asha S; Guide - Dr. D. Shanmugapriya
Insider threat is a potential threat to an organization that results in financial and reputation losses while exposing sensitive information. Past research extensively focused on external threats, and overlooked on both intentional and unintentional insider threats.Several researchers majorly focused on detecting such insider activities but fail to mitigate both intentional and unintentional insider threats. Few challenges such as mishandling imbalanced dataset and fail to incorporate feature engineering techniques, limited mitigation strategies are encountered. This research employs a hybrid machine learning approach to identify insider threats and incorporated behavioural biometrics with user profiling to mitigate both intentional and unintentional insiders effectively. A methodology comprising of three phases is proposed. It consist of Preprocessing and Insider Detection (P&ID) in Phase I, Unintentional Insider Mitigation (UIM) in Phase
II, and Intentional Insider Mitigation (IIM) in Phase III. P&ID consist of two layers - Preprocessing, and Insider Detection. In Layer 1, log data is preprocessed using data integration, encoding and tuned the nearmiss-2 sampling technique to obtain a balanced data to diminish the class imbalance problem. In Layer 2, a hybrid B-SVM combining Support Vector Machines (SVM) and Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) is applied. It classifies users into genuine, intentional insiders, and unintentional insiders. The proposed method achieved a 99.15% detection accuracy, with a low misclassification rate of 0.85% for detecting both intentional and unintentional insider threats. Once unintentional insiders are detected, the unintentional insiders are mitigated in
UIM phase. UIM phase consist of two layers – Feature engineering, and Core behavior identification. In Layer 1, Clonal Kernel Principal Component Analysis (CKPCA) is proposed for feature engineering. CKPCA integrates population subset selection, kernel mean embedding, and dimensionality reduction to improve feature representation. These features are further analyzed using Deep Belief Networks (DBN) in Layer 2 that achieved 99.84% authentication accuracy and a 0.15% Equal Error Rate (EER) of 0.15%. This phase significantly minimizes false alarms and ensures a reliable mitigation process for unintentional insiders.
In IIM phase, the detected intentional insiders are mitigated using user profiling mechanism based on their authentication outcome. IIM phase consist of three layers – Data pre-processing, Model training and evaluation, and User profiling. In Layer 1, data pre-processing is done using label encoding and train-test split. In layer 2, Decision tree is modeled to categorize users low-risk and high-risk. In Layer 3, Low-risk users with legitimate activities are profiled into the Allowlist, while users displaying malicious intent with high-risk are placed on the Denylist. This adaptive profiling ensures that intentional threats are neutralized without affecting genuine users. The methodology was validated using two datasets namely the CERT Insider Threat Dataset and the CIC Darknet Dataset. P&ID detected 8 intentional and one unintentional insider among 250,078 daily logs using CERT Dataset. P&ID is validated with darknet dataset, detected 4,783 intentional-Darknet users and 68 unintentional- Darknet users where (VPN: 42) (Tor: 21) (NonVPN: 5) among 134,305 daily activities. UIM mitigated one unintentional insider as an intentional insider using CERT log activities. UIM mitigated 68 unintentional-Darknet users as 64 Intentional-Darknet and 4
benign users using darknet dataset. IIM profiled 57 genuine users in Allowlist and 8 intentional insiders in Denylist using CERT dataset. Using CIC Darknet dataset, the IIM profiled 5063 benign users in Allowlist and 4847 Intentional-Darknet users in Denylist. This study offers a practical and highly effective solution for insider threats in environments where user log data is analyzed. By combining hybrid machine learning models with behavioral biometrics and user profiling, the approach ensures accurate detection and mitigation of both intentional and unintentional threats. This approach can be applied in any environment where user log is prevalent.
