scholarly journals Klasifikasi Sinyal Emg Pada Otot Tungkai Selama Berjalan Menggunakan Random Forest

2017 ◽  
Vol 1 (1) ◽  
pp. 51
Author(s):  
Darma Setiawan Putra ◽  
Adhi Dharma Wibawa ◽  
Mauridhi Hery Purnomo
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Random Forest ◽  
Gait Cycle ◽  
Cross Validation ◽  
Vastus Lateralis ◽  
Principal Component ◽  
Rectus Femoris ◽  
Component Analysis ◽  
Gastrocnemius Lateralis

Sinyal electromyography (EMG) merupakan suatu sinyal elektrik yang terdapat dalam lapisan otot selama gerakan aktif. Cara orang berjalan ditentukan oleh struktur otot dan tulang sehingga cara berjalan ini adalah unik dan dapat digunakan sebagai data biometrik. Pada penelitian ini, kami mengklasifikasi data EMG dari delapan jenis otot tungkai selama percobaan berjalan normal: Rectus Femoris, Vastus Lateralis, Vastus Medialis, Bicep Femoris, Semitendinosus, Gastrocnemius Lateralis, Gastrocnemius Medialis, dan Tibialis Anterior. Enam orang subyek diminta untuk berjalan di laboratorium GaitLab dengan 8 buah elektroda EMG ditempel pada otot mereka. Subyek diminta untuk berjalan sebanyak 1 gait cycle dengan 3 kali pengambilan data. Total dataset EMG untuk klasifikasi adalah sebanyak 18 buah. Metode graph feature extraction dan principal component analysis digunakan untuk ekstraksi fitur data EMG. Metode Random Forest digunakan untuk mengklasifikasi data EMG berdasarkan subyek. Metode pelatihan dan pengujian data EMG menggunakan cross validation (CV). Akurasi klasifikasi yang dihasilkan dengan menggunakan metode graph feature extraction adalah sebesar 88.88% dan metode principal component analysis adalah sebesar 72.22%. Hasil ini menunjukkan bahwa data EMG ketika berjalan dari 8 jenis otot tungkai dapat digunakan untuk identitas biometrik gaya berjalan (gait).

scholarly journals Differences in Simulated EMG Activities between a Non-Rotational Shot and an Ordinary Instep Kick Identified by Principal Component Analysis

Proceedings ◽  
2020 ◽  
Vol 49 (1) ◽  
pp. 154
Author(s):  
Tasuku Miyoshi ◽  
Yasuhisa Kamada ◽  
Yoshiyuki Kobayashi
Keyword(s):  
Principal Component Analysis ◽  
Vastus Lateralis ◽  
Gluteus Maximus ◽  
Principal Component ◽  
Rectus Femoris ◽  
Component Analysis ◽  
Vastus Intermedius ◽  
Longus Muscle ◽  
Instep Kick ◽  
Tensor Fasciae Latae

The aim of this study was to clarify the major differences in the electromyographic (EMG) activities in the hip joint required to achieve a non-rotational (NR) shot as compared with an instep kick from the spatiotemporal data. For this purpose, simulated EMG activities obtained from NR shots and instep kicks were analyzed using principal component analysis (PCA). The PCA was conducted using an input matrix constructed from the time-normalized average and the standard deviation of the EMG activities (101 data x (15 muscles; iliacus, gluteus maximus, rectus femoris, biceos femoris, vastus lateralis, vastus medialis, vastus intermedius, semimembranosus, semitendinosus, sartorius, tensor fasciae latae muscle, adductor magnus muscle, adductor longus muscle, gasctrocnemius, and tibialis anterior)). The PCA revealed that the 3rd, 4th and 8th principal component vectors (PCVs) of the 10 generated PCVs were related to achieving the NR shot (p < 0.05).

scholarly journals IPCARF: improving lncRNA-disease association prediction using incremental principal component analysis feature selection and a random forest classifier

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Rong Zhu ◽  
Yong Wang ◽  
Jin-Xing Liu ◽  
Ling-Yun Dai
Keyword(s):  
Principal Component Analysis ◽  
Random Forest ◽  
Cross Validation ◽  
Search Algorithm ◽  
Principal Component ◽  
Component Analysis ◽  
Biological Data ◽  
Learning Technology ◽  
Disease Associations ◽  
Fold Cross Validation

