Consumer Preferences for Purchasing Local Fruits at The Farmers Market Supermarket in Palembang City

/0 Comments/in /by

Fruit consumption in Palembang City remains below the World Health Organization (WHO) recommendation and has not reached an optimal level. Meanwhile, the increasing availability of imported fruits creates competition and affects consumer preferences toward local fruits. This study aims to identify the attributes influencing consumer preferences, analyze the dominance of physical and non-physical attributes, and examine the effect of imported fruit presence. A quantitative survey was conducted involving 100 respondents selected through accidental sampling. Data were analyzed using the Fishbein multi-attribute model, multiple linear regression, and path analysis. The results show that freshness, taste, and price are the main attributes shaping consumer attitudes. The attitude score (Ao) is categorized as high (101.167 or 67.44%), indicating that stronger positive attitudes are associated with higher consumer preferences for local fruits. Regression analysis reveals that product attributes significantly influence preferences, with physical attributes as the dominant factor. Meanwhile, the presence of imported fruits does not have a significant effect. These findings indicate that consumer preferences are mainly driven by product attributes and attitudes, suggesting that improving the quality of local fruits is essential to enhance their competitiveness.

Explainable Pneumonia Detection in Chest X-Rays: A Comparative Study of CNNs and Vision Transformers

/0 Comments/in /by

Pneumonia is a leading cause of global mortality, especially among children and the elderly, and chest radiography (CXR) remains the most widely used modality for its diagnosis. While deep learning has reached or exceeded radiologist-level performance on this task, the resulting models are still treated as opaque black boxes, which is a critical barrier to clinical deployment. In this work, we present a comparative and interpretable computer-aided-diagnosis (CAD) framework for pneumonia detection that combines three modern image-recognition backbones—a convolutional ResNet-50, a Swin Transformer (Swin-T), and a modernised convolutional network (ConvNeXt-T)—with Gradient-weighted Class Activation Mapping++ (Grad-CAM++) explanations. The three backbones were fine-tuned on the public Kermany chest X-ray dataset using a class-balanced training subset, weighted cross-entropy and an early-stopping protocol, and then evaluated on the held-out test set of 624 images. The Swin-T backbone achieved the best overall performance with a test accuracy of 95.51%, an F1-score of 0.95 and only 11 false negatives out of 234 normal cases, outperforming both ResNet-50 (93.11%) and ConvNeXt-T (88.94%). Grad-CAM++ heatmaps generated from the convolutional and transformer feature maps consistently localised on the affected pulmonary regions, providing radiologically plausible visual evidence for each prediction. Compared with five recent state-of-the-art pneumonia detectors, our Swin-T-based pipeline reaches a competitive accuracy while delivering layer-faithful visual explanations, supporting its use as a transparent decision-support tool in clinical workflows.