Genomic and epidemiological profile of cervical cancer patients - identifying risk factors, pathways and novel variants through integrated survey and whole exome sequencing strategies
(Avinashilingam, 2025-01) Sudha B; Guide - Dr. S. Sumathi
Cervical cancer is a serious global health concern in Tamil Nadu, India. It significantly affects rural women due to their fewer facilities and lesser knowledge regarding healthcare. The study was designed to examine cervical cancer's sociodemographic, clinical, and genetic aspects, thereby identifying existing knowledge gaps, enhancing clinical perception, and determining molecular targets for precision medicine. The socio-demographic assessment revealed poor awareness of the symptoms, preventive measures, and immunization, the most severe deficit in rural areas. Clinical profile analysis of cervical cancer patients from Sri Ramakrishna Hospital, Coimbatore, Tamil Nadu, revealed that middle-aged rural women were the most affected and squamous cell carcinoma is the predominant subtype. The advanced stage of diagnosis was typical, with the prevalent symptoms being abdominal pain and post-menopausal bleeding. It also proved that cisplatin combination therapy is effective enough to change survival results. Considering the dominance of squamous cell cervical cancer, we have tried to profile the mutational patterns from biopsy samples using whole exome sequencing. Genomic analysis of 37 detrimental mutations found in critical genes and confirmation of novel variants in genes like POM121C, PRICKLE1, and GLIS3 by Sanger sequencing revealed bioinformatic dysregulated pathways like Hippo and TGF-beta signaling pathways, highlighting the molecular complexity of the disease and potential targets for precision treatment. Despite the limitations of having insufficient biopsy samples, the study calls for immediate improvement in public awareness, early detection strategies, and genomic-based therapy tailored to individual needs. These results offer crucial insight into the clinical and molecular landscape of cervical cancer and pave the way for precision medicine approaches to reduce mortality rates among affected populations.
Exploring Neutrosophic Set Variants: Investigating Topological Insights, Approximation Spaces and Decision-Making Approaches
(Avinashilingam, 2025-08) Bhuvaneshwari S; Guide - Dr. C.Antony Crispin Sweety
List of Notations and Abbreviations : FS Fuzzy Set IVFS Interval Valued Fuzzy Set IFS Intuitionistic Fuzzy Set NS Neutrosophic Set SVNS Single Valued Neutrosophic Set TFS Temporal Fuzzy Set TIFS Temporal Intuitionistic Fuzzy Set PFS Pythagorean Fuzzy Set SFS Spherical Fuzzy Set PNS Pythagorean Neutrosophic Set
NSS Neutrosophic Spherical Set FNS Fermatean Neutrosophic Set FTNS Fermatean Temporal Neutrosophic Set IVFNS Interval Valued Fermatean Neutrosophic Set FNCS Fermatean Neutrosophic Cubic Set PNT Pythagorean Neutrosophic Topology PNP Pythagorean Neutrosophic Point PNTS Pythagorean Neutrosophic Topological Space PNN Pythagorean Neutrosophic Neighbourhood PNOS Pythagorean Neutrosophic Open Set PNCS Pythagorean Neutrosophic Closed Set NST Neutrosophic Spherical Topology NSTS Neutrosophic Spherical Topological Space NSP Neutrosophic Spherical Point NSN Neutrosophic Spherical Neighbourhood NSOS Neutrosophic Spherical Open Set NSCS Neutrosophic Spherical Closed Set FNT Fermatean Neutrosophic Topology FNTS Fermatean Neutrosophic Topological Space FNP Fermatean Neutrosophic Point FNN Fermatean Neutrosophic Neighbourhood FNOS Fermatean Neutrosophic Open Set FNCS Fermatean Neutrosophic Closed Set BT-FNS Bitopologies of Fermatean Neutrosophic Set BT-FNSubs Bitopologies of Fermatean Neutrosophic Subsets FTNS Fermatean Temporal Neutrosophic Set FNGO Fermatean Neutrosophic Gradation of Openness FNGC Fermatean Neutrosophic Gradation of Closedness gp- map Gradation preserving map In-BTF Category of all-inclusive BT-FNSubs and continuous functions FNr-top Category of rth graded FNTSs and gp-maps
