Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

Antimicrobial peptides (AMPs) are natural peptides possessing antimicrobial activities. These peptides are important components of the innate immune system. They are found in various organisms. AMP screening and identification by experimental techniques are laborious and time-consuming tasks. Alternatively, computational methods based on machine learning have been developed to screen potential AMP candidates prior to experimental verification. Although various AMP prediction programs are available, there is still a need for improvement to reduce false positives (FPs) and to increase the predictive accuracy. In this work, several well-known single and ensemble machine learning approaches have been explored and evaluated based on balanced training datasets and two large testing datasets. We have demonstrated that the developed program with various predictive models has high performance in differentiating between AMPs and non-AMPs. Thus, we describe the development of a program for the prediction and recognition of AMPs using MaxProbVote, which is an ensemble model. Moreover, to increase prediction efficiency, the ensemble model was integrated with a new hybrid feature based on logistic regression. The ensemble model integrated with the hybrid feature can effectively increase the prediction sensitivity of the developed program called Ensemble-AMPPred, resulting in overall improvements in terms of both sensitivity and specificity compared to those of currently available programs.

Download Full-text

PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins

Bioinformatics ◽

10.1093/bioinformatics/btz629 ◽

2019 ◽

Cited By ~ 3

Author(s):

Yanju Zhang ◽

Sha Yu ◽

Ruopeng Xie ◽

Jiahui Li ◽

André Leier ◽

...

Keyword(s):

Machine Learning ◽

Secreted Proteins ◽

Gradient Boosting ◽

Ensemble Model ◽

Gram Positive ◽

Gram Positive Bacteria ◽

Single Feature ◽

Gradient Boosting Machine ◽

Benchmark Datasets ◽

Feature Based

Abstract Motivation Gram-positive bacteria have developed secretion systems to transport proteins across their cell wall, a process that plays an important role during host infection. These secretion mechanisms have also been harnessed for therapeutic purposes in many biotechnology applications. Accordingly, the identification of features that select a protein for efficient secretion from these microorganisms has become an important task. Among all the secreted proteins, ‘non-classical’ secreted proteins are difficult to identify as they lack discernable signal peptide sequences and can make use of diverse secretion pathways. Currently, several computational methods have been developed to facilitate the discovery of such non-classical secreted proteins; however, the existing methods are based on either simulated or limited experimental datasets. In addition, they often employ basic features to train the models in a simple and coarse-grained manner. The availability of more experimentally validated datasets, advanced feature engineering techniques and novel machine learning approaches creates new opportunities for the development of improved predictors of ‘non-classical’ secreted proteins from sequence data. Results In this work, we first constructed a high-quality dataset of experimentally verified ‘non-classical’ secreted proteins, which we then used to create benchmark datasets. Using these benchmark datasets, we comprehensively analyzed a wide range of features and assessed their individual performance. Subsequently, we developed a two-layer Light Gradient Boosting Machine (LightGBM) ensemble model that integrates several single feature-based models into an overall prediction framework. At this stage, LightGBM, a gradient boosting machine, was used as a machine learning approach and the necessary parameter optimization was performed by a particle swarm optimization strategy. All single feature-based LightGBM models were then integrated into a unified ensemble model to further improve the predictive performance. Consequently, the final ensemble model achieved a superior performance with an accuracy of 0.900, an F-value of 0.903, Matthew’s correlation coefficient of 0.803 and an area under the curve value of 0.963, and outperforming previous state-of-the-art predictors on the independent test. Based on our proposed optimal ensemble model, we further developed an accessible online predictor, PeNGaRoo, to serve users’ demands. We believe this online web server, together with our proposed methodology, will expedite the discovery of non-classically secreted effector proteins in Gram-positive bacteria and further inspire the development of next-generation predictors. Availability and implementation http://pengaroo.erc.monash.edu/. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Ensemble Learning of Lightweight Deep Learning Models Using Knowledge Distillation for Image Classification

Mathematics ◽

10.3390/math8101652 ◽

2020 ◽

Vol 8 (10) ◽

pp. 1652

Author(s):

Jaeyong Kang ◽

Jeonghwan Gwak

Keyword(s):

Deep Learning ◽

Image Classification ◽

Limited Resources ◽

Ensemble Model ◽

Learning Models ◽

Model Compression ◽

Knowledge Distillation ◽

Feature Based ◽

Classification Tasks ◽

Teacher Model

In recent years, deep learning models have been used successfully in almost every field including both industry and academia, especially for computer vision tasks. However, these models are huge in size, with millions (and billions) of parameters, and thus cannot be deployed on the systems and devices with limited resources (e.g., embedded systems and mobile phones). To tackle this, several techniques on model compression and acceleration have been proposed. As a representative type of them, knowledge distillation suggests a way to effectively learn a small student model from large teacher model(s). It has attracted increasing attention since it showed its promising performance. In the work, we propose an ensemble model that combines feature-based, response-based, and relation-based lightweight knowledge distillation models for simple image classification tasks. In our knowledge distillation framework, we use ResNet−20 as a student network and ResNet−110 as a teacher network. Experimental results demonstrate that our proposed ensemble model outperforms other knowledge distillation models as well as the large teacher model for image classification tasks, with less computational power than the teacher model.

