scholarly journals A Comparison Study on Rule Extraction from Neural Network Ensembles, Boosted Shallow Trees, and SVMs

2018 ◽  
Vol 2018 ◽  
pp. 1-20 ◽  
Author(s):  
Guido Bologna ◽  
Yoichi Hayashi
Keyword(s):  
Neural Network ◽  
Cross Validation ◽  
Predictive Accuracy ◽  
Binary Classification ◽  
Support Vector ◽  
Multilayer Perceptrons ◽  
Classification Problems ◽  
Almost All ◽  
Neural Network Ensembles ◽  
Fold Cross Validation

One way to make the knowledge stored in an artificial neural network more intelligible is to extract symbolic rules. However, producing rules from Multilayer Perceptrons (MLPs) is an NP-hard problem. Many techniques have been introduced to generate rules from single neural networks, but very few were proposed for ensembles. Moreover, experiments were rarely assessed by 10-fold cross-validation trials. In this work, based on the Discretized Interpretable Multilayer Perceptron (DIMLP), experiments were performed on 10 repetitions of stratified 10-fold cross-validation trials over 25 binary classification problems. The DIMLP architecture allowed us to produce rules from DIMLP ensembles, boosted shallow trees (BSTs), and Support Vector Machines (SVM). The complexity of rulesets was measured with the average number of generated rules and average number of antecedents per rule. From the 25 used classification problems, the most complex rulesets were generated from BSTs trained by “gentle boosting” and “real boosting.” Moreover, we clearly observed that the less complex the rules were, the better their fidelity was. In fact, rules generated from decision stumps trained by modest boosting were, for almost all the 25 datasets, the simplest with the highest fidelity. Finally, in terms of average predictive accuracy and average ruleset complexity, the comparison of some of our results to those reported in the literature proved to be competitive.

scholarly journals Chronic Kidney Disease Prediction Using Neural Approach

2020 ◽  
Author(s):  
Samir Kumar Bandyopadhyay
Keyword(s):  
Neural Network ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Cross Validation ◽  
Health Condition ◽  
Support Vector ◽  
Kappa Score ◽  
Kidney Transplantations ◽  
End Stage ◽  
Fold Cross Validation

All over the world, chronic kidney disease (CKD) is a serious public health condition that needs to be detected in advance so that costly end-stage treatments like dialysis, kidney transplantations can be avoided. Neural network model and 10-fold cross-validation methodology under a single platform in proposed as well as implemented in order to classify patients with CKD. This will assist medical care fields so that counter measures can be suggested. The performance of proposed classifier is justified against other baseline classifiers such as Support Vector Machine, K-Nearest Neighbours, Decision tree and Gradient Boost classifier. Experimental results conclude that the performance of neural network with 10-fold cross-validation method reaches promising accuracy of 98.25%, f1-score of 0.98, and kappa score of 0.96 and MSE of 0.0175.

scholarly journals Chronic Kidney Disease Prediction Using Neural Approach

2020 ◽  
Author(s):  
Shawni Dutta ◽  
Samir Kumar Bandyopadhyay
Keyword(s):  
Neural Network ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Cross Validation ◽  
Health Condition ◽  
Support Vector ◽  
Kappa Score ◽  
Kidney Transplantations ◽  
End Stage ◽  
Fold Cross Validation

AbstractAll over the world, chronic kidney disease (CKD) is a serious public health condition that needs to be detected in advance so that costly end-stage treatments like dialysis, kidney transplantations can be avoided. Neural network model and 10-fold cross-validation methodology under a single platform in proposed as well as implemented in order to classify patients with CKD. This will assist medical care fields so that counter measures can be suggested. The performance of proposed classifier is justified against other baseline classifiers such as Support Vector Machine, K-Nearest Neighbours, Decision tree and Gradient Boost classifier. Experimental results conclude that the performance of neural network with 10-fold cross-validation method reaches promising accuracy of 98.25%, f1-score of 0.98, and kappa score of 0.96 and MSE of 0.0175.

