Publication Search

The integration of Artificial Intelligence (AI) into precision agriculture has significantly improved plant disease recognition; however, many existing deep learning models remain computationally expensive and feature-redundant, limiting their deployment on low-power and edge devices. To address these limitations, this study proposes a lightweight framework for maize leaf disease recognition based on serial deep feature extraction, dimensionality reduction, and machine-learning–based classification. A pre-trained MobileNetV2 network is employed as a fixed feature extractor to obtain discriminative visual representations, while Principal Component Analysis (PCA) is applied to reduce feature dimensionality by approximately 76%, retaining 95% of the original variance and improving computational efficiency. The compressed features are subsequently classified using a Radial Basis Function Support Vector Machine (RBF-SVM), optimized via grid search and cross-validation. Experiments conducted on a four-class maize leaf disease dataset (Northern Leaf Blight, Common Rust, Gray Leaf Spot, and Healthy), with class imbalance handled during training, demonstrate that the proposed MobileNetV2–PCA–SVM pipeline achieves 97.58% accuracy, 96.60% precision, 96.59% recall, and 96.59% F1-score, outperforming the DenseNet201 + Bayesian-optimized SVM baseline (94.60%, 94.40%, 94.40%, and 94.40%, respectively). This improvement corresponds to a 2.98% accuracy gain, a 55% reduction in error rate, an 86% reduction in model parameters (20.31M to 2.75M), and an 85% reduction in model size (81 MB to 12 MB). These results indicate that the proposed framework provides a compact and efficient solution with strong potential for deployment in resource-constrained agricultural environments.

The increasing consumption of packaged food products in Indonesia reflects modern lifestyle changes but simultaneously raises public health concerns related to high calorie, sugar, and fat intake. Nutritional information presented on food labels consists of multiple interrelated variables, making it difficult to identify dominant nutritional factors that characterize packaged food products. This study aims to apply Principal Component Analysis (PCA) to reduce the dimensionality of nutritional data and to map the nutritional characteristics of packaged food products in Indonesia. The research employs a quantitative exploratory approach using secondary data obtained from nutrition facts labels of 1,651 packaged food products. Seven nutritional variables were initially analyzed, namely total energy, protein, total fat, total carbohydrates, sugar, sodium, and dietary fiber. Data preprocessing included data cleaning, Z-score standardization, and iterative variable selection based on the Kaiser-Meyer-Olkin (KMO) measure and Bartlett’s Test of Sphericity to ensure sampling adequacy and sufficient correlation among variables. Variables with low sampling adequacy and perfect multicollinearity were eliminated, resulting in five variables retained for the final PCA model. Principal components were extracted using the eigenvalue greater than one criterion and confirmed through a scree plot, followed by Varimax rotation to enhance interpretability. The results indicate the formation of two principal components explaining approximately 69.7% of the total variance. The first component represents energy density and macronutrient richness, while the second component reflects carbohydrate-related characteristics, particularly the contrasting pattern between sugar and dietary fiber. Biplot visualization further illustrates product distribution based on these components. The findings demonstrate that PCA effectively simplifies complex nutritional information and provides a clear nutritional mapping of packaged food products, offering practical insights for consumers, producers, and policymakers in supporting healthier food choices in Indonesia.

This study develops a computational-based system to identify individual potential through the analysis of signature patterns using Artificial Neural Networks (ANN) and the Backpropagation algorithm. The research aims to explore and examine the effectiveness of applying ANN in recognizing and identifying signature patterns that are assumed to be related to an individual’s potential. In the data processing stage, Principal Component Analysis (PCA) is employed as a dimensionality reduction and feature extraction technique to optimally obtain the main characteristics of signature images. The system performance evaluation is conducted using a total of 80 signature images, consisting of 60 training data and 20 testing data. This study analyzes two network architecture configurations, namely a model with one hidden layer and a model with two hidden layers. The experimental results show that both network configurations achieve the same accuracy level of 92.5%. These findings indicate that the use of Artificial Neural Networks with the Backpropagation algorithm is effective in producing high accuracy in the signature pattern recognition process. Furthermore, the developed system has broad potential applications in the field of personal identification, such as employee evaluation, selection systems, and other applications across various organizational and industrial sectors.

This study aims to apply the Principal Component Analysis (PCA) method to identify the main factors influencing poverty in North Sumatra Province. Poverty rates in this region show significant variations among districts and cities, influenced by differences in social, economic, educational, and basic facility availability. The data used in this study include eleven indicators related to population, education, health, access to basic services, and economic conditions. All variables were initially normalized to ensure they had comparable scales, then PCA feasibility tests were conducted using MSA, KMO, and Bartlett's test, which indicated that the data were eligible for further analysis. The results of the PCA revealed three main components explaining a total of 69.91 percent of the variation. The first component represents regional population and economic factors, with the largest contributions coming from population density, open unemployment rate, and per capita expenditure. The second component reflects household living conditions, such as access to clean water, adequate sanitation, and health complaints. The third component describes the educational dimension through indicators of the population aged at the primary and secondary school levels. These findings indicate that poverty in North Sumatra is influenced not only by economic factors but also by the quality of basic services and education levels among the population. Therefore, this research is useful for policymakers at the central and regional government levels to consider the factors influencing the increase in poverty in North Sumatra.