Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
ABSTRAK
In this paper we show a simple and effective method for regularizing the Coulomb potential for numerical calculations of quantum mechanical problems, such as, for example, the solution of the Schrodinger equation, the expansion of charge density and others. The introduction explains why the regularization of the Coulomb potential is important. In the second part, the regularization method itself as well as its advantages and disadvantages will be described in detail. The third part demonstrates some numerical calculations for the Sulfur plus Hydrogen system using the proposed method. In the final part, the obtained results are summed up.

Abstrak :
Size effect on structural strength is normally understood as the effect of the characteristic structure size on the nominal strength of the structure when geometrically similar structures are compared. Fracture test are usually conducted on relatively small specimen and them this information is extrapolated to large structures. The question is that are we able to reproduce the size effect in the modern numerical techniques. Numerical calculations by computational code based on finite element have been done. The results show that in order to produce a size effect, it is necessary to use a regularization method.

Abstrak :
Size effect on structural strength is normally understood as the effect of the characteristic structure size on the nominal strength of the structure when geometrically similar structures are compared. Fracture test are usually conducted on relatively small specimen and them this information is extrapolated to large structures. The question is that are we able to reproduce the size effect in the modern numerical techniques. Numerical calculations by computational code based on finite element have been done. The results show that in order to produce a size effect, it is necessary to use a regularization method.

Abstrak :
Skripsi ini membahas mengenai pengembangan Sistem Penilaian Esai Otomatis (SIMPLE-O) yang dirancang dengan menerapkan Regularization pada model MLP(Multilayer Perceptron) untuk penilaian esai Bahasa Jepang. Sistem dirancang dengan menggunakan bahasa pemrograman Python. Penilaian otomatis oleh sistem dilakukan dengan cara membandingkan jawaban 43 mahasiswa dan kunci jawaban dari dosen yang telah diproses sebelumnya sedemikian rupa hingga berbentuk token. Jawaban mahasiswa dan dosen akan diproses menggunakan model MLP sehingga menghasilkan vector jawaban yang akhirnya akan dibandingkan menggunakan Manhattan Distance. Dari variasi model pada beberapa skenario yang diuji, model yang memiliki performa terbaik dari segi akurasi dan kekonsistenan tingkat akurasi terjadi pada model MLP yang menggunakan L1 Regularization dengan learning rate optimizer sebesar 0,00001 dan lambda 0,001. Model mendapatkan rata-rata nilai perbedaan antara nilai sistem dengan nilai asli sebesar 22,40% dan standar deviasi 11,54. ......This thesis discusses the development of an Automated Essay Scoring System (SIMPLE-O) designed by applying Regularization to the MLP (Multilayer Perceptron) model for Japanese Language essay scoring. System is developed using the Python programming language. Automatic assessment by the system is carried out by comparing the answers of 43 students and the answer keys from lecturers who have been processed previously in such a way that they are in the form of tokens. Student and lecturer answers will be processed using the MLP model, resulting in an answer vector that will eventually be compared using Manhattan Distance. From the model variations on some of the scenarios tested, model that has the best performance in terms of accuracy and consistency occurs in MLP models that use L1 Regularization with a optimizer learning rate of 0.00001 and lambda of 0.001. The model obtains an average value of the difference between the system value and the original value of 22.40% and a standard deviation of 11.54.

Abstrak :
Asuransi adalah layanan yang disediakan oleh perusahaan asuransi untuk memastikan risiko kerugian finansial bagi seseorang atau kelompok yang membayar premi berdasarkan perjanjian. Terdapat berbagai macam produk asuransi, di antaranya adalah asuransi perjalanan. Asuransi perjalanan adalah produk asuransi dalam mengalihkan risiko kerugian finansial akibat kecelakaan dalam perjalanan. Perusahaan asuransi harus dapat melakukan analisis yang tepat untuk memprediksi apakah pembayar premi akan mengajukan klaim atau tidak di masa depan, untuk meminimalkan kerugian yang diderita perusahaan. Dari sudut pandang machine learning, masalah prediksi klaim adalah masalah klasifikasi. Deep Neural Networks (DNN) adalah salah satu metode machine learning terbaru untuk menyelesaikan masalah prediksi klaim. Namun, DNN tidak memberikan akurasi yang lebih baik daripada Neural Network (NN) yang merupakan model dasarnya. Dalam tulisan ini, Regularization Learning Netowrk (RLN) yang merupakan pengembangan dari DNN dengan teknik regularisasi RLNs dianalisis untuk prediksi klaim dalam asuransi perjalanan. Simulasi menunjukkan bahwa RLN meningkatkan kinerja DNN dan memberikan akurasi yang lebih baik daripada DNN tanpa regularisasi RLNs dan NN standar. ......Insurance is a service provided by an insurance company to ensure the risk of financial loss for a person or group that pays a premium based on the agreement. There are various kinds of insurance products, including travel insurance. Travel insurance is insurance products in transferring the risk of financial loss due to accidents in transit. The insurance company must be able to conduct an appropriate analysis to predict whether the premium payer will file a claim or not in the future, to minimize losses suffered by the company. From a machine learning perspective, the problem of claim prediction is a classification problem. Deep neural networks (DNN) is one of the latest machine learning methods to solve claims prediction problems. However, DNN does not provide better accuracy than standard neural networks (NN). In this paper, the regularization learning network (RLN) which is an extension of DNN with a regularization layer analysed for prediction of claims in travel insurance. Our simulations show that RLN improves DNN performance and provides better accuracy than DNN and NN.

Abstrak :
ABSTRAK
We propose a new inverse problem formulation based on the hydrodynamics consideration of a gas/water fluid that results in planetary waves diagnostics. We analyze such a possibility beginning from a simplest version of geophysical hydrodynamics, written in the B plane model. The problem of diagnostics is solved approximately after expansion with respect to the transverse basis functions applying projecting to Rossby and Poincare waves in each transverse subspace that contains its superposition. The corresponding discrete version of the operators is built to be applied to the observation data.