Hasil Pencarian  ::  Simpan CSV :: Kembali

"Pandemi COVID-19 (coronavirus disease 2019) membuat para peneliti di seluruh dunia bekerja untuk memahaminya dengan menerapkan pendekatan machine learning. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) merupakan penyebab dari COVID-19. Penelitian ini membahas klasifikaasi sekuens protein SARS-CoV-2 menggunakan metode LightGBM dan Elastic Net. Metode LightGBM merupakan metode gradient boosting yang cepat dan memiliki high-performance berbasis decision tree untuk melakukan prediksi. Total data sekuens protein yang digunakan adalah 2000 data yang diambil dari situs Uniprot. Uniprot merupakan salah satu situs yang digunakan terkait bioinformatika atau sumber daya sekuens protein dan informasi fungsional yang memiliki kualitas tinggi, komprehensif dan dapat diakses secara bebas. Data tersebut memiliki perincian yaitu 1000 data sekuens protein SARS-CoV-2 dan 1000 data sekuens protein bukan SARS-CoV-2. Python package Discere digunakan untuk mengekstraksi 27 fitur sekuens protein. Selanjutnya, Elastic Net digunakan untuk memilih fitur-fitur yang optimal dan terpilih sebanyak 10 fitur. Terakhir, LightGBM digunakan sebagai metode klasifikasi sekuens protein SARS-CoV-2. Hasil evaluasi performa LightGBM diukur dari akurasi, sensitivitas, dan spesifisitas. Nilai rata-rata akurasi diperoleh 98,87%, nilai rata-rata sensitivitas diperoleh 99,02%, dan nilai rata-rata spesifisitas diperoleh 98,82%

---

The COVID-19 (coronavirus disease 2019) pandemic has researchers around the world working to understand it by applying a machine-learning approach. Secere acute respiratory syndrome coronavirus 2 (SARS-Cov-2) is the cause of COVID-19. This research discusses the classification of SARS-Cov-2 protein sequences using the LightGBM and Elastic Net methods. The LightGBM method is a gradient-boosting method that fast and has a high-performance decision tree based for making predictions. The total protein sequence data used is 2000 data taken from UniProt site. UniProt is one of the sites used for bioinformatics or protein sequence resources and functional information which is of high quality, comprehensive and freely accesible. The data has details, namely 1000 protein sequence data for SARS-CoV-2 and 1000 protein sequnce data for non-SARS-CoV-2. Python package Dsiscere is used to extraxt 27 protein sequence features. Futhermore, Elastic Net is used to select optimal features and 10 features are selected. While LightGBM is used as a classification method for SARS-Cov-2 protein sequences. The results of the LightGBM performance evaluation are measured by accuracy, sensitivity, and specificity. The average value for accuracy was 98,87%, the average value for sensitivity was 99,02%, and average value for specificity was 98,82%."

"SARS-COV-2 merupakan jenis virus yang menyebabkan pandemi COVID-19. Pandemi COVID-19 pertama kali terdeteksi di Wuhan, Cina. Berdasarkan data World Health Organization (WHO), jumlah orang yang telah terpapar COVID-19 adalah 123.216.178 orang dan 2.714.517 orang meninggal akibat COVID-19 berdasarkan data www.who.int pada tanggal 23 Maret 2021. Pada skripsi ini, dilakukan klasifikasi untuk SARS-COV-2 dengan menggunakan sekuens protein dari SARS-COV-2. Sekuens protein SARS-COV- 2 di ekstraksi fitur dengan menggunakan package discere dari Python. Package discere akan menghasilkan 27 fitur, dimana fitur-fitur diseleksi dengan menggunakan metode LASSO (Least Absolute Shrinkage and Selection Operator). Setelah dilakukan seleksi fitur, dilakukan klasifikasi dengan menggunakan dua metode, yaitu metode Absolute Correlation Weighted Naïve Bayes dan metode Naïve Bayes. Rata-rata akurasi, sensitifitas, dan spesifisitas tertinggi untuk metode Absolute Correlation Weighted Naïve Bayes berturut-turut adalah 81,85%, 74,81%, dan 89,19%, sedangkan rata-rata akurasi, sensitifitas, dan spesifisitas tertinggi untuk metode Naïve Bayes berturut-turut adalah 81,44%, 74,58%, dan 88,24%. Terlihat bahwa metode Absolute Correlation Weighted Naïve Bayes mempunyai rata-rata akurasi, sensitifitas, dan spesifisitas yang lebih tinggi dibandingkan dengan metode Naïve Bayes.

