Glaucoma which part of Diabetic Retinopathy is the disease distorted optical nerve system and resulted loss in vision. Fractal dimension one feature extraction that can been used retinopathy fields due to fractal able characterize retinal vasculature. In this paper, we presented a research based on not only distinguish healthy subjects diabetic patients, but also severe level patients. By using MESSIDOR dataset Random Forest as Classifier, obtained results dimensions are it did obtain...

Data in the real world, there are many conditions (situations) where number of instances one class is much less than other classes. This situation a problem unbalanced datasets (imbalance class). As result, performance classification will decrease some data systems. In this study, it was identified that apple leaf disease dataset used had large enough imbalance comparison between 1:5, so an oversampling method needed to solve problem. Methods can be include Synthetic Minority Over Sampling...

This research explores public discourse on financial policies by analyzing tweets mentioning the keyword 'Kemenkeu' (Ministry of Finance). Using Latent Semantic Analysis (LSA), study examined 10,099 to uncover key topics that reflect sentiment toward Ministry’s policies. Preprocessing steps, such as stopword removal and stemming with Sastrawi, were essential ensure effectiveness analysis. The results revealed three main topics: Finance Budget, Salaries Employee Welfare, Excise Customs...

Stunting, characterized by impaired growth and development in children, is one of the most serious public health problems often caused chronic malnutrition. This study aims to identify patterns among stunting cases through clustering analysis child data. The algorithm used this research uses K-Means. dataset data from 599 children Sambas Regency area East Kalimantan Province. has several features that are quite diverse such as height, weight, age, nutritional intake, socioeconomic status,...

In the digital era, ensuring customer satisfaction with IT services is crucial for business success. However, complexity of infrastructure makes it difficult to manage services, requiring companies focus on improving efficiency and reducing operational costs. One strategies used Information Technology Service Management (ITSM), main component which incident management, aims minimize service disruptions. While various studies ITSM exist, research focused Machine Learning models predicting...

Batik, an Indonesian cultural heritage recognized by UNESCO, faces challenges in pattern identification and documentation, particularly for the younger generation. Previous studies on batik classification have shown limitations handling small datasets maintaining accuracy with limited computational resources. This research proposes enhanced approach Semarang Batik motifs using MobileNetV2 architecture combined strategic data augmentation techniques. The study utilizes a dataset of 3,020...

Polycystic Ovary Syndrome (PCOS) is a hormonal disorder affecting women of reproductive age, with global prevalence rate 8–13%. However, approximately 70% cases remain undiagnosed. This study aimed to develop and compare eight Random Forest classification models for PCOS detection using publicly available Kaggle dataset. The methodology incorporated three key preprocessing techniques: outlier handling the Interquartile Range (IQR) method, feature selection through Mutual Information, class...

Medical image segmentation, especially in chest X-ray (CXR) analysis, encounters substantial problems such as class imbalance, annotation inconsistencies, and the necessity for accurate pathological region identification. This research introduces NCT-CXR, a robust framework that enhances semantic segmentation CXR images using an improved coordinate-geometric transformation strategy. NCT-CXR integrates carefully calibrated geometric transformations with intensity-based augmentations, ensuring...

Desa Banyuanyar merupakan salah satu desa di Kabupaten Boyolali dengan populasi sapi mencapai 1.840 ekor yang berpotensi menghasilkan limbah kotoran sebanyak 32 ton per hari. Limbah dibuang ke lingkungan dapat menyebabkan masalah kesehatan dan lingkungan. Tujuan dari kegiatan pemberdayaan wilayah ini adalah untuk mengembangkan penggunaan biogas sebagai energi alternatif memanfaatkan sapi. Rangkaian meliputi analisis komunitas, pembangunan biodigester biogas, slurry, pelatihan biodigester....

Feature selection and ensemble learning can be used to improve the accuracy robustness of epileptic seizure detection classification. Unfortunately, a few studies have fully utilized feature learning. In this paper, we present an adaptive hybrid selection-based classifier (AHFSE) for The AHFSE creates new sample subsets in every bootstrap using selection. It combines them rank aggregation obtain distinguished subset features. These samples' are then fed into classifier. Finally, majority...

Twitter adalah salah satu media sosial dan fasilitas microblogging yang menjadi tempat bagi penggunanya berbagi pengalamannya secara bebas, realtime, bersifat publik. Hal ini dapat menjadikan twitter sebagai sumber informasi berupa opini, ataupun komentar positif maupun negatif. Dari opini masyarakat tersebut diimplementasikan tolak ukur, karena memiliki nilai suatu perusahaan agar bahan evaluasi untuk menentukan langkah dalam meningkatkan layanannya. Oleh itu mengolah dibutuhkan teknik...