Combination of Support Vector Machine and K-Fold cross-validation for prediction of long-term degradation of the compressive strength of marine concrete

2018 ◽  
Vol 1 (1) ◽  
pp. 120-130 ◽  
Author(s):  
Chunxiang Qian ◽  
Wence Kang ◽  
Hao Ling ◽  
Hua Dong ◽  
Chengyao Liang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Environmental Factors ◽  
Cross Validation ◽  
Concrete Strength ◽  
Simulation Method ◽  
Support Vector ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Influence Degree ◽  
Fold Cross Validation

Support Vector Machine (SVM) model optimized by K-Fold cross-validation was built to predict and evaluate the degradation of concrete strength in a complicated marine environment. Meanwhile, several mathematical models, such as Artificial Neural Network (ANN) and Decision Tree (DT), were also built and compared with SVM to determine which one could make the most accurate predictions. The material factors and environmental factors that influence the results were considered. The materials factors mainly involved the original concrete strength, the amount of cement replaced by fly ash and slag. The environmental factors consisted of the concentration of Mg2+, SO42-, Cl-, temperature and exposing time. It was concluded from the prediction results that the optimized SVM model appeared to perform better than other models in predicting the concrete strength. Based on SVM model, a simulation method of variables limitation was used to determine the sensitivity of various factors and the influence degree of these factors on the degradation of concrete strength.

scholarly journals Pengenalan Wajah Manusia berbasis Algoritma Local Binary Pattern

2017 ◽  
Vol 17 (2) ◽  
pp. 29-38
Author(s):  
Ratih Purwati ◽  
Gunawan Ariyanto
Keyword(s):  
Computer Vision ◽  
Support Vector Machine ◽  
Face Recognition ◽  
Local Binary Pattern ◽  
Cross Validation ◽  
Support Vector ◽  
Fold Cross Validation

Face Recognition merupakan teknologi komputer untuk mengidentifikasi wajah manusia melalui gambar digital yang tersimpan di database. Wajah manusia dapat berubah bentuk sesuai dengan ekspresi yang dimilikinya. Wajah manusia dapat berubah bentuk sesuai dengan eskpresi yang dimilikinya. Ekspresi wajah manusia memiliki kemiripan satu sama lain sehingga untuk mengenali suatu ekspresi adalah kepunyaan siapa akan sedikit sulit. Pengenalan wajah terus menjadi topik aktif di zaman sekarang pada penelitian bidang computer vision. Penggunaan wajah manusia sering kita jumpai pada fitur-fitur aplikasi media sosial seperti Snapchat, Snapgram dari Instagram dan banyak aplikasi sosial media lainnya yang menggunakan teknologi tersebut. Pada penelitian ini dilakukan analisa pengenalan ekpresi wajah manusia dengan pendekatan fitur alogaritma Local Binary Pattern dan mencari pengembangan alogaritma dasar Local Binary Pattern yang paling optimal dengan cara menggabungkan metode Hisogram Equalization, Support Vector Machine, dan K-fold cross validation sehingga dapat meningkatkan pengenalan gambar wajah manusia pada hasil yang terbaik. Penelitian ini menginput beberapa database wajah manusia seperti JAFFE yang merupakan gambar wajah manusia wanita jepang yang berjumlah 10 orang dengan 7 ekspresi emosional seperti marah, sedih, bahagia, jijik, kaget, takut dan netral ke dalam sistem. YALE yaitu merupakan gambar wajah manusia orang Amerika. Serta menggunakan dataset CALTECH yang merupakan gambar manusia yang terdiri dari 450 gambar dengan ukuran 896 x 592 piksel dan disimpan dalam format JPEG. Kemudian data tersebut di sesuaikan dengan bentuk tekstur wajah masing-masing. Dari hasil penggabungan ketiga metode diatas dan percobaan-percobaan yang sudah dilakukan, didapatkan hasil yang paling optimal dalam pengenalan wajah manusia yaitu menggunakan dataset JAFFE dengan resolusi 92 x 112 piksel dan dengan tingkat penggunaan processor yang tinggi dapat mempengaruhi waktu kecepatan komputasi dalam proses menjalankan sistem sehingga menghasilkan prediksi yang lebih tepat.

Abstract 473: Identification of Apolipoproteins Using Feature Selection Technique

2016 ◽  
Vol 36 (suppl_1) ◽  
Author(s):  
Hua Tang ◽  
Hao Lin
Keyword(s):  
Support Vector Machine ◽  
Cross Validation ◽  
Support Vector ◽  
Feature Subset ◽  
Risk Markers ◽  
Dipeptide Composition ◽  
Accurate Identification ◽  
Feature Selection Technique ◽  
Physiological Importance ◽  
Fold Cross Validation

