Claim Missing Document
Check
Articles

Found 18 Documents
Search

Pelayanan Lembaga Pendidikan Anak Usia Dini Untuk Mempersiapkan Generasi Indonesia Seutuhnya Winarno, Sri
Jurnal Ekonomi Bisnis dan Kewirausahaan Vol 4, No 2 (2015): Jurnal Ekonomi Bisnis dan Kewirausahaan
Publisher : Jurnal Ekonomi Bisnis dan Kewirausahaan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (6.026 KB)

Abstract

Pendidikan  merupakan  hal  yang  sangat  penting  bagi  kesejahteraan  anak  dan berkontribusi  terhadap  penurunan  kemiskinan  dan  ketidaksetaraan.  Kualitas  layanan lembaga pendidikan yang baik berperan penting dalam menyukseskan tumbuh kembang anak untuk mencetak generasi masa depan yang mumpuni, membanggakan dan bermoral, yang dimulai dari periode emasnya yaitu Pendidikan Anak Usia Dini (PAUD). Penelitian ini  mengunakan  Metode  Focus  Group  Discussion  (FGD)  merupakan  metode  kualitatif.Hasil Penelitian ini menunjukan bahwa perlu ditingkatkan pelayanan lembaga pendidikan agar mampu mewujudkan generasi Indonesia  seutuhnya.Kata Kunci: Pelayanan, PAUD , Generasi.
Penyuluhan Dan Pelatihan Invisible & Visible Knowledge Profiling Untuk Meningkatkan Kompetensi Pada SMA Negeri 3 Semarang Gamayanto, Indra; Sukamto, Titien Suhartini; Sani, Ramadhan Rakhmat; Wibowo, Sasono; Winarno, Sri; Rohmani, Asih
ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT Vol 4, No 3 (2021): September 2021
Publisher : LPPM UNIVERSITAS DIAN NUSWANTORO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/ja.v4i3.274

Abstract

AbstrakPendidikan memiliki arti menggabungkan antara pengetahuan dan pengalaman untuk menghasilkan inovasi yang bermanfaat bagi umat manusia. Keduanya saling terhubung satu sama lain dan tidak boleh dipisahkan. Oleh sebab itu, menggabungkan antara pengetahuan dan pengalaman adalah hal mutlak yang seharusnya diterapkan dalam semua lini pendidikan agar siap dalam menghadapi globalisasi dengan level tertinggi. Definisi kesempurnaan adalah menggabungkan antara pengetahuan dan pengalaman sehingga menghasilkan hal-hal inovatif yang bermanfaat dan memberikan kontribusi positif terhadap hidup orang banyak. Artikel ini merupakan penyuluhan dan pelatihan invisible & visible knowledge profiling yang merupakan dua hal penting yang harus dapat dikembangkan di dalam pendidikan dan dunia kerja. Lebih jauh lagi, artikel ini merupakan pengembangan dari artikel sebelumnya yaitu pelatihan dan implementasi social media profiling. Pengabdian masyarakat yang kami lakukan haruslah berkelanjutan dan terus dikembangkan hingga mencapai tingkat kualitas tertinggi dalam pengetahuan, inilah prinsip yang terdapat pada invisible & visible knowledge profiling. Hasil dari artikel ini adalah bagaimana car akita meningkatkan kinerja sumber daya manusia yang terdapat di dalam dunia pendidikan, profil lengkap kemampuan dan sumber daya manusia yang ada, klasifikasi dan tahapan apa saja yang seharusnya dapat dilakukan. Konsep dalam artikel ini menggabungkan dengan tiga metode yaitu  3SDP-mendukung komunitas belajar aktif, merancang peluang kepemimpinan, menghasilkan sumber daya pendidikan (yang berasal dari Harvard University), Johari window dan E=KM.C2. Kata kunci: Pendidikan, Invisible-visible knowledge, Inovasi, Profiling, Sumber Daya Manusia
Machine Learning-Enhanced Geographically Weighted Regression for Spatial Evaluation of Human Development Index across Western Indonesia Firmansyah, Gustian Angga; Zeniarja, Junta; Azies, Harun Al; winarno, Sri; Ganiswari, Syuhra Putri
Journal of Applied Geospatial Information Vol 7 No 2 (2023): Journal of Applied Geospatial Information (JAGI)
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jagi.v7i2.6755