Abstract Background Identifying lncRNA-disease associations not only helps to better comprehend the underlying mechanisms of various human diseases at the lncRNA level but also speeds up the identification of potential biomarkers for disease diagnoses, treatments, prognoses, and drug response predictions. However, as the amount of archived biological data continues to grow, it has become increasingly difficult to detect potential human lncRNA-disease associations from these enormous biological datasets using traditional biological experimental methods. Consequently, developing new and effective computational methods to predict potential human lncRNA diseases is essential. Results Using a combination of incremental principal component analysis (IPCA) and random forest (RF) algorithms and by integrating multiple similarity matrices, we propose a new algorithm (IPCARF) based on integrated machine learning technology for predicting lncRNA-disease associations. First, we used two different models to compute a semantic similarity matrix of diseases from a directed acyclic graph of diseases. Second, a characteristic vector for each lncRNA-disease pair is obtained by integrating disease similarity, lncRNA similarity, and Gaussian nuclear similarity. Then, the best feature subspace is obtained by applying IPCA to decrease the dimension of the original feature set. Finally, we train an RF model to predict potential lncRNA-disease associations. The experimental results show that the IPCARF algorithm effectively improves the AUC metric when predicting potential lncRNA-disease associations. Before the parameter optimization procedure, the AUC value predicted by the IPCARF algorithm under 10-fold cross-validation reached 0.8529; after selecting the optimal parameters using the grid search algorithm, the predicted AUC of the IPCARF algorithm reached 0.8611. Conclusions We compared IPCARF with the existing LRLSLDA, LRLSLDA-LNCSIM, TPGLDA, NPCMF, and ncPred prediction methods, which have shown excellent performance in predicting lncRNA-disease associations. The compared results of 10-fold cross-validation procedures show that the predictions of the IPCARF method are better than those of the other compared methods.

scholarly journals Comparison of Geographical Traceability of Wild and Cultivated Macrohyporia Cocos With Different Data Fusion Approaches

2021 ◽  
Author(s):  
Qinqin Wang ◽  
Yuan-Zhong Wang ◽  
Yunmei Wang
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Random Forest ◽  
Data Fusion ◽  
Principal Component ◽  
Component Analysis ◽  
Level Data ◽  
Significant Difference ◽  
High Level ◽  
Geographical Traceability

Abstract Background Poria originated from the dried sclerotium of Macrohyporia cocos is an edible traditional Chinese medicine with high economic value. Due to the significant difference in quality between wild and cultivated M. cocos, the study aimed to trace the origin of the fungus from the perspectives of wild and cultivation. In addition, there were quite limited studies about data fusion, a potential strategy, employed and discussed in the geographical traceability of M. cocos. Therefore, we traced the origin of M. cocos from the perspectives of wild and cultivation using multiple data fusion approaches. Methods Supervised pattern recognition techniques like partial least squares discriminant analysis (PLS-DA) and random forest, were employed in this study using. Five types of data fusion involving low-, mid- and high-level data fusion strategies were performed. Two feature extraction approaches including the selecting variables by a random forest-based method—Boruta algorithm and producing principal components by the dimension reduction technique of principal component analysis were considered in data fusion. Results (1) the difference of wild and cultivated samples did exist in terms of the content analysis of vital chemical component and fingerprint analysis. (2) the cultivated samples from different origins could be easily identified by Fourier transform infrared spectroscopy or liquid chromatography, while the wild required data fusion. (3) Boruta outperformed principal component analysis (PCA) in feature extraction. (4) Mid-level-Boruta preceded Mid-level-PCA, low-level and high-level data fusion and individual techniques. The Mid-level-Boruta PLS-DA model took full advantage of information synergy and showed the best performance. Conclusions This study proved that both geographical traceability and optimal identification methods of cultivated and wild samples were different, and data fusion was a potential technique in the geographical identification.

scholarly journals Deteksi Penyakit Kanker Payudara dengan Seleksi Fitur berbasis Principal Component Analysis dan Random Forest

2020 ◽  
Vol 2 (1) ◽  
pp. 96-101
Author(s):  
Ahmad Fauzi ◽  
Riki Supriyadi ◽  
Nurlaelatul Maulidah
Keyword(s):  
Breast Cancer ◽  
Principal Component Analysis ◽  
Random Forest ◽  
Cross Validation ◽  
Principal Component ◽  
Component Analysis ◽  
Data Set ◽  
Fold Cross Validation

