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.

This study discusses the introduction of digital signature patterns using the Backpropagation method on Artificial Neural Network (JST) to identify a person's characteristics and potential. The increasing use of digital identities demands a verification system that is more secure, accurate, and adaptive to the variations of each individual's signature. The main problem faced in the signature recognition system is the low level of accuracy when the visual features of the signature have similarities between users, both in terms of shape, size, and stroke pressure. In addition, variations of signatures made by the same individual are also a challenge in the identification process. As a solution, this study implements Principal Component Analysis (PCA) to extract important features from the signature image before the training process using JST. PCA is used to reduce the data dimension so that the learning process becomes more efficient and optimal. A total of 80 signature images were used in this study, consisting of 60 training data and 20 test data. The results showed that the system was able to achieve an accuracy level of 92.5%. These findings prove that the combination of PCA and JST methods is effective in recognizing digital signature patterns and has the potential to be applied to digital security-based biometric identification systems.

The development of information technology has encouraged institutions, including hospitals, to adopt digital systems to improve operational efficiency. One important aspect is the employee attendance system, which previously relied on fingerprints. This method has limitations, such as difficulty detecting when fingers are not in ideal condition and causing queues during peak hours. This research aims to design and implement an Android-based attendance system using the Eigenface facial recognition method as a faster, safer, and more accurate alternative. Eigenface works by extracting facial features using Principal Component Analysis (PCA), thus being able to efficiently recognize individual identities. The system was developed with MySQL database integration and tested on employees of Khalishah General Hospital. The implementation results showed that the system can recognize faces with a good level of accuracy and increase the effectiveness of attendance recording. Furthermore, the use of facial-based attendance can minimize the potential for fraud and increase user comfort because it does not require physical contact. Thus, the Eigenface method has proven feasible to be implemented as a modern attendance solution to support employee attendance management in hospital work environments and other institutions.

The Maluku Islands are a high-poverty region in Indonesia. The region consists of 2 provinces, namely Maluku province and North Maluku province. There are 21 districts/cities in the region, with 17 regencies and 4 municipalities. The poverty rate in this region is a challenge that always wants to be studied with a socio-population approach and a mathematical statistics approach. One method or approach in analyzing poverty is Principal Component Analysis (PCA).  PCA has the advantage of simplifying information from various variables to several principal components without losing much information and can overcome the problem of multiple linearity by changing variables that correlate with freely related components. The purpose of this research is to identify poverty in districts/municipalities in Maluku Islands using the PCA approach. The results showed that the components formed by the PCA method were formed in 2 factors. Factor 1 consists of GRDP (X2), Life Expectancy Rate (X3), Unemployment Rate (X4) and Percentage of Population (X6). Meanwhile, factor 2 consists of 2 variables, namely the Poverty Level (X1) and TPAK (X5).

Chitosan is a natural polysaccharide derived from chitin, commonly found in the shells of crustacean animals. The production of chitosan involves several stages: deproteinization, demineralization, and deacetylation, which require the use of acidic and alkaline solutions. This study aimed to evaluate the effectiveness of various types of organic acids and a natural acid source, Averrhoa bilimbi (bilimbi fruit) extract, in the chitosan extraction process from Vannamei shrimp shells. The study employed a completely randomized design with a single factor consisting of four acid treatments: acetic acid (AA), citric acid (CA), lactic acid (LA), and bilimbi fruit extract (BE), each replicated three times. The chitosan obtained from each treatment was analyzed for its chemical characteristics and mineral content, and the results were further analyzed using Principal Component Analysis (PCA). The best results were obtained from the citric acid treatment, which produced chitosan with a moisture content of 6.59%, a degree of deacetylation of 91.72%, ash content of 2.68%, and magnesium and calcium contents of 2.56 mg/100g and 0.15 mg/100g (dry basis), respectively. In contrast, the bilimbi extract treatment resulted in an ash content of 41.64%, with magnesium and calcium contents of 1456.52 mg/100g and 4.17 mg/100g (dry basis), indicating that the bilimbi fruit extract still has low demineralization effectiveness.