Abstract

The HDI (Human Development Index) is one of the important components to measure the level of success in efforts to improve the quality of human life. The human development index is built with three dimensions, namely the longevity and health dimension, the knowledge dimension and the decent standard of living dimension. The longevity and health dimension is measured using Life expectancy at birth. The knowledge dimension is measured using expected years of schooling and average years of schooling. Meanwhile, the decent standard of living dimension is measured using Adjusted per capita expenditure. This study aims to find factors that influence HDI (Human Development Index) in Western Indonesia Region using machine learning models. The results obtained are that HDI is influenced by average years of schooling, expected years of schooling, Life expectancy at birth, and Adjusted per capita expenditure which are sorted from the most significantly influential. The model used in this study is GWR (Geographically Weighted Regression) with evaluation results including, AIC of 215.3162, AICc of 226.5107, and the accuracy level in the form of R-square of 99.38% which means this model is good to use.
Multi-Layer Perceptron For Diagnosing Stroke With The SMOTE Method In Overcoming Data Imbalances Ariansyah, M. Hafidz; Winarno, Sri; Nur Fitri, Esmi; Arga Retha, Helynda Mulya
INNOVATICS: International Journal on Innovation in Research of Informatics Vol 5, No 1 (2023): Maret 2023
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v5i1.6565

Abstract

Stroke is the sudden loss of brain function due to an interruption of the blood supply to the brain. Stroke is a dangerous disease that can even cause death for patients. The diagnosis of stroke must be made quickly and precisely to increase the likelihood that the patient can live a normal life again. In making a diagnosis, several factors can influence the patient to get a stroke diagnosis, including symptoms of hypertension to heart disease. From these problems, the researcher wants to classify the diagnosis of stroke so that stroke can get earlier treatment so that patients do not experience prolonged illness. The data used in this study is a stroke dataset with 4861 data labeled 0 which indicates no stroke, and 249 data labeled 1 which indicates a stroke diagnosis. This study uses the Synthetic Minority Over-sampling (SMOTE) method that will be applied to the Multi-Layer Perceptron algorithm so that researchers can get the performance of the stroke diagnosis classification model. Researchers use the SMOTE method so that the data in the classification model is balanced so that the model can make accurate predictions and avoid overfitting on the Multi-Layer Perceptron so that the accuracy in predicting stroke is better than just using an ordinary Multi-Layer Perceptron. The results of the confusion matrix analysis show that SMOTE can increase the prediction of stroke diagnosis from 12,5% to 84,89% in optimal test.
Simple Additive Weight Algorithm to Determine Lecturer Competency in Hybrid Learning Approach Pratama, Rifky Ariya; Winarno, Sri; Zeniarja, Junta
Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer Vol 19, No 1 (2024): Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer
Publisher : Mulawarman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jim.v19i1.14158

Abstract

As the COVID-19 vaccination process continues, the pandemic is starting to subside. All educational institutes in Indonesia are starting to transition from online learning to hybrid learning. One crucial factor in the learning process is the competency of the lecturers. However, some students still feel dissatisfied with the learning process due to the lack of competence from the lecturers. This is exacerbated by the students and lecturers’ lack of familiarity with the hybrid learning system. Therefore, the aim of this research is to find a fair evaluation model for the lecturer’s competency that is suitable for the current hybrid learning approach. The data used in this research comes from questionnaires filled out by all students of Dian Nuswantoro University every year before the Final Semester Exam (UAS). The questionnaire consists of 10 questions regarding the hybrid learning process in the academic year of 2022/2023. Students provide their answers using a 4-point Likert scale, consisting of "Strongly Agree," "Agree," "Disagree," and "Strongly Disagree." The responses from students are grouped based on the courses/classes taught by the lecturers. The evaluation of lecturers’ competency is represented by two aspects: knowledge mastery and teaching skill. Each aspect of the lecturers’ evaluation consists of 5 questions in the questionnaire. The method used to evaluate the lecturers’ competency is the Decision Support System (DSS) algorithm combined with Simple Additive Weight (SAW). Result shows that students are mostly pleased with the quality of the lectures presented. Furthermore, lecturers with high evaluation scores tend to have a small number of students.
Comparison of Hyperparameter Optimization Techniques in Hybrid CNN-LSTM Model for Heart Disease Classification Maulani, Ahmad Alaik; Winarno, Sri; Zeniarja, Junta; Putri, Rusyda Tsaniya Eka; Cahyani, Ailsa Nurina
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 1 (2024): Articles Research Volume 8 Issue 1, January 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i1.13219