---

SARS-COV-2 is the type of virus that causes the COVID-19 pandemic. The COVID-19 pandemic was first detected in Wuhan, China. Based on data from the World Health Organization (WHO), the number of people who have been exposed to COVID-19 is 123,216,178 people and 2,714,517 people died from COVID-19 based on data from www.who.int on March 23, 2021. In this paper, the SARS-COV-2 classification is done by using the protein sequence of SARS-COV-2. The SARS-COV-2 protein sequence will be feature extraction using the discere package from Python. The discere package will produce 27 features, where the features are selected using the LASSO (Least Absolute Shrinkage and Selection Operator) method. After feature selection, classification is carried out using two methods, namely the Absolute Correlation Weighted Naïve Bayes method and the Naïve Bayes method. The highest average accuracy, sensitivity, and specificity for the Absolute Correlation Weighted Naïve Bayes method are 81.85%, 74.81%, and 89.19%, respectively, whereas the highest average accuracy, sensitivity, and specificity for the Naïve Bayes method are 81.44%, 74.58%, and 88.24%, respectively. It can be seen that the Absolute Correlation Weighted Naïve Bayes method has a higher average accuracy, sensitivity, and specificity than the Naïve Bayes method."

"The book presents homogeneous solutions in static and dynamical problems of anisotropic theory of elasticity, which are constructed for a hollow cylinder. It also offers an asymptotic process for finding frequencies of natural vibrations of a hollow cylinder, and establishes a qualitative study of several applied theories of the boundaries of applicability.Further the authors develop a general theory for a transversally isotropic spherical shell, which includes methods for constructing inhomogeneous and homogeneous solutions that allow the characteristic features of the stress-strain state of an anisotropic spherical shell to be revealed. Lastly, the book introduces an asymptotic method for integrating the equations of anisotropic theory of elasticity in variable thickness plates and shells."

"Coronavirus (CoV) adalah keluarga virus penyebab penyakit sistem pernapasan ringan hingga berat pada berbagai spesies hewan termasuk manusia. Salah satu spesies Coronavirus yang muncul pada akhir tahun 2019 yaitu SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) dan menimbulkan penyakit baru bernama Covid-19 (Coronavirus disease-2019) kemudian berstatus pandemi. Penyebaran Covid-19 yang cepat dan dengan tingkat kematian yang tinggi terus terjadi di berbagai negara. Oleh karena itu, deteksi dini patogen perlu dilakukan secara cepat dengan menggunakan data sekuens protein Coronavirus. Sekuens protein merupakan data struktur primer dari suatu protein yang memiliki 27 fitur berdasarkan discere. Dalam penerapannya, tidak semua fitur relevan dengan data yang digunakan sehingga perlu seleksi fitur untuk menghindari dimensi data yang tinggi dan tidak optimal. Seleksi fitur algoritma genetika memberikan fitur-fitur optimal pada data dan metode K-Nearest Neighbor (KNN) melakukan klasifikasi data sekuens protein Coronavirus dengan fitur hasil seleksi fitur algoritma genetika. Seleksi fitur algoritma genetika menghasilkan 11 fitur optimal yang meningkatkan performa running time metode klasifikasi KNN menjadi 0,0541 detik. Fitur optimal diperoleh dari karakteristik AA-count , secondary structure fraction , isoelectric point dan instability index. Hasil terbaik performa akurasi, spesifisitas beserta sensitifitas secara berurutan yaitu 96,68%, 98,7% dan 94,4% yang diperoleh pada nilai parameter K=3.

---

Coronaviruses (CoV) are a family of viruses that cause mild to severe respiratory system diseases in various animal species including humans. One of the Coronavirus species that emerged at the end of 2019 was SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) and caused a new disease called Covid-19 (Coronavirus disease-2019) then had a pandemic status. The rapid spread of Covid-19 and with a high death rate continues to occur in most of countries. Therefore, early detection of pathogens needs to be done quickly using Coronavirus protein sequence data. Protein sequences are primary structural data of a protein that has 27 features but not all of the existing features are relevant to the data used, so feature selection is necessary to avoid high and suboptimal data dimensions. The genetic algorithm feature selection provides optimal features to the data and the K-Nearest Neighbor (KNN) method performs the classification of Coronavirus protein sequences data with features resulting from the genetic algorithm feature selection. The genetic algorithm feature selection produces 11 optimal features that improve the running time performance of the KNN classification method. The average result of running time is 0.0541 second. The best results were accuracy performance, specificity and sensitivity are 96.68%, 98.7% and 94.4% respectively which were obtained at the parameter value K=3."

