Article
Computer Science, Artificial Intelligence
Sangdi Lin, Bahareh Azarnoush, George Runger
Summary: This paper proposes a multi-target boosting method, named MTBR, for regression problems. Although it builds models separately for each target attribute, all target attributes are utilized when building each model by selecting the best models from all target attributes in each boosting iteration. The novel knowledge transfer approach introduced in this method uses the tree structure learned from one target attribute to predict another, proving the effectiveness of MTBR in leveraging knowledge from multiple target attributes and improving model accuracy through experiments with six datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
George Bai, Rohitash Chandra
Summary: This paper presents a Bayesian ensemble learning framework that utilizes Bayesian inference to improve prediction accuracy and quantify uncertainty. By combining multiple base learners and training them using MCMC sampling, the framework has good scalability on large-scale models.
Article
Computer Science, Artificial Intelligence
Andrei Konstantinov, Lev Utkin
Summary: This method proposes a way to interpret black-box models locally and globally based on ensemble gradient boosting machines, using simple decision tree structures and the Lasso method for weight calculation and update. Compared to the neural additive model, it provides a more intuitive and easy-to-train approach.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Maya Hilda Lestari Louk, Bayu Adhi Tama
Summary: This study introduces a dual ensemble model for anomaly-based intrusion detection systems, which combines bagging and gradient boosting decision tree (GBDT) techniques. The evaluation using multiple publicly available data sets shows that the proposed technique not only improves the detection rate and reduces the false alarm rate but also outperforms other similar techniques reported in the literature.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Thermodynamics
Rui Pan, Tongshen Liu, Wei Huang, Yuxin Wang, Duo Yang, Jie Chen
Summary: This paper proposes a two-stage transformation-based feature extraction method combined with the gradient boosting decision tree (GBDT) algorithm to estimate the state of health (SOH) of lithium-ion batteries. The proposed method effectively addresses the challenges posed by noise data, abnormal data, and data discontinuities, and achieves accurate and reliable SOH estimation.
Article
Computer Science, Artificial Intelligence
Kun Wang, Jie Lu, Anjin Liu, Yiliao Song, Li Xiong, Guangquan Zhang
Summary: This paper proposes a novel adaptive iterations (AdIter) method that automatically selects the number of iterations based on the severity of concept drift, in order to improve the prediction accuracy of data streams under concept drift.
Article
Genetics & Heredity
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Majid Bashir Malik, Saurav Mallik, Hong Qin
Summary: This study successfully predicted diabetes using machine learning algorithms with a high accuracy rate, and gradient boosting algorithm achieved the best performance among all classifiers. The results demonstrate the applicability of the suggested model for other diseases with similar predicate indications.
FRONTIERS IN GENETICS
(2023)
Article
Genetics & Heredity
Haodong Xu, Zhongming Zhao
Summary: In this study, a large benchmark dataset was generated, consisting of 124,879 experimentally supported linear epitope-containing regions in 3567 protein clusters from over 1.3 million B cell assays. The analysis of this dataset revealed a wide range of pathogen diversity. A ten-layer deep learning framework called NetBCE was developed for linear BCE prediction.
GENOMICS PROTEOMICS & BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Nishant Jain, Prasanta K. Jana
Summary: This paper proposes a logically randomized forest (LRF) algorithm, which improves traditional tree-based ensemble algorithms (TEAs) by incorporating two enhancements. The first enhancement addresses biasness by performing feature-level engineering, while the second enhancement selects more informative feature sub-spaces. Experimental results demonstrate that the LRF algorithm outperforms existing TEAs.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Ju-fu Cui, Hui Xia, Rui Zhang, Ben-xu Hu, Xiang-guo Cheng
Summary: The paper proposes an optimization scheme for GBDT to improve its detection precision and training efficiency, addressing issues such as imbalanced data and high dimensional data characteristics. The scheme includes using MSMOTE to address data imbalance, RFE-HCV to reduce data feature dimensionality, and FGS algorithm for parameter optimization efficiency. The experimental results show that the new scheme ensures data balance, eliminates redundant data features, and significantly improves parameter optimization efficiency.
COMPUTER COMMUNICATIONS
(2021)
Article
Mechanics
Quang-Viet Vu, Viet-Hung Truong, Huu-Tai Thai
Summary: This paper proposes an efficient and powerful machine learning-based framework for predicting the strength of concrete filled steel tubular (CFST) columns under concentric loading. The framework is based on the gradient tree boosting (GTB) algorithm and verified with a comprehensive database of over 1,000 tests on circular CFST columns.
COMPOSITE STRUCTURES
(2021)
Article
Computer Science, Artificial Intelligence
Janmenjoy Nayak, Bighnaraj Naik, Pandit Byomakesha Dash, Alireza Souri, Vimal Shanmuganathan
Summary: This paper proposes an efficient hand gesture recognition method based on LightGBM and memetic firefly algorithm, achieving a high accuracy of 99.36% and robust reliability.