Abstract

Heart disease, which causes the highest number of deaths worldwide, recorded about 17.9 million cases in 2019, or about 32% of total global deaths, according to the World Health Organization (WHO). The significance of early detection of heart disease drives research to develop effective diagnosis systems utilizing machine learning. The advancement of machine learning in healthcare currently primarily serves as a supporting role in the ability of clinicians or analysts to fulfill their roles, identify healthcare trends, and develop disease prediction models. Meanwhile, deep learning has experienced rapid development and has become the most popular method in recent years, one of which is detecting diseases. The main objective of this research is to optimize the hybrid convolutional neural network (CNN) and long short-term memory (LSTM) model for classifying heart disease by comparing hyperparameter optimization using grid search and random search. Although random search requires less time in hyperparameter tuning, the classification performance results of grid search show higher accuracy. In the test, the hybrid CNN and LSTM model with grid search achieved 91.67% accuracy, 89.66% recall (sensitivity), 93.55% specificity, 92.86% precision, 91.23% f1-score, and 0.9310 AUC value. These results confirm that using a hybrid CNN and LSTM model with a grid search approach is better suited for classifying heart disease.
Keyword Security Implementation Based on Hill Cipher Optimized Using Genetic Algorithms Yudantiar, Mayang Arinda; Purwanto, Purwanto; Winarno, Sri
International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 5 No. 2 (2023): November 2023
Publisher : Informatics Department-Universitas Dr. Soetomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25139/ijair.v5i2.6907

Abstract

In the process of exchanging data and information, the most important task is to maintain data and information security and reach out to interested parties. One way this can be achieved is through encryption, a process better known as cryptography. Cryptography can scramble messages so that, even if intercepted, the message cannot be immediately read. One example of an encryption algorithm is the Hill Cipher. The Hill Cipher uses an m-by-m-sized matrix as the key for the encryption and decryption process, making it a challenging algorithm to crack. The key provided for the Hill Cipher encryption and decryption process cannot be arbitrary. The keys with mismatched determinants cannot be used, as they can prevent the encrypted message from being restored to its original form. Optimization can be carried out to overcome these obstacles using a genetic algorithm. Genetic algorithms can determine the keys to encrypt and decrypt the Hill Cipher. A key with the appropriate composition for the Hill Cipher will be obtained through the genetic algorithm's evaluation function. This research aims to enhance message security by using the correct composition to generate Hill Cipher encryption and decryption keys. The research results indicate that out of 10 tests conducted with different lengths of original text, eight succeeded, while two failed to complete the encryption and decryption process.
Optimizing Classification Algorithms Using Soft Voting: A Case Study on Soil Fertility Dataset Kamarudin, Fatkhurridlo Pranoto; Budiman, Fikri; Winarno, Sri; Kurniawan, Defri
Jurnal Teknologi Informasi dan Pendidikan Vol 16 No 2 (2023): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v16i2.800

Abstract

Classification algorithms are crucial in developing predictive models that identify and classify soil fertility levels based on relevant attributes. However, optimizing classification algorithms presents a major challenge in enhancing the accuracy and effectiveness of these models. Therefore, this research aims to optimize the classification algorithm in soil fertility analysis using ensemble learning techniques, specifically Soft Voting Ensemble. This research method is designed to understand soil fertility levels in modern agriculture by comparing the performance of various classification algorithms and ensemble approaches. Using a dataset from the Purwodadi Department of Agriculture, this study examines the optimization of algorithm parameters such as Random Forest, Gradient Boosting, and Support Vector Machine (SVM) and the implementation of Soft Voting Ensemble. Before applying Soft Voting Ensemble, each algorithm was evaluated with the following results: Random Forest achieved an accuracy of 90.93%, precision of 91.08%, recall of 90.33%, and F1-Score of 90.70%; Gradient Boosting achieved an accuracy of 91.53%, precision of 91.19%, recall of 91.56%, and F1-Score of 91.38%; SVM achieved an accuracy of 88.91%, precision of 89.66%, recall of 87.45%, and F1-Score of 88.54%. After implementing Soft Voting Ensemble, the accuracy improved to 91.63%, with an average precision of 91.21%, recall of 91.77%, and F1-Score of 91.49%. This study divided the data into 80% for training data and 20% for testing data. These findings indicate that the Soft Voting Ensemble has the potential to enhance agricultural productivity and sustainability.
Comparing Haar Cascade and YOLOFACE for Region of Interest Classification in Drowsiness Detection Andrean, Muhammad Niko; Shidik, Guruh Fajar; Naufal, Muhammad; Zami, Farrikh Al; Winarno, Sri; Azies, Harun Al; Putra, Permana Langgeng Wicaksono Ellwid
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.7167

