Model Prediksi Cancer Menggunakan Autoencoder

Fauzi, Muhammad Ridho; Mia, Mendy Tutu Aries; Yahya, Ari Kusuma

doi:10.32832/pkm-p.v3i1.375

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Autoencoder merupakan sebuah metode yang memiliki dua bagian utama yaitu Encoder dan Decoder, Autoencoder memiliki jumlah masukan dan keluaran yang sama dan selalu berbentuk simetris atau jam pasir. Selain itu juga memiliki layer code, Fitra Septia & Hilman Ferdinandus, Aoutoencoder untuk Sistem Prediksi … 237 dan jumlah neuron pada layer code merupakan jumlah dimensi yang mengurangi dimensi yang terdapat pada data (Fauzi et al, 2019) (Kristian et al, 2018). Kelebihan dari metode ini adalah dapat melakukan hierarchical feature learning dari data yang digunakan , sehingga dapat menciptakan representasi bertingkat dimana representasi tersebut semakin abstrak dari tingkatan sebelumnya sehingga diharapkan menghasilkan representasi yang baik (Prodi et al, 2017).…”

Section: Pendahuluanunclassified

Autoencoder untuk Sistem Prediksi Berat Lahir Bayi

Nugraha

Pardede²

2022

JTIIK

View full text Add to dashboard Cite

Salah satu ukuran terpenting saat awal persalinan adalah keakuratan prediksi berat lahir. Dengan menggunakan metode prediksi yang tepat, perkiraan ekstrim berat lahir bayi dapat dideteksi lebih atau kurang sehingga beberapa tindakan pencegahan dapat dilakukan sebelum persalinan. Di sisi lain, untuk meningkatkan akurasi suatu proses pembelajaran, dibutuhkan suatu prediksi yang akurat untuk masalah yang dihadapi atau dengan menggunakan gabungan beberapa metode. Penelitian bertujuan untuk prediksi berat lahir bayi menggunakan metode Deep Learning autoencoder untuk memprediksi berat lahir bayi. Salah satu tantangan dalam pengembangan sistem prediksi berat lahir bayi adalah datanya yang berdimensi tinggi. Teknik konvensional untuk feature reduction seperti principal component analysis (PCA), mengasumsikan orthogonality atau independensi antar komponen prinsipal nya. Dengan autoencoder, asumsi tersebut tidak ada. Sehingga autoencoder dapat memodelkan korelasi antar fitur. Dengan melakukan variasi parameter pada autoencoder, performa terbaik diperoleh adalah MSE 0.002, MAE 0.029, R2 0.991 dengan autoencoder dengan 4 lapisan hidden layer encoder dan decoder. Ini lebih baik dibandingkan PCA. AbstractOne of the most important measurements at the onset of labor is the accuracy of the prediction of birth weight. By using precise prediction methods extreme estimates of baby birth weight can be detected more or less so that some precautions can be taken before delivery. On the other hand, to improve the accuracy of a learning process, an accurate prediction is needed for the problem at hand or by using a combination of several methods. This study aims to predict baby birth weight using the Deep Learning autoencoder method to predict baby birth weight. One of the challenges in developing a predictive system for infant birth weight is the high dimensional data. Conventional techniques for feature reduction, such as principal component analysis (PCA), assume orthogonality or independence between the principal components. With an autoencoder, that assumption doesn't exist. So that the autoencoder can model the correlation between features. By varying the parameters of the autoencoder, the best performance is MSE 0.002, MAE 0.029, R2 0.991 with an autoencoder with 4 hidden layer encoder and decoder layers. This is better than PCA.

show abstract

Section: Pendahuluanunclassified

Autoencoder untuk Sistem Prediksi Berat Lahir Bayi

Nugraha

Pardede²

2022

JTIIK

View full text Add to dashboard Cite

show abstract

“…Qualunque ordine introdotto nel pattern di forze contribuisce ad uno stato di equilibrio dinamico. 113 La prima esposizione del progetto metabolista fuori dal Giappone avvenne ad Otterloo, in occasione del CIAM X: in questa occasione K. Tange presentò i suoi progetti e quelli di K. Kikutake, tra cui la Città del Mare, un progetto che condensava progetti anteriori quali la Città Marina e la Città delle Torri, e che terminò nel 1962 con il progetto della Città Oceanica. Oltre a mettere in scena progetti metabolisti, Tange sottolineò quelli che erano i punti chiave del Metabolismo: si prese coscienza che la città, con tempi diversi, metabolizza gli eventi, e che al suo interno ci sono parti più resistenti (permanenti) e parti che hanno un carattere più effimero, transitorio.…”

Section: Metabolismounclassified

Per una scienza architettonica del pattern?

Zappulla

View full text Add to dashboard Cite

The basic premise of this work is to consider architecture as the result of the interrelationship between its constituent parts: aesthetic, tectonics, social, environmental , cultural, and organizational. When the project is focused only on one or a few of these levels, this is when hollow formalisms are generated. The main aim here is to demonstrate that patterns are able to facilitate the interaction and integration ofthese constituents. The rise of computation in architecture has had the effect of diluting the natural thought process of the architect. This paper therefore, helps to fill that theoretical void in parametric design. Hence, new tools are needed to analyse and understand architectural phenomena. For this to happen, the relationship between mathematical models and architecture needs to be cemented, and from here on after, pattern needs to be seen as an invaluable component of architecture. A methodology based on my belief that Complexity Theory could be the basis for interpreting architecture and pattern as structure, in order to transform the abstract into reality.

show abstract

Model Prediksi Cancer Menggunakan Autoencoder

Cited by 2 publications

References 2 publications

Autoencoder untuk Sistem Prediksi Berat Lahir Bayi

Autoencoder untuk Sistem Prediksi Berat Lahir Bayi

Per una scienza architettonica del pattern?

Contact Info

Product

Resources

About