Optimal Hyper-Parameter Tuning of SVM Classifiers With Application to Medical Diagnosis

Rojas-Domínguez, Alfonso; Padierna, Luis Carlos; Carpío, Martín; Soberanes, Héctor José Puga; Fraire, Héctor

doi:10.1109/access.2017.2779794

Cited by 72 publications

(40 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Two approaches for hyperparameter optimization were tested in this work, Randomized [20] and Bayes Search Cross Validation [11]. The Grid search was not considered given its rather high computational complexity.…”

Section: E the Class Data Balance And The Hyperparameter Optimizationmentioning

confidence: 99%

An Accurate Data Preparation Approach for the Prediction of Mortality in ACLF Patients using the CANONIC Dataset

García

Doyle

Ranco

et al. 2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Section: E the Class Data Balance And The Hyperparameter Optimizationmentioning

confidence: 99%

An Accurate Data Preparation Approach for the Prediction of Mortality in ACLF Patients using the CANONIC Dataset

García

Doyle

Ranco

et al. 2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

“…Each model in our experiment was tuned to the best SVM parameters on a separate 1840 random observations from the total 4840 imputed observations. Consistent with the literature, our tuning process used 10-fold cross-validation that ensured optimal parameters for each model [47]. We used the SVM and tune functions in the e1071 R library to perform the tuning process [38].…”

Section: Evaluation Of the Linguistic Battery With Machine Learning Tmentioning

confidence: 99%

“…Finally, the machine learning algorithm used for building the diagnostic models was tuned to the optimal parameters on each model [47]. As such, performing similar experiments on a different dataset would require that the machine learning algorithm is tuned on that dataset to PLOS ONE…”

Section: Limitationsmentioning

confidence: 99%

A machine learning-based linguistic battery for diagnosing mild cognitive impairment due to Alzheimer’s disease

et al. 2020

View full text Add to dashboard Cite

There is a limited evaluation of an independent linguistic battery for early diagnosis of Mild Cognitive Impairment due to Alzheimer's disease (MCI-AD). We hypothesized that an independent linguistic battery comprising of only the language components or subtests of popular test batteries could give a better clinical diagnosis for MCI-AD compared to using an exhaustive battery of tests. As such, we combined multiple clinical datasets and performed Exploratory Factor Analysis (EFA) to extract the underlying linguistic constructs from a combination of the Consortium to Establish a Registry for Alzheimer's disease (CERAD), Wechsler Memory Scale (WMS) Logical Memory (LM) I and II, and the Boston Naming Test. Furthermore, we trained a machine-learning algorithm that validates the clinical relevance of the independent linguistic battery for differentiating between patients with MCI-AD and cognitive healthy control individuals. Our EFA identified ten linguistic variables with distinct underlying linguistic constructs that show Cronbach's alpha of 0.74 on the MCI-AD group and 0.87 on the healthy control group. Our machine learning evaluation showed a robust AUC of 0.97 when controlled for age, sex, race, and education, and a clinically reliable AUC of 0.88 without controlling for age, sex, race, and education. Overall, the linguistic battery showed a better diagnostic result compared to the Mini-Mental State Examination (MMSE), Clinical Dementia Rating Scale (CDR), and a combination of MMSE and CDR.

show abstract

“…Selain itu, SVM juga dapat diaplikasikan pada klasifikasi gambar seperti yang dilakukan dalam penelitian [4]. Penelitian terkait dengan optimasi SVM juga dilakukan pada [5] dan diaplikasikan untuk diagnosa medis. Sementara pada penelitian ini, SVM digunakan untuk memprediksi kondisi air tambak berdasarkan beberapa input nilai parameter air.…”

Section: Pendahuluanunclassified

Grid SVM: Aplikasi Machine Learning dalam Pengolahan Data Akuakultur

Natan

Gunawan

Dewantara

2019

JRE

View full text Add to dashboard Cite

Kondisi air merupakan faktor utama yang mempengaruhi tingkat kesuksesan dalam akuakultur khususnya pada budidaya udang. Akan tetapi, petani sering mengalami kesulitan dalam menentukan kondisi tersebut yang didasarkan pada hasil pengukuran berbagai parameter air. Oleh karena itu, diperlukan sebuah model klasifikasi yang tepat untuk membantu petani dalam mengklasifikasi kondisi air di tambak. Dengan mengetahui kondisi tersebut, maka treatment yang tepat dan sesuai dapat diberikan. Pada penelitian ini, algoritma machine learning bernama support vector machine (SVM) digunakan untuk membuat model dari sebuah dataset akuakultur. Teknik pemrosesan lain seperti normalisasi data dan penggunaan algoritma optimasi bernama grid search juga dilakukan untuk meningkatkan hasil pemodelan. Selanjutnya, sebuah skema pengujian dengan k-fold cross validation dilakukan untuk mengetahui performa dari model yang diukur berdasarkan nilai akurasi, presisi, recall, f-measure, dan area under receiver operating characteristic curve (AUROC). Kemudian, model dari SVM ini dibandingkan dengan model yang dibentuk dengan algoritma yang lain yaitu K-nearest neighbor (KNN), random forest (RF), logistic regression (LR), complement naive bayes (CNB), dan multi-layer perceptron (MLP) guna mengetahui model yang paling bagus untuk diimplementasikan pada proses budidaya. Dari hasil percobaan, model yang dibentuk dengan SVM dan optimasi grid search memiliki performa paling tinggi saat proses validasi dengan skor performa keseluruhan sebesar 3,54383.

show abstract

Optimal Hyper-Parameter Tuning of SVM Classifiers With Application to Medical Diagnosis

Cited by 72 publications

References 22 publications

An Accurate Data Preparation Approach for the Prediction of Mortality in ACLF Patients using the CANONIC Dataset

An Accurate Data Preparation Approach for the Prediction of Mortality in ACLF Patients using the CANONIC Dataset

A machine learning-based linguistic battery for diagnosing mild cognitive impairment due to Alzheimer’s disease

Grid SVM: Aplikasi Machine Learning dalam Pengolahan Data Akuakultur

Contact Info

Product

Resources

About