IRPI Publisher Journals (Institute of Research and Publication Indonesia)
Not a member yet
1012 research outputs found
Sort by
Implementation of Naïve Bayes Classifier for Classifying Alzheimer’s Disease Using the K-Means Clustering Data Sharing Technique
Get PDFAlzheimer's disease is a neurodegenerative disease that is very universal and characterized by memory loss and cognitive function decline which ultimately leads to dementia. In 2015, it is estimated that around million people worldwide will suffer from Alzheimer's disease or dementia. Globally, the number of Alzheimer's diseases will increase from 26.6 million in 2006 to 106.8 million cases in 2050. Due to the large number of people with Alzheimer's disease, it is necessary to classify symptoms that lead to indicators of Alzheimer's disease, so that data mining methods are used for data processing. Alzheimer's data taken from Kaggle amounted to 373 records, through the stages of data preprocessing, data sharing using the Hold-Out method and clustering with AK-Means algorithm. The data is processed using data mining techniques using NBC algorithms. Validation testing the accuracy value obtained the result that the NBC algorithm with K-Means Clustering data sharing has relatively better accuracy than the hold-Out method of 91.89%
Implementation of C4.5 and Support Vector Machine (SVM) Algorithm for Classification of Coronary Heart Disease
Get PDFCoronary Heart Disease (CHD) is a chronic disease that is not contagious and can cause heart attacks. This makes CHD one of the diseases that cause the highest mortality globally. CHD can be caused by the main factor, namely an unhealthy lifestyle, so that in an effort to identify and deal with CHD, many studies have been conducted, one of which is the use of information technology. With so many CHD patient data, data mining can be used using. classification methods include C4.5 algorithm and Support Vector Machine (NBC). The C4.5 algorithm is a decision tree-like algorithm that groups attribute values into classes so that it resembles a tree, while SVM is an algorithm that separates data with a hyperplane. This study aims to classify the CHD dataset by comparing the C4.5 and SVM algorithms. So that the best accuracy value for this data is produced, namely the SVM algorithm of 64.51% and followed by the C4.5 algorithm of 64.30%
Klasifikasi Keparahan Demensia Alzheimer Menggunakan Metode Convolutional Neural Network pada Citra MRI Otak: Classification of Alzheimer's Dementia Severity Using Convolutional Neural Network Method on MRI Image of Brain
No full textKlasifikasi Gambar adalah bidang yang telah menemukan jalan ke berbagai aspek kehidupan, seperti pencarian gambar, pengenalan wajah, dan riset pemasaran. Alzheimer, penyakit neurodegeneratif yang belum ada obatnya, umumnya terdeteksi menggunakan MRI dan gejala yang dilaporkan oleh si penderita. Namun, kesalahan diagnosis sering terjadi karena gejala usia tua dan gejala Alzheimer yang tumpang tindih, dan pemeriksaan jaringan otak untuk diagnosis yang jelas hanya dapat dilakukan setelah kematian. Dengan harapan untuk memperbaiki proses ini, maka dikembangkanlah model jaringan saraf tiruan untuk mengklasifikasikan tingkat keparahan demensia Alzheimer untuk membantu dokter meninjau ulang dan meningkatkan akurasi diagnosis. Untuk melakukan ini, kami menggunakan set gambar MRI dengan 4 kelas dan Convolutional Neural Networks (CNN) dari metode pembelajaran awal dan transfer. Metode yang kami temukan yang paling akurat memprediksi kelas Alzheimer dari pemindaian MRI adalah Convolution Neural Network
Komparasi Algoritma K-NN, Naive Bayes dan SVM untuk Prediksi Kelulusan Mahasiswa Tingkat Akhir: Comparison of K-NN, Naive Bayes and SVM Algorithms for Final-Year Student Graduation Prediction