This study aims to optimize the implementation of the K-Nearest Neighbors (K-NN) algorithm for medical image classification by focusing on selecting the optimal KKK parameter and applying dimensionality reduction techniques to improve accuracy and efficiency. The data used was sourced from public medical image repositories such as The Cancer Imaging Archive (TCIA) and Medical Image Analysis datasets, covering various diseases, including brain tumors, lung cancer, and kidney lesions. The research process involves data collection, data preprocessing, dimensionality reduction using Principal Component Analysis (PCA), applying the K-NN algorithm with Euclidean, Minkowski, and Cosine distance metrics, and performance evaluation using accuracy, precision, recall, and F1-score. Experimental results demonstrate that K=5with the Euclidean distance metric provides the best performance, achieving an accuracy of 90%. Additionally, PCA effectively reduces computational time by 30% without significantly compromising accuracy. This study proves that K-NN is an effective method for medical image classification. However, further research is needed to integrate K-NN with deep learning models to enhance performance and feature extraction capabilities.

Poverty is one of the main issues in Indonesia although many policies have been implemented by the government to overcome this problem. With this problem, a study was conducted which aims to identify factors that affect poverty in East Java in 2023 using the principal component analysis (PCA) method. PCA is a multivariate analysis technique used to extract information from correlated data, so as to summarize several variables into principal components. In this study, the variables used include the number of poor people, percentage of poor people, poverty severity index, open unemployment rate, labor force participation rate, and life expectancy from 38 districts/cities in East Java. It was found that the data characteristics had low variance with the exception of one variable, and met the assumptions of multivariate normal distribution, interrelationship between variables, data sufficiency, and correlation between variables suitable for PCA. Factor analysis with PCA produces two main components, namely community living conditions and labor conditions, which can represent the original variables in their influence on poverty in East Java. Suggestions from this study are expected to be a reference for policy makers in improving community welfare and labor conditions in East Java. Future research is expected to add related variables to obtain more detailed results.

Indonesia has significant fisheries potential due to its vast waters. Its abundant fishery resources have strong export potential. However, export activities often face challenges that cause export volumes to fluctuate. This fluctuation is influenced by various factors. These factors can be minimized using statistical methods such as Principal Component Analysis (PCA) and Factor Analysis. This study includes data characterization for each variable and testing PCA and factor analysis assumptions, including multivariate normality testing, independence testing (Bartlett's test), sampling adequacy (KMO test), anti-image correlation testing, PCA testing, and factor analysis. The results indicate that the percentage contribution of fisheries to GDP, the number of coastal villages with disaster mitigation facilities, and the average daily per capita calorie consumption from fish are relatively less dispersed and not highly variable around the mean. Additionally, all data meet the assumptions, and the sample size is adequate. Factors such as aquaculture pond production and the percentage contribution of fisheries to GDP sufficiently explain the data variations.

Factor analysis is a statistical method aimed at exploring correlations or relationships among variables studied, which are then grouped into fewer new factors. Principal Component Analysis (PCA) is a statistical technique used to reduce the dimensions of data with the goal of identifying hidden patterns or significant structures within the data. The research results indicate the presence of 5 factors influencing the decision-making process in online shopping among students of the University of North Sumatra via Shopee, namely the Funding Application Factor (28.141%), Information Reputation Factor (13.983%), Communication Satisfaction Factor (7.452%), Types and Compensation Factor (6.683%), and Guarantees and Prices Factor (5.794%). These five factors obtained a cumulative variance of 62.051%, indicating that they influence online shopping decisions through Shopee among University of North Sumatra students by 62.051%.

This paper will employ a novel approach that builds upon the lasso method, utilizing it in two stages.   The first stage applies to the principal components to select the important principal component and exclude the unimportant ones. This technique is effective in identifying significant principal components while attempting to eliminate bias in selecting these components over others. Additionally, it removes the ranking in determining the principal components compared to classical methods.  Moreover, the second stage involves determining the effective importance within each component by zeroing out the scores loading values within each component. To compare the performance of the proposed method in principal component analysis, a simulation approach can be used. Subsequently, the performance of the proposed method is tested using real data.

In the agricultural sector, the automatic identification of chili pepper varieties is crucial for improving production efficiency and quality. This study developed a chili pepper variety detection system based on characteristics using the Principal Component Analysis (PCA) method. The PCA method was used to reduce the dimensionality of chili pepper image data, thereby facilitating the classification process while retaining the key features necessary for chili pepper variety identification. The recognition system for chili pepper identification involves inputting chili pepper image data into a computer. The computer then interprets and identifies the chili pepper variety, and the test data utilizes a dataset of chili pepper images from various varieties. The research results indicate that the proposed system achieves a high level of accuracy in detecting and classifying chili pepper varieties. Consequently, this system can assist farmers and agricultural industry stakeholders in the chili pepper sorting and selection process, thereby improving operational efficiency and the quality of the harvest.