Abstrak  - Skrining merupakan upaya deteksi dini untuk mengidentifikasi penyakit atau kelainan yang secara klinis belum jelas dengan menggunakan tes, pemeriksaan atau prosedur tertentu. Upaya ini dapat digunakan secara cepat untuk membedakan orang - orang yang kelihatannya sehat tetapi sesungguhnya menderita suatu kelainan.Tujuan utama penelitian ini adalah untuk meningkatkan peforma klasifikasi pada diagnosis kanker payudara dengan menerapkan seleksi fitur pada beberapa algoritme klasifikasi. Penelitian ini menggunakan database kanker payudara Breast Cancer Coimbra Data Set . Metode seleksi fitur berbasis pricipal component analysis akan dipasangkan dengan beberapa algoritme klasifikasi dan metode, seperti Logitboost,Bagging,dan Random Forest. Penelitian ini menggunakan 10 fold cross validation sebagai metode evaluasi. Hasil penelitian menunjukkan metode seleksi fitur berbasis pricipal component analysis mengalami peningkatan peforma klasifikasi secara signifikan setelah dipasangkan dengan seleksi fitur Random Forest dan logitboost, Random forest menunjukan peforma terbaik dengan akurasi 79.3103% dengan nilai AUC sebesar 0,843. Kata Kunci: Seleksi Fitur,PCA, Kanker Payudara,Skrining,Random Forest

scholarly journals Comparison of Geographical Traceability of Wild and Cultivated Macrohyporia cocos with Different Data Fusion Approaches

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Li Wang ◽  
Qinqin Wang ◽  
Yuanzhong Wang ◽  
Yunmei Wang
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Random Forest ◽  
Data Fusion ◽  
Economic Value ◽  
Principal Component ◽  
Component Analysis ◽  
Chemical Components ◽  
Significant Difference ◽  
Geographical Traceability

Poria originated from the dried sclerotium of Macrohyporia cocos is an edible traditional Chinese medicine with high economic value. Due to the significant difference in quality between wild and cultivated M. cocos, this study aimed to trace the origin of the fungus from the perspectives of wild and cultivation. In addition, there were quite limited studies about data fusion, a potential strategy, employed and discussed in the geographical traceability of M. cocos. Therefore, we traced the origin of M. cocos from the perspectives of wild and cultivation using multiple data fusion approaches. Supervised pattern recognition techniques, like partial least squares discriminant analysis (PLS-DA) and random forest, were employed in this study using. Five types of data fusion involving low-, mid-, and high-level data fusion strategies were performed. Two feature extraction approaches including the selecting variables by a random forest-based method—Boruta algorithm and producing principal components by the dimension reduction technique of principal component analysis—were considered in data fusion. The results indicate the following: (1) The difference between wild and cultivated samples did exist in terms of the content analysis of vital chemical components and fingerprint analysis. (2) Wild samples need data fusion to realize the origin traceability, and the accuracy of the validation set was 95.24%. (3) Boruta outperformed principal component analysis (PCA) in feature extraction. (4) The mid-level Boruta PLS-DA model took full advantage of information synergy and showed the best performance. This study proved that both geographical traceability and optimal identification methods of cultivated and wild samples were different, and data fusion was a potential technique in the geographical identification.

scholarly journals Analisis Metode Pengenalan Wajah Two Dimensial Principal Component Analysis (2DPCA) dan Kernel Fisher Discriminant Analysis Menggunakan Klasifikasi KNN (K- Nearest Neighbor)

2020 ◽  
Vol 2 (2) ◽  
pp. 29-38
Author(s):  
Abdur Rohman Harits Martawireja ◽  
Hilman Mujahid Purnama ◽  
Atika Nur Rahmawati
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Cross Validation ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
K Nearest Neighbor ◽  
Fisher Discriminant Analysis ◽  
Fisher Discriminant ◽  
Kernel Fisher Discriminant Analysis

Pengenalan wajah manusia (face recognition) merupakan salah satu bidang penelitian yang penting dan belakangan ini banyak aplikasi yang menerapkannya, baik di bidang komersil ataupun di bidang penegakan hukum. Pengenalan wajah merupakan sebuah sistem yang berfungsikan untuk mengidentifikasi berdasarkan ciri-ciri dari wajah seseorang berbasis biometrik yang memiliki keakuratan tinggi. Pengenalan wajah dapat diterapkan pada sistem keamanan. Banyak metode yang dapat digunakan dalam aplikasi pengenalan wajah untuk keamanan sistem, namun pada artikel ini akan membahas tentang dua metode yaitu Two Dimensial Principal Component Analysis dan Kernel Fisher Discriminant Analysis dengan metode klasifikasi menggunakan K-Nearest Neigbor. Kedua metode ini diuji menggunakan metode cross validation. Hasil dari penelitian terdahulu terbukti bahwa sistem pengenalan wajah metode Two Dimensial Principal Component Analysis dengan 5-folds cross validation menghasilkan akurasi sebesar 88,73%, sedangkan dengan 2-folds validation akurasi yang dihasilkan sebesar 89,25%. Dan pengujian metode Kernel Fisher Discriminant dengan 2-folds cross validation menghasilkan akurasi rata rata sebesar 83,10%.

Sign in / Sign up

Export Citation Format

Share Document