22 research outputs found
Prediksi Data Time Series Saham Bank BRI Dengan Mesin Belajar LSTM (Long ShortTerm Memory)
Full text linkAbstract
This study aims to measure the accuracy in predicting time series data using the LSTM (Long Short-Term Memory) machine learning method, and determine the number of epochs needed to produce a small RMSE (Root Mean Square Error) value. The result of this research is a high level of variation in RMSE value to the number of epochs needed in the data processing. This variation is quite difficult to obtain the right epoch value. By doing an iteration of the LSTM process on the number of different epochs (visualized in the graph), then the number of epochs with a minimum RMSE value will be easier to obtain. From the research of BBRI\u27s stock data prediction, a good RMSE value was obtained (RMSE = 227.470333244533).
Keywords: long short-term memory, machine learning, epoch, root mean square error, mean square error.
Abstrak
Penelitian ini bertujuan untuk mengukur ketelitian dalam memprediksi data time series menggunakan metode mesin belajar LSTM (Long Short-Term Memory), serta menentukan banyaknya epoch yang diperlukan untuk menghasilkan nilai RMSE (Root Mean Square Error) yang kecil. Hasil dari penelitian ini adalah tingkat variasi yang tinggi nilai rmse terhdap jumlah epoch yang diperlukan dalam proses pengolahan data. Variasi ini cukup menyulitkan untuk memperoleh nilai epoch yang tepat. Dengan melakukan iterasi dari proses LSTM terhadap jumlah epoch yang berbeda (di visualisasikan dalam grafik), maka jumlah epoch dengan nilai RMSE minimal akan lebih mudah diperoleh. Dari penelitan prediksi data saham BBRI diperoleh nilai RMSE yang cukup baik yaitu 227,470333244533.
Kata kunci: long short-term memory, machine learning, epoch, root mean square error, mean square error
Diagnosa COVID-19 Chest X-Ray Dengan Convolution Neural Network Arsitektur Resnet-152
Full text linkThe availability of medical aids in adequate quantities is very much needed to assist the work of the medical staff in dealing with the very large number of Covid patients. Artificial Intelligence (AI) with the Deep Learning (DL) method, especially the Convolution Neural Network (CNN), is able to diagnose Chest X-ray images generated by the Computer Tomography Scanner (C.T. Scan) against certain diseases (Covid). Resnet Version-152 architecture was used in this study to train a dataset of 10.300 images, consisting of 4 classifications namely covid, normal, lung opacity with 3,000 images each and viral pneumonia 1,000 images. The results of the study with 50 epoch training obtained very good values for the accuracy of training and validation of 95.5% and 91.8%, respectively. The test with 10.300 image dataset obtained 98% accuracy testing, with the precision of each class being Covid (99%), Lung_Opacity (99%), Normal (98%) and Viral pneumonia (98%).
A Breakthrough in Viral Pneumonia Detection: Unveiling Insights with ResNet-152
Full text linkViral pneumonia is one of the most serious health issues. The key problem in providing early detection and rapid mitigation through the use of chest X-ray imaging has become the ability to identify accurately. The ResNet-152 convolutional neural network approach will be used in this study to predict viral pneumonia. The input dataset was obtained from Kaggle.com. The accuracy findings from this investigation obtained a substantial value, namely 0.99, indicating that the model used performed admirably. The model used can efficiently distinguish between the viral pneumonia dataset and other datasets. It is intended that the findings of this study will be used to inform early decisions in related medical sectors
Menggunakan Xception, Transfer Learning, dan Permutasi untuk Meningkatkan Klasifikasi Ketidaksempurnaan Permukaan Baja: Using Xception, Transfer Learning, and Permutation to Improve the Classification of Steel Surface Imperfections
No full textKualitas permukaan baja yang diproduksi sangat penting untuk meningkatkan daya saing dalam industri baja. Tingginya tingkat cacat pada permukaan baja merupakan masalah serius yang berdampak pada kualitas keluaran. Pengendalian yang masih dilakukan secara manual dan visual saat ini hanya dapat dilakukan oleh orang-orang dengan bakat dan keahlian tertentu. Pengamatan dengan metode konvensional ini memerlukan waktu yang lama, lamban, dan presisi yang rendah. Saat ini, perkembangan teknik pembelajaran mendalam memungkinkan deteksi cacat permukaan baja secara otomatis dengan tingkat akurasi yang tinggi. Arsitektur Xception digunakan dalam pekerjaan ini untuk menerapkan strategi pembelajaran mendalam. Teknik permutasi dan augmentasi digunakan untuk mengatasi ketidakseimbangan data. Model yang dikembangkan dapat membedakan empat jenis cacat pada permukaan baja. Koleksi 7.095 foto permukaan baja digunakan dalam prosedur pelatihan. Jika dibandingkan dengan tidak menggunakan transfer learning, hasil pengukuran kinerja proses pelatihan dengan menggunakan transfer learning (Imagenet) menunjukkan hasil yang lebih baik. Pelatihan pembelajaran transfer menghasilkan skor akurasi masing-masing sebesar 94,9% dan 97,7% untuk data pelatihan dan validasi. Sedangkan hasil penilaian nilai kerugian untuk data latih dan validasi masing-masing sebesar 19,4% dan 14,4%