Download Full-text

STACKING ENSEMBLE MODEL FOR POLARITY CLASSIFICATION IN FEATURE BASED OPINION MINING

Indian Journal of Computer Science and Engineering ◽

10.21817/indjcse/2018/v9i3/180903004 ◽

2018 ◽

Vol 9 (3) ◽

pp. 91-95

Author(s):

Padmapani P. Tribhuvan ◽

Sunil G. Bhirud ◽

Ratnadeep R. Deshmukh

Keyword(s):

Opinion Mining ◽

Ensemble Model ◽

Feature Based ◽

Polarity Classification

Download Full-text

Nonverbal Communication through Facial Expression in Diverse Conditions

10.5772/intechopen.95109 ◽

2021 ◽

Author(s):

Mahesh Goyani

Keyword(s):

Facial Expression ◽

Template Matching ◽

Facial Expression Recognition ◽

Recognition Rate ◽

Training Sample ◽

Expression Recognition ◽

Feature Based ◽

Multi Level ◽

Space Recognition ◽

Vision Technique

In this chapter, we investigated computer vision technique for facial expression recognition, which increase both - the recognition rate and computational efficiency. Local and global appearance-based features are combined in order to incorporate precise local texture and global shapes. We proposed Multi-Level Haar (MLH) feature based system, which is simple and fast in computation. The driving factors behind using the Haar were its two interesting properties - signal compression and energy preservation. To depict the importance of facial geometry, we first segmented the facial components like eyebrows, eye, and mouth, and then applied feature extraction on these facial components only. Experiments are conducted on three well known publicly available expression datasets CK, JAFFE, TFEID and in-house WESFED dataset. The performance is measured against various template matching and machine learning classifiers. We achieved highest recognition rate for proposed operator with Discriminant Analysis Classifier. We studied the performance of proposed approach in several scenarios like expression recognition from low resolution, recognition from small training sample space, recognition in the presence of noise and so forth.

Download Full-text

Automated music video generation using multi-level feature-based segmentation

Multimedia Tools and Applications ◽

10.1007/s11042-008-0225-0 ◽

2008 ◽

Vol 41 (2) ◽

pp. 197-214 ◽

Cited By ~ 14

Author(s):

Jong-Chul Yoon ◽

In-Kwon Lee ◽

Siwoo Byun

Keyword(s):

Music Video ◽

Feature Based ◽

Multi Level

Download Full-text

Ensembled liver cancer detection and classification using CT images

Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine ◽

10.1177/0954411920971888 ◽

2020 ◽

pp. 095441192097188

Author(s):

Abhay Krishan ◽

Deepti Mittal

Keyword(s):

Liver Cancer ◽

Early Stage ◽

Imaging Techniques ◽

Ct Images ◽

Computer Assisted ◽

Ensemble Model ◽

Tumor Identification ◽

Multi Level ◽

The Individual ◽

Cellular Carcinoma

Computed tomography (CT) images are commonly used to diagnose liver disease. It is sometimes very difficult to comment on the type, category and level of the tumor, even for experienced radiologists, directly from the CT image, due to the varying intensities. In recent years, it has been important to design and develop computer-assisted imaging techniques to help doctors/physicians improve their diagnosis. The proposed work is to detect the presence of a tumor region in the liver and classify the different stages of the tumor from CT images. CT images of the liver have been classified between normal and tumor classes. In addition, CT images of the tumor have been classified between Hepato Cellular Carcinoma (HCC) and Metastases (MET). The performance of six different classifiers was evaluated on different parameters. The accuracy achieved for different classifiers varies between 98.39% and 100% for tumor identification and between 76.38% and 87.01% for tumor classification. To further, improve performance, a multi-level ensemble model is developed to detect a tumor (liver cancer) and to classify between HCC and MET using features extracted from CT images. The k-fold cross-validation (CV) is also used to justify the robustness of the classifiers. Compared to the individual classifier, the multi-level ensemble model achieved high accuracy in both the detection and classification of different tumors. This study demonstrates automated tumor characterization based on liver CT images and will assist the radiologist in detecting and classifying different types of tumors at a very early stage.

Download Full-text