No full textMahasiswa tingkat akhir adalah seorang pelajar yang sedang berjuang demi mendapat gelar sarjana dan memilih tujuan hidup dengan tugas yang baru seperti pekerjaan yang sesuai dengan minat dan bakatnya. Untuk mendapatkan tingkat kelulusan dengan baik dan tepat waktu. Mahasiswa sangat bergantung pada pengaruh dari faktor dalam dan luar kampus. Pemilihan dan penentuan data yang digunakan, diambil dari data publik. Dengan 379 orang mahasiswa tahap akhir sebagai responden. Pengujian ini membandingkan algoritma K-NN, NBC, dan SVM yang lebih baik menyelesaikan masalah terkait prediksi tingkat kelulusan mahasiswa pascasarjana. Berdasarkan perbandingan algoritma tersebut dengan teknik splitting data, didapatkan bahwa Algoritma K-NN (K-Nearest Neighbor) memiliki rata-rata lebih tinggi dibandingkan (NBC) Naïve Bayes Classifier dan SVM (Support Vector Machine) untuk prediksi kelulusan mahasiswa tingkat akhir dengan akurasi 87,8%, presisi 87,8%, dan recall 84%
Classification of Date Fruit Types Using CNN Algorithm Based on Type
Get PDFDate fruits are an important commodity in the agriculture and food industry. However, in the process of sales and distribution to ordinary people, there are often errors in identifying different types of date fruits. Therefore, this research aims to develop an automatic classification system to distinguish the types of date fruits based on their types using the Convolutional Neural Network (CNN) algorithm. The case study was conducted at Hamima Dates date shop. The data used are fruit images with 9 categories and a total of 1658 samples, which are divided into 1496 samples for training data and 162 samples for testing data. The test results show that the CNN algorithm has a high level of accuracy in classifying the type of date fruit, with an accuracy of 96%. In this study, feature analysis was also conducted to determine the contribution of each feature to the classification of date fruit types. The results of this study can be the basis for the development of a more sophisticated date fruit automatic classification system and can be applied to other types of fruit
Pengembangan Aplikasi Pemetaan Desa Rawan Sanitasi Berbasis Web Menggunakan Open StreatMap: Development of a Web-Based Sanitation-Prone Village Mapping Application Using Open StreatMap
No full textRendahnya kondisi sanitasi di Indonesia, terutama di desa-desa, yang dapat menyebabkan masalah kesehatan dan lingkungan. Akses informasi terkait masalah sanitasi masih sangat minim terutama di desa-desa. Diperlukan aplikasi yang mampu memberikan informasi pemetaan terhadap kondisi sanitasi. Penelitian ini bertujuan untuk mengembangkan aplikasi pemetaan desa rawan sanitasi dengan menggunakan teknologi leafletjs dan Open StreatMap untuk menyediakan informasi pemetaan wilayah rawan sanitasi. dengan mengintegrasikan data spasial dengan data kondisi sanitasi desa aplikasi ini dapat menampilkan pemetaan wilayah desa untuk memudahkan visualisasi desa rawan sanitasi. Hasil pengujian menggunakan metode blackbox testing menunjukkan hasil aplikasi dapat berjalan dengan baik sesuai dengan yang diharapkan
Analysis of The Influence of Brand Image, Digital Marketing and Product Knowledge on Customers Purchase Intention of Banking Products
Get PDFThe purpose of this study is to determine whether there is a simultaneous relationship between digital marketing, brand image, and product understanding on the decision to become a customer. In this study, the population consists of all Sharia bank customers. With a total of 100 respondents, this study used a non-probability sampling strategy. This study employs a quantitative methodology and a causal research design, gathering information with a questionnaire. The decision to become a customer was found to be significantly influenced in a good way by digital marketing, according to the research findings. This indicates that the decision to become a customer can be influenced by digital marketing. The more effectively digital marketing is implemented, the more it will persuade consumers to become clients. The decision to become a customer is positively and significantly influenced by brand image. This implies that the decision to become a customer may be influenced by brand image. Making the choice to become a customer will be simpler the more positively the brand is portrayed. The decision to become a customer is positively and significantly impacted by product knowledge. This implies that product expertise can affect a potential customer's choice to buy
The Role of E-Commerce Use, Capital Availability and Business Training on Performance of Small Medium Enterprise (SMEs) in Indonesia