Sentiment analysis in terms of polarity classification is very important everyday life, with the existence polarity, many people can find out whether respected document has positive or negative sentiment so that it help choosing and making decisions. usually done manually. Therefore, an automatic process needed. However, rare to studies discuss extraction features which learning models are suitable for unstructured types Amazon food review case. This research explores some such as Word Bags,...

The SME sector in Indonesia comprises 99.99% of businesses, employing 96.9% the workforce and contributing 60.5% to GDP non-oil exports.Despite their importance, SMEs face challenges including limited financial access, product hygiene concerns, fluctuating demand.Accurate demand prediction is crucial for optimizing production, inventory, resource allocation.SARIMAX VAR models are commonly used prediction, with SARIMAX proving more effective, especially when integrating weather data.Due there...

Micro, Small, and Medium Enterprises (MSMEs) constitute a significant portion of the economy in many developing countries, playing vital role employment generation economic growth. Sales performance is critical factor for MSMEs, influenced by various internal external factors. Time-series analysis offers valuable tool to predict sales quantities analyzing historical data identifying patterns trends. In this context, SARIMAX (Seasonal Autoregressive Integrated Moving Average with Exogenous...

Multi-label learning plays a critical role in the areas of data mining, multimedia, and machine learning. Although many multi-label approaches have been proposed, few them considered to de-emphasize effect noisy features process. To address this issue, paper designs new method named representative algorithm. Instead considering all features, proposed algorithm focuses only on ones, via incorporating an affinity propagation algorithm, kernel formulation, support vector into framework....

Masyarakat mampu mengkonsumsi tiap informasi yang tersebar di internet dengan cepat dan terkadang beredar tidak selalu memberikan kebenaran sesuai kenyataannya (hoax). Demi mendapatkan keuntungan mencapai tujuan pribadi, hoax seringkali sengaja dibuat dibagikan. Informasi didapatkan dari tentunya dapat mempengaruhi masyarakat karena menimbulkan keraguan kebingungan terhadap diterima Oleh itu, penelitian ini membahas tentang bagaimana mengklasifikasikan berita berbahasa Indonesia mengenai isu...

Agriculture is a source of income for the country. One most promising agricultural commodities shallots. Shallots are always found in every traditional market, markets one connecting places between buyers and sellers shallots to carry out buying selling activities Onion carried still conventional this case, such as payment processing that use cash, then price not fixed, aka can haggle, so these two things quite time-consuming personnel business process shallot sales transactions. For reason,...

E-commerce is selling and buying goods through an online or system. One of the business models in which consumers sell products to other Customer (C2C) model. thing that needs be considered model knowing level customer loyalty. By loyalty, company can provide several different treatments its customers maintain good relationships with increase product purchase revenue. In this study, author wants segment on data companies Brazil using K-Means clustering algorithm RFM (Recency, Frequency,...

An influencer can be a netizen who influences society, it positive or negative effects, depending on what they say social media. Therefore, guide is needed to determine the types of influencers and effect have when an shares information, something, provide comments so that people will know kind are facing. This research development previous studies, as listed in introduction. The survey has conducted thirty covering general public, college student, lecturers influencers' influence study's...

Red Onion or the Latin name Allium Cepa is included in group of vegetable plants that are needed by public for food needs. Onions one seasonal crops so their availability can change market which causes price instability due to a lack supply production several factors: 1) not yet it's harvest time, 2) crop attacked disease pests and fungi, 3) weather factor. Therefore, study predict red onion prices, it be used as information government stabilize prices. The method this CRISP-DM Extreme...

Indexing content is the process of text mining.An index made using root words that can be located in text.The section includes found index.The also used as a database to find trends text, such how frequently word appears.Text mining essentially act turning into are then analyzed.Data collection, preprocessing, Term Weigthing, and categorization some research techniques used.The goal this study identify appear Twitter comments choose best normalization technique based on dictionary.The...

Abstract Feature selection in the classification model has a role to choose relevant and interconnected features data mining task. medical world, feature can help predicting heart attack. Naive Bayes is one of most popular learning methods that predict patients helping paramedics make decisions. The addition form backward elimination increase accuracy Naïve by 89.45% from 84.29% previously. results this study indicate method attack quite high adding accuracy.

The ensemble learning approach, especially in classification, has been widely carried out and is successful many scopes, but unfortunately not approaches are used for the detection classification of epilepsy biomedical terms. Compared to using a simple bagging framework, we propose fusion bagging-based framework (FBEF) that uses 3 weak learners each oracle, rules, learner will give results as predictors oracle. All oracle be included trust factor get better prediction classification....