"Coronavirus yaitu kelompok virus yang menginfeksi sistem pernapasan yang dapat menyebabkan infeksi pernapasan ringan maupun berat. Salah satu virus yang termasuk ke dalam coronavirus adalah SARS-CoV-2. Penyakit yang disebabkan oleh virus SARS-CoV-2 disebut COVID-19. COVID-19 pertama kali terdeteksi pada tahun 2019 di Wuhan, China. Penyebaran COVID-19 sangat cepat dengan tingkat kematian yang tinggi terus terjadi di berbagai negara sehingga penyakit ini berstatus pandemi. Skripsi ini menyelesaikan masalah klasifikasi virus SARS-CoV-2 dengan menggunakan data sekuens protein coronavirus. Seleksi fitur pada data sekuens protein coronavirus menggunakan metode seleksi fitur Random Forest-Recurisive Feature Elimination (RF-RFE). Setelah dilakukan seleksi fitur, dilakukan klasifikasi menggunakan pendekatan machine learning dengan metode Support Vector Machine (SVM) dan Particle Swarm Optimization-Support Vector Machine (PSO-SVM). Hasil terbaik performa rata-rata akurasi, spesifisitas, dan sensitivitas untuk metode SVM berturut-turut adalah 93,43%, 98,06%, dan 88,84% pada data pelatihan sebesar 80%. Untuk metode PSO-SVM, hasil terbaik rata-rata akurasi dan spesifisitas adalah 98,48% dan 98,57% pada data pelatihan sebesar 80%, sedangkan hasil terbaik rata-rata sensitivitas adalah 98,96% pada data pelatihan sebesar 90%. Oleh karena itu, pada penelitian ini dapat disimpulkan bahwa metode PSO-SVM menghasilkan performa yang lebih baik dibandingkan dengan metode SVM.

---

Coronaviruses are a group of viruses that infect the respiratory system that can cause mild or severe respiratory infections. One of the viruses that belongs to the coronavirus is SARS-CoV-2. The disease caused by the SARS-CoV-2 virus is called COVID-19. COVID-19 was first detected in 2019 in Wuhan, China. The spread of COVID-19 is very fast with a high mortality rate that continues to occur in various countries so that this disease has a pandemic status. This thesis solves the problem of classifying the SARS-CoV-2 virus using coronavirus protein sequence data. Feature selection on coronavirus protein sequence data used the Random Forest-Recursive Feature Elimination (RF-RFE) feature selection method. After feature selection, classification is carried out using a machine learning approach with the Support Vector Machine (SVM) and Particle Swarm Optimization-Support Vector Machine (PSO-SVM) methods. The best results of the average performance of accuracy, specificity, and sensitivity for the SVM method are 93.43%, 98.06%, and 88.84%, respectively, for training data of 80%. For the PSO-SVM method, the best results on average accuracy and specificity are 98.48% and 98.57% on training data of 80%, while the best results on average sensitivity are 98.96% on training data of 90%. Therefore, in this study it can be concluded that the PSO-SVM method produces better performance than the SVM method."

"ABSTRAKSkripsi ini akan membahas dua metode yang digunakan untuk mengevaluasi gaya dalam lintang dari berbagai jenis elemen pelat lentur kuadrilateral dan triangular tipe diskrit. Metode pertama menggunakan persamaan konstitutif sedangkan metode kedua menggunakan persamaan keseimbangan. Metode elemen hingga digunakan untuk mengevaluasi gaya dalam lintang. Analisis dilakukan dengan menggunakan seperempat pelat lingkaran dengan berbagai ketebalan sedangkan kondisi batas yang digunakan adalah jepit dan sendi. Elemen pelat kuadrilateral yang akan dibahas adalah DSQ, MITC4, dan DKMQ sedangkan elemen pelat triangular yang akan dibahas antara lain , DST-BL, DST-BK, DKMT. Uji numerik dilakukan dengan menggunakan FEAP 8.3, MATLAB R2015b dan Mathematica 10. Uji numerik menunjukkan bahwa elemen MITC4 menghasilkan gaya dalam lintang lebih akurat jika menggunakan persamaan konstitutif dibandingkan persamaan keseimbangan sedangkan elemen DKMQ dan DSQ menunjukkan hasil gaya dalam lintang yang lebih akurat jika menggunakan persamaan keseimbangan. Untuk elemen triangular, semua elemen menunjukkan hasil gaya dalam lintang yang lebih akurat jika menggunakan persamaan keseimbangan dibandingkan persamaan konstitutif.