Objective: Apolipoproteins are of great physiological importance and are associated with different diseases such as dyslipidemia, thrombogenesis and angiocardiopathy. Apolipoproteins have therefore emerged as key risk markers and important research targets yet the types of apolipoproteins has not been fully elucidated. Accurate identification of the apoliproproteins is very crucial to the comprehension of cardiovascular diseases and drug design. The aim of this study is to develop a powerful model to precisely identify apolipoproteins. Approach and Results: We manually collected a non-redundant dataset of 53 apoliproproteins and 136 non-apoliproproteins with the sequence identify of less than 40% from UniProt. After formulating the protein sequence samples with g -gap dipeptide composition (here g =1~10), the analysis of various (ANOVA) was adopted to find out the best feature subset which can achieve the best accuracy. Support Vector Machine (SVM) was then used to perform classification. The predictive model was evaluated using a five-fold cross-validation which yielded a sensitivity of 96.2%, a specificity of 99.3%, and an accuracy of 98.4%. The study indicated that the proposed method could be a feasible means of conducting preliminary analyses of apoliproproteins. Conclusion: We demonstrated that apoliproproteins can be predicted from their primary sequences. Also we discovered the special dipeptide distribution in apoliproproteins. These findings open new perspectives to improve apoliproproteins prediction by considering the specific dipeptides. We expect that these findings will help to improve drug development in anti-angiocardiopathy disease. Key words: Apoliproproteins Angiocardiopathy Support Vector Machine

Enhancing Vibration-Based Structural Health Monitoring via Edge Computing: A Tiny Machine Learning Perspective

2021 ◽  
Author(s):  
Federica Zonzini ◽  
Francesca Romano ◽  
Antonio Carbone ◽  
Matteo Zauli ◽  
Luca De Marchi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Network Architecture ◽  
Binary Classification ◽  
Low Cost ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Structural Health

Abstract Despite the outstanding improvements achieved by artificial intelligence in the Structural Health Monitoring (SHM) field, some challenges need to be coped with. Among them, the necessity to reduce the complexity of the models and the data-to-user latency time which are still affecting state-of-the-art solutions. This is due to the continuous forwarding of a huge amount of data to centralized servers, where the inference process is usually executed in a bulky manner. Conversely, the emerging field of Tiny Machine Learning (TinyML), promoted by the recent advancements by the electronic and information engineering community, made sensor-near data inference a tangible, low-cost and computationally efficient alternative. In line with this observation, this work explored the embodiment of the One Class Classifier Neural Network, i.e., a neural network architecture solving binary classification problems for vibration-based SHM scenarios, into a resource-constrained device. To this end, OCCNN has been ported on the Arduino Nano 33 BLE Sense platform and validated with experimental data from the Z24 bridge use case, reaching an average accuracy and precision of 95% and 94%, respectively.

The Animal Classification: An Evaluation of Different Transfer Learning Pipeline

Mekatronika ◽  
2021 ◽  
Vol 3 (1) ◽  
pp. 27-31
Author(s):  
Ken-ji Ee ◽  
Ahmad Fakhri Bin Ab. Nasir ◽  
Anwar P. P. Abdul Majeed ◽  
Mohd Azraai Mohd Razman ◽  
Nur Hafieza Ismail
Keyword(s):  
Transfer Learning ◽  
Classification System ◽  
Cross Validation ◽  
Support Vector ◽  
Svm Classifier ◽  
Average Classification Accuracy ◽  
Validation Technique ◽  
Search Approach ◽  
Fold Cross Validation

The animal classification system is a technology to classify the animal class (type) automatically and useful in many applications. There are many types of learning models applied to this technology recently. Nonetheless, it is worth noting that the extraction of the features and the classification of the animal features is non-trivial, particularly in the deep learning approach for a successful animal classification system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards animal classification applications are somewhat limited. The present study aims to determine a suitable TL-conventional classifier pipeline for animal classification. The VGG16 and VGG19 were used in extracting features and then coupled with either k-Nearest Neighbour (k-NN) or Support Vector Machine (SVM) classifier. Prior to that, a total of 4000 images were gathered consisting of a total of five classes which are cows, goats, buffalos, dogs, and cats. The data was split into the ratio of 80:20 for train and test. The classifiers hyper parameters are tuned by the Grids Search approach that utilises the five-fold cross-validation technique. It was demonstrated from the study that the best TL pipeline identified is the VGG16 along with an optimised SVM, as it was able to yield an average classification accuracy of 0.975. The findings of the present investigation could facilitate animal classification application, i.e. for monitoring animals in wildlife.

Sign in / Sign up

Export Citation Format

Share Document