APPLIED SOFT COMPUTING
(2021)
Article
Mathematics
Luca Di Persio, Nicola Fraccarolo
Summary: In recent years, there has been a growing interest in developing accurate and efficient forecasting methods for energy production and consumption. Traditional linear approaches are insufficient in modeling the relationships between variables, especially when dealing with multiple features. This study proposes a Gradient-Boosting-Machine-based framework to forecast the demand of customers in different locations within the Italian electricity market. The main challenge is to provide precise one-day-ahead predictions using historical data that is two months old, which requires incorporating exogenous regressors and tailoring them to the specific case. Numerical simulations demonstrate that the Gradient Boosting method outperforms classical statistical models such as ARMA, particularly in capturing holidays.
Article
Computer Science, Artificial Intelligence
Fabio Sigrist
Summary: The KTBoost algorithm combines kernel boosting and tree boosting, adding either a regression tree or an RKHS regression function in each boosting iteration. The combination of discontinuous trees and continuous RKHS regression functions allows for better learning of functions with parts of varying degrees of regularity. Empirical results demonstrate that KTBoost significantly outperforms both tree and kernel boosting in terms of predictive accuracy.
NEURAL PROCESSING LETTERS
(2021)
Article
Telecommunications
Debasmita Mishra, Bighnaraj Naik, Janmenjoy Nayak, Alireza Souri, Pandit Byomakesha Dash, S. Vimal
Summary: In this paper, an advanced and optimized Light Gradient Boosting Machine (LGBM) technique is proposed for identifying intrusive activities in the Internet of Things (IoT) network. The major contributions are: i) the development of an optimized LGBM model for identifying malicious IoT activities; ii) the adoption of an efficient evolutionary optimization approach for finding the optimal set of hyper-parameters of LGBM; iii) the evaluation of the proposed model using state-of-the-art ensemble learning and machine learning-based models. Simulation outcomes show that the proposed approach outperforms other methods and proves to be a robust approach for intrusion detection in an IoT environment.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Biochemical Research Methods
Xin Zhang, Lesong Wei, Xiucai Ye, Kai Zhang, Saisai Teng, Zhongshen Li, Junru Jin, Minjae Kim, Tetsuya Sakurai, Lizhen Cui, Balachandran Manavalan, Leyi Wei
Summary: A novel deep learning framework SiameseCPP is proposed for automated prediction of cell-penetrating peptides (CPPs). SiameseCPP learns discriminative representations of CPPs based on a well-pretrained model and a Siamese neural network comprising a transformer and gated recurrent units. Comprehensive experiments demonstrate that SiameseCPP outperforms existing baseline models for CPP prediction and exhibits satisfactory generalization ability on other functional peptide datasets.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemistry & Molecular Biology
Adeel Malik, Watshara Shoombuatong, Chang-Bae Kim, Balachandran Manavalan
Summary: A machine learning-based predictor called GPApred was developed to identify LPXTG-like proteins from their primary sequences. This predictor can be utilized for functional characterization and drug targeting in further research.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Multidisciplinary Sciences
Nattanong Bupi, Vinoth Kumar Sangaraju, Le Thi Phan, Aamir Lal, Thuy Thi Bich Vo, Phuong Thi Ho, Muhammad Amir Qureshi, Marjia Tabassum, Sukchan Lee, Balachandran Manavalan
Summary: Tomato yellow leaf curl virus (TYLCV) has spread to different countries, particularly in subtropical regions, and is associated with more severe symptoms. This study developed an integrated computational framework to accurately identify symptoms (mild or severe) based on TYLCV sequences isolated in Korea. Blind predictions revealed that 2 groups had severe symptoms and 1 group had mild symptoms.
Article
Biology
Saraswathy Nithiyanandam, Vinoth Kumar Sangaraju, Balachandran Manavalan, Gwang Lee
Summary: Protein folding is a complex process where a polymer of amino acids transitions from an unfolded state to a unique three-dimensional structure. Previous studies have identified structural parameters and examined their relationship with protein folding rate, but these parameters are only applicable to a limited set of proteins. Machine learning models have been proposed, but they fail to explain plausible folding mechanisms. In this study, ten different machine learning algorithms were evaluated using various structural parameters and network centrality measures, with support vector machine showing the best predictive capability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Phasit Charoenkwan, Pramote Chumnanpuen, Nalini Schaduangrat, Changmin Oh, Balachandran Manavalan, Watshara Shoombuatong
Summary: In this study, a novel computational approach called PSRQSP was developed to improve the prediction and analysis of QSPs. Experimental results showed that PSRQSP outperformed conventional methods in identifying QSPs and demonstrated its predictive capability and effectiveness. PSRQSP also constructed an easy-to-use web server for accelerating the discovery of potential QSPs for drug development.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biochemistry & Molecular Biology
Phasit Charoenkwan, Nalini Schaduangrat, Nhat Truong Pham, Balachandran Manavalan, Watshara Shoombuatong
Summary: Proposed the first stack-based approach, Pretoria, for accurate and large-scale identification of CD8+ T-cell epitopes (TCEs) of eukaryotic pathogens. Constructed a pool of 144 different machine learning (ML)-based classifiers based on 12 popular ML algorithms and used feature selection method to determine important ML classifiers for building the stacked model. Experimental results demonstrated that Pretoria outperformed several conventional ML classifiers and the existing method, with an accuracy of 0.866, MCC of 0.732, and AUC of 0.921 in the independent test.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Biochemistry & Molecular Biology
Ahmad Firoz, Adeel Malik, Hani Mohammed Ali, Yusuf Akhter, Balachandran Manavalan, Chang-Bae Kim
Summary: In this study, a new two-layer hybrid framework called PRR-HyPred was constructed to simultaneously predict and classify PRRs. Using support vector machine and random forest-based classifier, PRR-HyPred achieved accuracies of 83.4% and 95% in the first and second layers respectively. This is the first study that can predict and classify PRRs into specific families, and it can be a valuable tool for large-scale PRR prediction and classification, facilitating future studies.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Computer Science, Artificial Intelligence
Diponkor Bala, Md. Shamim Hossain, Mohammad Alamgir Hossain, Md. Ibrahim Abdullah, Md. Mizanur Rahman, Balachandran Manavalan, Naijie Gu, Mohammad S. Islam, Zhangjin Huang
Summary: The monkeypox virus poses a new pandemic threat. However, there is currently no reliable monkeypox database available for training and testing deep learning models. The MSID dataset has been developed for this purpose, providing a collection of monkeypox patient images for building confident deep learning models. The proposed MonkeyNet model can accurately identify monkeypox disease and assist doctors in making early diagnoses.