FT-NTS Fermatean Temporal Neutrosophic Topological Spaces SFT-NT Fermatean Temporal Neutrosophic Topology in Šostak’s sense CFT-NT Fermatean temporal neutrosophic topology in Chang’s sense LFT-NT Fermatean Temporal neutrosophic topology in Lowen’s sense FTN- closed Fermatean Temporal Neutrosophic closed FTNRS Fermatean Temporal Neutrosophic Rough Set FNRAS Fermatean Neutrosophic Rough Approximation Space FN-r Fermatean Neutrosophic relation LT Linguistic Term MCDM Multi-Criteria Decision-Making CODAS Combinative Distance-Based Assessment ÐϺ Decision Maker SWAM Spherical Weighted Arithmetic Mean SWGM Spherical Weighted Geometric Mean FWAM Fermatean Weighted Arithmetic Mean FWGM Fermatean Weighted Geometric Mean D-Mx Decision Matrix NS D-Mx Neutrosophic Spherical Decision Matrix FN D-Mx Fermatean Neutrosophic Decision Matrix PIS Positive Ideal Solution NIS Negative Ideal Solution SF Score Function AC Accuracy Function TMNSDM Tangent Metric Neutrosophic Spherical Distance Measure TMFNDM Tangent Metric Fermatean Neutrosophic Distance Measure TOPSIS Technique for Order Preference by Similarity to Ideal Solution ED Euclidean distance N-ED Normalized Euclidean Distance HD Hamming Distance N-HD Normalized Hamming Distance SMSVND Sine Metric Single- Valued Neutrosophic Distance : The scope of this thesis is to explore some of the existing neutrosophic variants and introduce some new types of neutrosophic variants. The notion of extended Pythagorean neutrosophic set, neutrosophic spherical set, and Fermatean neutrosophic set has been examined and the concepts of topology, rough set, operators, and measures has been developed and analysed. The idea of the proposed logic is extended to define Fermatean neutrosophic cubic set to manage high levels of uncertainty and vagueness and also to introduce Fermatean temporal neutrosophic set to deal with time moments. Further, the thesis combines rough set concept with Fermatean temporal neutrosophic set to construct a new class of rough set called Fermatean temporal neutrosophic rough set. A new class of aggregation operators for neutrosophic variant has been developed and used in a COmbinative Distance-based ASsessment (CODAS) evaluation method. Furthermore, tangent metric neutrosophic spherical distance measure and tangent metric Fermatean neutrosophic distance measure are formulated and applied to the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. Illustrative examples have been provided to validate and compare the defined aggregation operators and distance measures.
Antioxidant Potential of Cucurbita Pepo L Pumpkin Seed Extract in the treatment of Stress Induced Male Infertility An in Vivo Study
(Avinashilingam, 2025-01) Amrutha B Nair; Guide - Rajeswari P.A
Infertility is a growing global health concern, with male factors contributing to nearly 50% of reported cases. Environmental toxicants such as lead are known to impair male reproductive function primarily through oxidative stress. Pumpkin (Cucurbita pepo L.) seeds, often discarded as biowaste, are rich in bioactive compounds and possess potential antioxidant properties. However, their role in stress-induced male infertility remains
inadequately explored. The present study investigated the ameliorative effects of C. pepo seed aqueous extract against lead acetate induced reproductive toxicity in male Wistar rats. The study was conducted in five phases involving nutritional and antinutritional profiling, phytochemical and chromatographic analyses, in vitro antioxidant assays, acute oral toxicity evaluation, and an in vivo experimental study. Thirty rats were divided into five groups: control, lead acetate (30 mg/kg bw), seed extract alone (1000 mg/kg bw), lead acetate with low-dose extract (100 mg/kg bw), and lead acetate with high-dose extract (1000 mg/kg bw). Oral administration was carried out intermittently (15th, 30th and 45th days) for a duration of 45 days. The parameters such as body weight and individual organ weight measurements, sperm parameters, hormonal assays, serum and testis antioxidant assays, and histopathology analysis of reproductive organs were carried out using established methodologies. Lead acetate exposure resulted in significant reductions in body and individual organ weights, sperm count, motility, viability, reproductive hormone levels (FSH, LH and testosterone) and antioxidant enzyme levels (SOD, GPx, catalase) along with increased sperm abnormalities, semen pH, lipid peroxidation (MDA), and
histopathological alterations in reproductive organ tissues. Co-administration of C. pepo seed extract, particularly at the higher dose, significantly ameliorated these alterations in a dose-dependent manner. The key finding of this research was that the C. pepo seed extract treatment has mitigated lead induced toxicity and exhibited significant improvement in their reproductive potential owing to the antioxidant property of their phytochemical components. Keywords: Male Infertility, Oxidative Stress, Lead Acetate, Cucurbita pepo L. Seeds,
Antioxidant Potential
Acquisition and adoption of Digital Competency among Women Entrepreneurs in the Informal Sector