OPTIMASI CONVOLUTION NEURAL NETWORK UNTUK DETEKSI COVID-19
Full text linkAbstrak: Optimasi Convolution Neural Network Untuk Deteksi Covid-19. Kondisi pandemi seperti sekarang ini diperlukan sebuah algoritma pembelajaran mesin untuk mendeteksi covid-19 secara otomatis berdasarkan pada gambar rontgen dada guna memudahkan dalam mambantu pengambil keputusan. Penelitian ini ingin membandingkan arsitektur CNN AlexNet dan MobileNetV2 untuk mendeteksi (a) covid-19, (b) lung opacity, (c) normal, (d) viral pneumonia. Data himpunan rontgen dada yang digunakan sejumlah 4000 yang berasal dari kaggle.com, 0.8 data dibagi untuk pelatihan sedangkan 0.2 nya digunakan untuk pengujian. Optimizer yang digunakan yaitu keras SGD momentum, dengan nilai learning rate 0.005 dan momentum 0.9, serta epoch 50. Ukuran gambar untuk input yaitu 224x224 serta ukuran batch 32. Hasil optimasi dari kedua algoritma tersebut yaitu, MobileNetV2 lebih baik untuk mendeteksi covid-19 dengan nilai akurasi presisi mencapai 99%. Penelitian selanjutnya dapat membandingkan algoritma CNN yang lainnya serta data himpunan yang lebih banyak.
Kata kunci: CNN; AlexNet; MobileNetV2; Covid-19
Abstract: Convolution Neural Network Optimization for Covid-19 Detection. In the current pandemic conditions, a machine learning algorithm is needed to detect COVID-19 automatically based on chest X-ray images to make it easier to assist decision makers. Aim study be disposed for compare the architecture of CNN AlexNet and MobileNetV2 to detect (a) covid-19, (b) lung opacity, (c) normal, (d) viral pneumonia. The data set of chest X-rays used are 4000 from kaggle.com, 0.8 of the data is shared for training while 0.2 is used for testing. The optimizer used is hard SGD momentum, with a value of leaning rate 0.005 and momentum 0.9, and epoch 50. The image size for the input is 224x224 and the batch size is 32. The optimization results from the two algorithms are, MobileNetV2 is better for detecting covid-19 with an accuracy value The precision reaches 99%. Future research can compare other CNN algorithms and larger data sets.
Keywords: CNN; AlexNet; MobileNetV2; Covid-1
A critical exposition of historicism and implicit activism in Elundini Lothukela
No full textBibliography: leaves 186-193.It is the gentle but sharp manner of refutation of negative labels that early Europeans, through negative and undermining othering, attached to the Nguni in South Africa, that was investigated and discovered in this novel, that the author of this thesis is putting under the spotlight here. This thesis seeks to demonstrate that this novel is one radiant example of typical combative, counter-hegemonic, and engage works in Xhosa literature, the kind of resistance and indictment literature where the message on national liberation lies embedded in its and groundwork; in it we see graphic reflections of the pre-colonial Nguni Indigenes in South Africa, their admirable and glorious which manifested itself in a virile political pattern, orderly social-religious systems, and structured industrial practices. We use these aspects to reinforce our exposition of this novel as a work of art that refutes all negative labels that were attached to the Nguni Indigenes
PREDICTING SOLAR POWER GENERATION: A MACHINE LEARNING APPROACH FOR GRID STABILITY AND EFFICIENCY
Full text linkIn countries with high levels of insolation, the demand for renewable energy sources has driven the rapid emergence and growth of solar power plants. Maintaining grid stability and efficient power management in response to weather variations that affect solar radiation intensity and battery consumption limits remains a major challenge. This study aims to develop a machine learning-based prediction model to estimate the electricity generated by solar power plants using weather data. Four algorithms are utilized: Linear Regression, Random Forest Regressor, Decision Tree Regressor, and Gradient Boosting Regressor. The results show that the Random Forest algorithm produces the best model, with MAE and RMSE values of 0.1114281 and 0.3187232, respectively. This research contributes to the literature, particularly on the relatively unexplored topic of using multiple machine learning models to predict energy output from photovoltaic systems. The findings have the potential to inform more efficient energy policies and improve energy integration technologies for grid-connected solar power systems
