http://drr.vau.ac.lk/handle/123456789/247 Sat, 09 May 2026 17:36:55 GMT 2026-05-09T17:36:55Z http://drr.vau.ac.lk/handle/123456789/2057 The impact of Promotional Strategies on Brand Awareness - Special Reference to Full Cream Milk Powder Brands available in Vavuniya District Praveena, R.; Jude Leon, S.A. Marketers carry out different kinds of promotional strategies to survive their brands in the market place. But most of them fail to succeed, because of the incorrect promotional strategy would be selected, suited to their target audience of the brands. As a result, promotional strategies are said to be useless to stimulate the customers to buying it. Therefore, present study attempted to identify what extent the promotional strategies namely advertising, sponsorship, packaging, and sales promotion impact on brand awareness. To study the relationship between promotional strategies and brand awareness, and to find out the most influential promotional strategy, which effect on brand awareness of selected milk powder brands in Vavuniya district of Sri Lanka. A total of 100 consumers in Vavuniya were surveyed via structured questionnaire to carry out we have chosen convenience sampling method. Based on the literature, five hypotheses were drafted and tested via correlation and regression models. Study found that there is a positive relationship between promotional strategies and brand awareness. Further, the research implicated that attractive packaging of the brand and various levels of sales promotion activities lead to high level of brand awareness. However, advertising has better influence than other variables. These findings showed that the brands, which targeted to the specific direct segments, should be promoted through the appropriate promotional strategies which have direct association with creating brand awareness, therefore marketers, especially brand managers have to consider the implication of having effective promotional strategies rather than promoting just with a selected strategy. Sat, 01 Jan 2011 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/2057 2011-01-01T00:00:00Z http://drr.vau.ac.lk/handle/123456789/2049 Mining for Insights: An Evaluation of Association Rules for Household Water Perception Data Satheeskumar, T.; Satheeskumar, T.; Selvarajan, P. Understanding household perceptions of water quality and safety is essential for effective water management and public health planning. This study analyses household water perception data from Sri Lanka’s Northern Province using Association Rule Mining (ARM). Data from 101 households covering twelve categorical perception variables were examined using the Apriori algorithm. Frequent itemsets and association rules were evaluated using support, confidence, and lift measures. The analysis identified consistent perception patterns, particularly linking perceived water quality and supply reliability with household precautionary practices. Several strong, high-confidence rules indicated non-random relationships among perception variables. Overall, the findings demonstrate that ARM is a transparent and effective method for uncovering latent perception structures in household survey data and provides useful insights to inform water management and public health interventions. Thu, 01 Jan 2026 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/2049 2026-01-01T00:00:00Z http://drr.vau.ac.lk/handle/123456789/2048 Hybrid CNN-SVM model for face mask detector to protect from a seasonal allergy Thevaka, S.; Suthesan, K. Masks used to avoid the spread of the infection to be used especially in closed and crowded environments, the people should continue wearing face mask which can protect from seasonal allergies. It reduces the symptoms associated with seasonal allergies. A dataset consisting of images of people with masks or without mask is created and used in this study. The images were collected in total 7553 from Kaggle and own since a dataset that relates to faces has many privacy issues attached it. We converted image size into 128 *128 and transformed into RGB. The study considers an approach that aggregates Convolution Neural Networks (CNN) deep learning techniques and classical ML classifiers. To classify images into masked and unmasked own architecture on CNN was used to extract unique features, then Support Vector Machine (SVM) used to classify the image. Purpose of the hybrid modelling on CNN, it recognizes these advanced features from the sample data, thus reducing the workload of developing a new feature extractor for such problem and when the number of data is small, CNN do not work well. In order to sort out that issue we bring SVM algorithm also here which can be possessing high accuracy even with less data. The problem for our proposed model is to learn the interpretation of various features in images and classify accordingly. By analysing various architectures on CNN, own model created in leveraging the spatial information in images. With this concept, the own architecture designed because some of existing architectures are complex, some pertinent information may be lost there during feature extraction phase and the computation time is considerable. The pervious Custom CNN architecture Model training accuracy reached 94% and Validation accuracy 96%. When the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This indicated that the proposed fusion achieved superior recognition accuracy of 97.35 % compared to the previous approach. We used 1511 data for testing from that 10% used for validation. Mon, 01 Jan 2024 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/2048 2024-01-01T00:00:00Z http://drr.vau.ac.lk/handle/123456789/2047 A CNN-LSTM Technique Based Optimization Model for Estimating Obesity Level Thevaka, S.; Deegalla, S.; Viththakan, S. Obesity is a rapidly increasing global health concern linked to numerous chronic diseases and significant healthcare challenges, emphasizing the need for accurate early prediction and intervention strategies. This study aims to develop an effective predictive model for obesity risk using a hybrid deep learning approach that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) architectures. The proposed model utilizes health-related data, where CNN is employed for efficient feature extraction and LSTM captures temporal and sequential patterns within the dataset. The model performance was evaluated using standard metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, along with cross-validation techniques to ensure robustness. The experimental findings indicate that the hybrid CNN-LSTM model achieves superior predictive performance compared to conventional machine learning models and individual deep learning approaches. The results demonstrate improved classification accuracy and reliability in identifying individuals at risk of obesity. This study highlights the potential of integrating advanced deep learning techniques into clinical decision support systems, enabling early diagnosis, effective risk stratification, and informed preventive healthcare interventions to reduce the burden of obesity. Mon, 01 Jan 2024 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/2047 2024-01-01T00:00:00Z