(Avinashilingam, 2025-07) Mary Treasa C P; Guide - Dr. P .Shanthi
Digital competency has emerged as a critical requirement for business development, sustained growth, and long-term competitiveness across sectors. The ability to navigate digital tools and platforms enhances operational efficiency, facilitates access to broader markets, strengthens customer engagement, and improves financial and administrative management. In this context, Digital skills serve as a vital indicator of an individual’s capacity to remain competitive, adapt to technological advancements, and leverage innovation for sustainable business outcomes. In the absence of adequate digital proficiency, many face the risk of exclusion from mainstream economic activities. The present study examines the influence of core antecedents, namely digital
competency, performance expectancy, effort expectancy, social influence, and facilitating conditions, on behavioural intention, and how these factors contribute to the actual usage of technology in business operations. The study adopts the Unified Theory of Acceptance and Use of Technology (UTAUT) as its theoretical framework, which effectively captures the interplay between these constructs and their impact on technology adoption. The study is both descriptive and analytical. The locale of the study is Palakkad district in
Kerala, India, which was purposively selected due to its prominence for largely informal micro-enterprises. Primary data were collected from a sample of 240 informal women entrepreneurs using a structured questionnaire, and the internal consistency of the instrument was confirmed with a Cronbach’s alpha value exceeding 0.70, indicating acceptable reliability. In addition, secondary sources such as government reports,
published research articles, and institutional databases were utilized to complement and contextualize the findings. Targeted Digital competency intervention addresses the digital skill gap by systematically enhancing individual abilities in preparing training modules across key dimensions of digital competency and business applications for business operations. Moreover, technology adoption is closely linked to behavioural factors of
technology adoption. Rank analysis was employed to identify the most significant challenges to technology adoption. To assess whether a significant mean difference existed in digital competency levels of women in the informal sector before and after the training intervention, the Wilcoxon Signed-Rank Test was applied. Additionally, the Kruskal-Wallis Test and the Mann-Whitney U Test were used to examine significant
differences in digital competency across various socio-demographic and business profile variables of the respondents. The Structural Equation Modelling (SEM) was conducted to evaluate the influence of key antecedents of behavioural intention on the actual use of technology The result indicated that digital competency was found to be significantly influenced by performance expectancy, indicating that enhanced digital skills improve perceptions of technology’s usefulness in business operations. This perception of performance expectancy, in turn, had a strong positive impact on behavioural intention to adopt technology. Social influence also emerged as a significant predictor of behavioural intention, emphasising the role of peer support and community validation in shaping technology adoption decisions. Furthermore, both digital competency and behavioural intention significantly contributed to the actual use of technology in business, confirming
their pivotal roles in the adoption process. Behavioural intention was also identified as a key mediator between social influence and actual technology usage. On the other hand, Digital competency did not influence effort expectancy, suggesting that users still perceive new technologies as requiring effort despite increased digital proficiency. Effort expectancy and facilitating conditions did not significantly affect behavioural intention,
indicating that ease of use and external support were less influential in determining intent to adopt technology. The sustained technology adoption is more closely tied to internal factors such as digital competency and perceived performance benefits than to structural or external enablers alone. Keywords: Women Entrepreneurs, Technology Adoption, Digital Competency, Behavioural Intention, Performance Expectancy, Effort Expectancy, Social Influence, Facilitating Conditions, Actual Usage.