Get PDFThis study aims to determine whether the simultaneous use of finance, business training, and e-commerce has a favorable and significant impact on microbusiness revenue. Multiple linear regression is being used in this quantitative research approach. The people who participate in microbusinesses and have received business training make up the population of this study. Purposive sampling, a non-probability sample technique, and a total of 100 respondents make up the approach employed in this study. The questions for this study were made available and directly completed by respondents using Google Forms. The Likert scale was employed by the author as a measurement in this study. The usage of e-commerce has a good and considerable impact on microbusiness income, according to the research findings. Microbusiness income is significantly and favorably impacted by capital. Microbusiness income is significantly and favorably affected by enterprise training. Microbusiness revenue benefits significantly and positively from the usage of e-commerce, financing, and business training all at once. 52% of microbusiness income is impacted by the usage of e-commerce, financing, and enterprise training. The other 48%, meanwhile, was affected by things unrelated to this study
Klasifikasi Skala Kerapatan dan Transparansi Tajuk Jenis Daun Jarum dengan VGG16: Classification of Density and Transparency Scales of Needle Leaf Types with VGG16
No full textArtikel ini membahas penggunaan deep learning, khususnya arsitektur Convolutional Neural Network (CNN) VGG16, untuk mengklasifikasikan tingkat kerapatan dan transparansi tajuk pada pohon jenis daun jarum. Penelitian ini mengumpulkan gambar dari empat jenis pohon daun jarum: araucaria heterophylla, pinus merkusii, cupressus retusa, dan shorea javanica, masing-masing dengan sepuluh tingkat kerapatan dan transparansi yang berbeda. Setiap jenis memiliki 1000 gambar yang telah di-label. Proses preprocessing melibatkan perubahan ukuran, dan augmentasi gambar. Data dibagi menjadi data training (70%), data validation (10%), dan data testing (20%). Model deep learning yang digunakan adalah VGG16 dengan hyperparameter yang telah ditentukan. Hasil pelatihan model menunjukkan bahwa VGG16 berhasil mengklasifikasikan pohon daun jarum dengan tingkat akurasi yang baik. Hasil akurasi mencapai 90.00% untuk pinus merkusii, 92.00% untuk araucaria heterophylla, 96.00% untuk cupressus retusa, dan bahkan 99.00% untuk shorea javanica. Hasil evaluasi juga mencakup precision, recall, dan F1-score untuk setiap kelas kerapatan dan transparansi. Kesalahan prediksi terutama terjadi pada kelas dengan tingkat kesamaan visual yang tinggi antar gambar. Penelitian ini membuktikan bahwa teknologi deep learning dapat digunakan untuk mengklasifikasikan tingkat kerapatan dan transparansi tajuk pada pohon daun jarum. Hasilnya dapat digunakan dalam pemantauan kesehatan hutan, membantu pemerintah dan organisasi terkait dalam pengelolaan hutan yang berkelanjutan
Optimization of Energy Consumption in 5G Networks Using Learning Algorithms in Reinforcement Learning
Get PDFThe 5G network is an evolution of the 4G LTE (Long Term Evolution) fast internet network that is widely adopted in smart phones or gadgets. 5G networks offer faster wireless internet for various purposes. This research is a literature review of several articles related to machine learning, specifically regarding energy consumption optimization with 5G networks and reinforcement learning algorithms.The results show that various techniques have evolved to overcome the complexity of large energy intake including integration with 5G networks and algorithms have been completed by many researchers. Related to electricity consumption, it was found that during 5G use cases, in a low site visitor load scenario and while reducing power intake takes precedence over QoS, power savings can be made by 80% with 50 ms latency, 75% with 20 ms and 10 ms latency, and 20% with 1 ms latency. If QoS is prioritized, then power savings reach a maximum of five percent with minimum impact in terms of latency. Moreover, with regards to power performance, it has been observed that DQN-assisted motion can offer improvements