Review
Biochemical Research Methods
Le Thi Phan, Changmin Oh, Tao He, Balachandran Manavalan
Summary: Enhancers are non-coding DNA elements that enhance the transcription rate of specific genes. Computational platforms have been developed to complement experimental methods in identifying enhancers. This review provides an overview of machine learning-based prediction methods and databases for enhancer identification and discusses the advantages and drawbacks of these methods, as well as guidelines for developing more efficient enhancer predictors.
Editorial Material
Medicine, Research & Experimental
Shaherin Basith, Balachandran Manavalan
MOLECULAR THERAPY-NUCLEIC ACIDS
(2023)
Article
Toxicology
Tae Hwan Shin, Gwang Lee
Summary: Nanoparticles have been widely used in neurological research, but their potential toxicity remains a concern. This study investigated the effects of silica-coated magnetic nanoparticles on BV2 microglial cells and found that the nanoparticles induced amyloid beta accumulation and changes in lysosomal function. By employing triple-omics analysis, it was revealed that the nanoparticles caused a reduction in proteasome activity and lysosomal swelling. However, co-treatment with glutathione and citrate alleviated these effects.
ARCHIVES OF TOXICOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Nhat Truong Pham, Duc Ngoc Minh Dang, Ngoc Duy Nguyen, Thanh Thi Nguyen, Hai Nguyen, Balachandran Manavalan, Chee Peng Lim, Sy Dzung Nguyen
Summary: This paper proposes a deep learning framework for speech emotion recognition, which combines a hybrid data augmentation method and deep attention-based dilated convolutional-recurrent neural networks. The framework is able to extract high-level representations from three-dimensional log Mel spectrogram features. Experimental results show that the proposed framework outperforms other state-of-the-art methods on the EmoDB and ERC datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Biochemistry & Molecular Biology
Jun Sung Park, Kyonghwan Choe, Amjad Khan, Myeung Hoon Jo, Hyun Young Park, Min Hwa Kang, Tae Ju Park, Myeong Ok Kim
Summary: The aim of this study was to establish a functional in vitro co-cultured BBB model to investigate BBB-related physiological conditions. A co-cultured model consisting of brain-derived endothelial and astrocyte cells was successfully established on transwell membranes. The co-cultured model showed effective barrier properties and enhanced expression of tight junction proteins. Under disease conditions, the co-cultured model mimicked BBB damages. This in vitro BBB model can be a useful tool for studying BBB-related pathological and physiological processes.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Oncology
Hye Jin Yun, Min Li, Dong Guo, So Mi Jeon, Su Hwan Park, Je Sun Lim, Su Bin Lee, Rui Liu, Linyong Du, Seok-Ho Kim, Tae Hwan Shin, Seong-il Eyun, Yun-Yong Park, Zhimin Lu, Jong-Ho Lee
Summary: This study reveals that enhanced glucose-derived de novo serine biosynthesis is a critical metabolic feature of GBM cells under metabolic stress, and highlights the potential to target SSP for treating human GBM.
JOURNAL OF EXPERIMENTAL & CLINICAL CANCER RESEARCH
(2023)
Article
Biology
Shaherin Basith, Balachandran Manavalan, Gwang Lee
Summary: This study combined microsecond-scale unbiased molecular dynamics simulation with network analysis to elucidate the local and global conformational changes and allosteric communications in SOD1 systems. Structural analyses revealed significant variations in catalytic sites and stability due to unmetallated SOD1 systems and cysteine mutations. Dynamic motion analysis showed balanced atomic displacement and highly correlated motions in the Holo system.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