---

ABSTRACTThis thesis will discuss two methods to evaluate shear forces of various types of discrete quadrilateral dan triangular plate bending elements. The first method uses constitutive equations while the latter uses plate equilibrium equation. Finite element method is used to evaluate the shear forces. Analysis is done using a quarter symmetric circular plate with various thickness while boundary conditions are considered clamped and soft simply supported. Quadrilateral plate elements that are discussed is DSQ, MITC4 and DKMQ while triangular plate elements that are discussed is , DST BL, DST BK and DKMT. Numerical methods are done using FEAP 8.3, MATLAB R2015b dan Mathematica 10. Numerical analysis show that MITC4 element provide accurate shear results when using constitutive equation compared to equilibrium equation while DKMQ and DSQ element provide better shear results when using equilibrium equation. For triangular elements, all elements provide better shear forces results when using equilibrium equation compared to using constitutive equation. "

"This book presents simplified analytical methodologies for static and dynamic problems concerning various elastic thin plates in the bending state and the potential effects of dead loads on static and dynamic behaviors. The plates considered vary in terms of the plane (e.g. rectangular or circular plane), stiffness of bending, transverse shear and mass. The representative examples include void slabs, plates stiffened with beams, stepped thickness plates, cellular plates and floating plates, in addition to normal plates. The closed-form approximate solutions are presented in connection with a groundbreaking methodology that can easily accommodate discontinuous variations in stiffness and mass with continuous function as for a distribution. The closed-form solutions can be used to determine the size of structural members in the preliminary design stages, and to predict potential problems with building slabs intended for human beings practical use."

"

Penelitian ini bertujuan untuk melakukan pengelompokan varian virus SARS-CoV-2 melalui proses clustering menggunakan metode unsupervised learning. Data yang digunakan adalah sekuens protein SARS-CoV-2 yang diekstraksi fiturnya menggunakan paket Discere dalam bahasa pemrograman Python. Sebanyak 27 fitur dihasilkan dan diseleksi dengan metode seleksi fitur Least Absolute Shrinkage and Selection Operator (LASSO). Metode Elbow digunakan untuk menentukan jumlah cluster yang optimal. Dalam penelitian ini, digunakan metode clustering K-Means dan Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH). Evaluasi hasil clustering dilakukan menggunakan metrik evaluasi Silhouette Score dan Davies-Bouldin Index, serta memperhatikan waktu runtime untuk setiap simulasi. Hasil evaluasi kemudian dibandingkan untuk melihat perbedaan performa antara kedua metode clustering yang digunakan, serta pengaruh seleksi fitur terhadap performa clustering. Hasil terbaik diperoleh pada simulasi dengan metode clustering BIRCH + LASSO, dengan nilai Silhouette Score 0,74186 untuk jumlah cluster k=4 dan 0,73207 untuk k=5. Nilai Davies-Bouldin Index terbaik juga diperoleh pada simulasi tersebut, yaitu 0,42697 untuk k=4 dan 0,37949 untuk k=5. Waktu runtime terbaik tercatat pada simulasi dengan metode K-Means + LASSO, yaitu 0,21551 detik untuk k=4 dan 0,17539 detik untuk k=5. Dapat disimpulkan bahwa metode BIRCH menghasilkan cluster yang lebih baik berdasarkan metrik evaluasi, namun K-Means memberikan proses clustering yang lebih cepat. Seleksi fitur dengan metode LASSO juga membantu meningkatkan performa clustering.

---

This study aims to perform clustering of SARS-CoV-2 virus variants using unsupervised learning methods. The data used consists of SARS-CoV-2 protein sequences whose features are extracted using the Discere package in the Python programming language. A total of 27 features are generated and selected using the Least Absolute Shrinkage and Selection Operator (LASSO) feature selection method. The Elbow method is employed to determine the optimal number of clusters for the clustering process. The clustering methods used in this research are K-Means clustering and Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH). The clustering results are evaluated using the Silhouette Score and Davies-Bouldin Index metrics, while also considering the runtime for each simulation. The evaluation results are then compared to examine the performance differences between the two clustering methods and the impact of feature selection on clustering performance. The best Silhouette Score is obtained in the simulation using the BIRCH + LASSO clustering method, with a value of 0.74186 for k=4 and 0.73207 for k=5. The best Davies-Bouldin Index is also achieved in the same simulation, with values of 0.42697 for k=4 and 0.37949 for k=5. The fastest runtime is recorded in the simulation using the K-Means + LASSO method, with a time of 0.21551 seconds for k=4 and 0.17539 seconds for k=5. In conclusion, the BIRCH method yields better clustering results based on the evaluation metrics, while K-Means provides faster clustering processes. The LASSO feature selection method also aids in improving clustering performance.

"