Exloratory Data Analysis Untuk Data Belanja Pelanggan dan Pendapatan Bisnis
Full text linkA more quantifiable perspective is assuming the role of mechanistic management in an effort to enhance business based on its capacity to transform data into knowledge and insight. The industry has not completely supported its business strategy also with driven data. Using a transaction dataset taken from one of the Kaggle.com challenges, this experiment attempts to determine consumer spending patterns and Retail Fashion business revenues (H&M Personalized Fashion Recommendations). The results of the experiment are the number of transactions based on customer age, the most sales product and one-time purchased item, and the type of product that generates the highest and smallest income. The approach employed is EDA using the Python language. In order for businesses to generate analytical findings that provide future perspectives and to help identify the gap by delivering analytical results in the form of suggestions that can be perpetuated, the findings of this experiment are intended to support the capabilities of simulation. The challenge in this experiment is the abundance of datasets, which necessitates a suitable operating environment.Pandangan manajemen mekanistik sedang digantikan oleh pandangan yang lebih terukur untuk mendorong bisnis berdasarkan kemampuannya guna mengubah data menjadi pengetahuan dan wawasan. Industri belum memanfaatkan data driven secara maksimal untuk menunjang strategi bisnis mereka. Eksperimen ini bertujuan untuk menganalisa data belanja pelanggan dan pendapatan bisnis retail fashion menggunakan dataset transaksi yang diperoleh dari salah satu kompetisi di Kaggle.com (H&M Personalized Fashion Recommendations). Metode yang digunakan yaitu EDA menggunakan bahasa python, hasil dari eksperimen ini yaitu memperlihatkan kuantitas transaksi berdasarkan umur pelanggan, produk dengan penjualan terbanyak dan hanya sekali serta jenis produk yang memberikan pendapatan terbesar dan terkecil. Hasil eksperimen ini diharapkan dapat mendukung kemampuan simulasi, agar industri dapat mengembangkan hasil analitik yang memberikan pandangan ke depan, serta membantu menjembatani kesenjangan antara knowledge dan wisdom untuk memberikan hasil analitik yang bersifat saran yang berkelanjutan. Tantangan dalam eksperimen ini yaitu jumlah dataset yang besar, membutuhkan lingkungan operasi yang mumpuni
PREDICTING SOLAR POWER GENERATION: A MACHINE LEARNING APPROACH FOR GRID STABILITY AND EFFICIENCY
Full text linkIn countries with high levels of insolation, the demand for renewable energy sources has driven the rapid emergence and growth of solar power plants. Maintaining grid stability and efficient power management in response to weather variations that affect solar radiation intensity and battery consumption limits remains a major challenge. This study aims to develop a machine learning-based prediction model to estimate the electricity generated by solar power plants using weather data. Four algorithms are utilized: Linear Regression, Random Forest Regressor, Decision Tree Regressor, and Gradient Boosting Regressor. The results show that the Random Forest algorithm produces the best model, with MAE and RMSE values of 0.1114281 and 0.3187232, respectively. This research contributes to the literature, particularly on the relatively unexplored topic of using multiple machine learning models to predict energy output from photovoltaic systems. The findings have the potential to inform more efficient energy policies and improve energy integration technologies for grid-connected solar power systems
Mengatasi Ketimpangan Data Deep Neural Network dengan Pelipatan Fitur Data Klasifikasi Spektroskopi Darah
No full textPermasalahan utama dalam penelitian ini adalah ketimpangan data masukan menghasilkan dampak negatif yang signifikan terhadap hasil prediksi dari model Deep Neural Network (DNN). Kemampuan klasifikasi DNN sangat akurat hanya untuk dataset yang berimbang, namun DNN pada awalnya tidak di rancang untuk menangani ketimpangan data. Ketimpangan data merupakan hal yang sering dijumpai dalam dunia nyata, menjadikan ini sebagai tantangan besar dalam prediksi klasifikasi menggunakan model DNN. Penelitian ini berfokus untuk memprediksi tingkat kandungan kolesterol tinggi, kolesterol rendah dan hemoglobin, menggunakan data kasus di kompetisi Zindi Blood Spectroscopy Classification Challenge. Dengan melakukan analisa data, cleansing outlier, fine tunning, model neural network, jaringan pengelompokan data target dengan kategori sejenis, urutan pemrosesan, pemilihan nilai pelipatan (7 pelipatan) yang tepat terhadap data input train dan data test serta epoch 60, dapat meningkatkan hasil nilai score prediksi yang cukup tinggi sebesar 0.94594