Abstract

Driver drowsiness poses a serious threat to road safety, potentially leading to fatal accidents. Current research often relies on facial features, specific eye components, and the mouth for drowsiness classification. This causes a potential bias in the classification results. Therefore, this study shifts its focus to both eyes to mitigate potential biases in drowsiness classification.This research aims to compare the accuracy of drowsiness detection in drivers using two different image segmentation methods, namely Haar Cascade and YOLO-face, followed by classification using a decision tree algorithm. The dataset consists of 22,348 images of drowsy driver faces and 19,445 images of non-drowsy driver faces. The segmentation results with YOLO-face prove capable of producing a higher-quality Region of Interest (ROI) and training data in the form of eye images compared to segmentation results using the Haar Cascade method. After undergoing grid search and 10-fold cross-validation processes, the decision tree model achieved the highest accuracy using the entropy parameter, reaching 98.54% for YOLO-face segmentation results and 98.03% for Haar Cascade segmentation results. Despite the slightly higher accuracy of the model utilizing YOLO-face data, the YOLO-face method requires significantly more data processing time compared to the Haar Cascade method. The overall research results indicate that implementing the ROI concept in input images can enhance the focus and accuracy of the system in recognizing signs of drowsiness in drivers.
Analisis Perbandingan Algoritma Naive Bayes Classifier dan Support Vector Machine untuk Klasifikasi Berita Hoax pada Berita Online Indonesia Sani, Ramadhan Rakhmat; Pratiwi, Yunita Ayu; Winarno, Sri; Udayanti, Erika Devi; Alzami, Farrikh
Jurnal Masyarakat Informatika Vol 13, No 2 (2022): JURNAL MASYARAKAT INFORMATIKA
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.13.2.47983

Abstract

Masyarakat mampu mengkonsumsi tiap informasi yang tersebar di internet dengan cepat dan terkadang informasi yang beredar tidak selalu memberikan kebenaran yang sesuai dengan kenyataannya (hoax). Demi mendapatkan keuntungan dan mencapai tujuan pribadi, hoax seringkali sengaja dibuat dan dibagikan. Informasi yang didapatkan dari hoax tentunya dapat mempengaruhi masyarakat karena menimbulkan keraguan dan kebingungan terhadap informasi yang diterima Oleh karena itu, penelitian ini membahas tentang bagaimana mengklasifikasikan berita hoax berbahasa Indonesia mengenai isu kesehatan menggunakan TF-IDF serta algoritma Naïve Bayes Classifier dan Support Vector Machine dengan 4 model yang berbeda sehingga mampu memprediksi sebuah berita hoax atau valid. Pada penelitian ini dataset yang dikumpulkan sebanyak 287 diantaranya 200 valid dan 87 hoax. Hasil evaluasi model penelitian ini dengan menggunakan 4 model berbeda pada masing-masing algoritma, diperoleh nilai classification report terbesar untuk algoritma NBC pada model Complement Naïve Bayes dengan hasil precision 95.4%, recall 95.4%, f1-score 95.4% dan accuracy 93.1%. Sedangkan nilai classification report terbesar untuk algoritma SVM pada kernel Sigmoid dengan hasil precision 95.6%, recall 100%, f1-score 97.7% dan accuracy 96.5%. Sehingga dapat disimpulkan bahwa hasil performa rata-rata dari algoritma SVM memiliki kinerja yang lebih baik jika dibandingkan dengan algoritma NBC dalam melakukan klasifikasi berita hoax mengenai isu kesehatan.