检索结果-内蒙古大学图书馆

Non-toxic antimicrobial peptide Hm-AMP2 from leech metagenome proteins identified by the gradient-boosting approach

MATERIALS & DESIGN 2022年 224卷

作者： Grafskaia, Ekaterina N. Pavlova, Elizaveta R. Latsis, Ivan A. Malakhova, Maja V. Ivchenkov, Dmitrii V. Bashkirov, Pavel V. Kot, Erik F. Mineev, Konstantin S. Arseniev, Alexander S. Klinov, Dmitry V. Lazarev, Vassili N. Fed Med Biol Agcy Fed Res & Clin Ctr Phys Chem Med Moscow 119435 Russia Russian Acad Sci Shemyakin Ovchinnikov Inst Bioorgan Chem Moscow 117997 Russia Natl Res Univ Moscow Inst Phys & Technol 141700 Dolgoprudny Moscow 141701 Russia Peoples Friendship Univ Russia RUDN Univ Moscow 117198 Russia

The number of infections caused by antibiotic-resistant pathogens is increasing alarmingly every year and will continue to grow. Antimicrobial peptides (AMPs) are considered new therapeutic agents for the effective combat against infectious diseases. We report the design of antimicrobial peptides derived from a database of leech metagenome proteins using a machine learning approach. Peptides with antimicrobial activity and reduced toxicity were identified by the CatBoost algorithm. Among them, Hm-AMP2 possesses the most promising application in practice, including antibacterial activity against both Gram-positive and Gram-negative bacteria, low cytotoxic and hemolytic effects. Hm-AMP2 kills various bacteria at low concentrations (4.6-18.5 lM) by the disruption of bacterial membranes. According to nuclear magnetic resonance analysis, the peptide adopts an a-helical structure in a membrane environment. Hm-AMP2 interacts with lipopolysaccharides of different bacteria according to microscale thermophoresis and CD spectroscopy analysis. This effect can play a role in the first defense against the organism's bacterial invasion. The computational approach developed for the identification of AMP can be useful for the rational design of effective non-toxic peptide antibiotics. (c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-NDlicense (http://***/licenses/by-nc-nd/4.0/).

关键词： Antimicrobial peptides Medicinal leech Non-toxic effect gradient boosting algorithm

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive framework for Parkinson's disease diagnosis using explainable artificial intelligence empowered machine learning techniques

引用

ALEXANDRIA ENGINEERING JOURNAL 2024年 107卷 568-582页

作者： Priyadharshini, S. Ramkumar, K. Vairavasundaram, Subramaniyaswamy Narasimhan, K. Venkatesh, S. Amirtharajan, Rengarajan Kotecha, Ketan SASTRA Deemed Univ Sch Elect & Elect Engn Thanjavur India SASTRA Deemed Univ Sch Comp Thanjavur India Vellore Inst Technol Sch Comp Sci & Engn Vellore India Symbiosis Int Symbiosis Inst Technol Symbiosis Ctr Appl Artificial Intelligence Pune India

Parkinson's disease (PD) is the second most prevalent neurological disorder, predominantly affecting older people. With no existing cure, the early detection of PD, where symptoms are not entirely evident but indicative of the disease's onset, is critical. This study aims to design and develop AI-based diagnostic methods that can detect these early signs of PD with high accuracy, thereby facilitating more effective disease management. This study focuses on developing a method that not only identifies PD at an early stage but also provides clinicians with a tool to interpret the decisions taken by the AI models to avoid misdiagnosis. In this study, a T2-weighted 3D Magnetic resonance imaging (MRI) dataset is used to analyze detailed morphological, textural, and structural changes. The MRI scans are pre-processed using brain extraction, image registration, bias correction, normalization, and segmentation processes. Upon segmentation, feature extraction was applied to the segmented subcortical regions using radiomics tools, resulting in the extraction of 107 features. The top 20 features were selected through Pearson's correlation, recursive feature elimination, and a ranking model, which are responsible for the ML model's class prediction. Statistical validation of these features was also performed using Analysis of Variance (ANOVA), pairwise t-tests, and Kruskal-Wallis H-tests to ensure that the identified 20 features were dominant for the prediction. Based on the identified features, several Machine Learning (ML) models were used to identify the best classifier for the provided real-world MRI scans. The gradient boosting (GB) algorithm achieved better prediction accuracy among the compared models. Incorporating the Synthetic Minority Oversampling Technique (SMOTE) to address data imbalances significantly improved the model's performance, boosting accuracy to 96.8 % from 87 %. Further, multiple Explainable Artificial Intelligence (XAI) techniques were deployed to enh

关键词： Parkinson's disease gradient boosting algorithm Magnetic resonance imaging analysis Explainable artificial intelligence Early detection

来源：评论

学校读者我要写书评

暂无评论

Noise Figure Estimation of EDFA Based on gradient boosting Regression Approach for THz Applications

Noise Figure Estimation of EDFA Based on Gradient Boosting R...

引用

Workshop on Microwave Theory and Techniques in Wireless Communications (MTTW)

作者： Sadik, Serif Ali Kutahya Dumlupinar Univ Photon Technol Applicat & Res Ctr Kutahya Turkey

ISBN: (数字)9781665464390

ISBN: (纸本)9781665464390

Optical communication systems operating in the THz region require monitoring and control of transmission quality for higher network performance. Erbium-doped fiber amplifiers (EDFA) are one of the most important elements of such systems and input power and wavelength depended gain and noise characteristics of EDFAs complicate the network control. In this work, noise figure (NF) parameter of an EDFA was estimated with gradient boosting regressor model. The training and test data for the model were collected experimentally. The predicted values and real values of NF were fitted well with a coefficient of determination value of 0.9742, mean absolute error of 03428, and the root mean square error of 0.4429.

关键词： erbium-doped fiber amplifier noise figure machine learning gradient boosting algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Markov chain latent space probabilistic decision-making for feature optimization in content-based image recognition

引用

SOFT COMPUTING 2023年第2期28卷 653-653页

作者： Kaur, Ramandeep Devendran, V. Lovely Profess Univ Dept Comp Sci & Engn Phagwara Punjab India

Content-Based Image Retrieval (CBIR) systems use a group of preset and predefined parameters for their configuration. However, in machine learning methods, feature selection is a preprocessing step. Framework designed for feature selection considers feature subsets of datasets as a node and edges as a customized relation between features. However, most feature selection strategies are ineffective when dealing with diverse and inhomogeneous data. Therefore, Markov chain rule-based feature selection technique has been proposed for handling all kinds of data. The novelty of work is that a feature selection algorithm-based probabilistic latent network has been proposed, which will consider all subsets of features as a pathway on an undirected graph. Such kind of pathways is possible during ranking phase on a graph, which will effectively avoid the combinatorial problem. At last, gradient boosting algorithm was applied to classify the features. The suggested work's main contribution is identifying the relevance. Results have been compared for different clustering techniques along with different machine learning algorithms like SVM, Decision Tree and KNN and proposed technique have got better results with Fuzzy C mean and used it for further feature optimization along with gradient boosting algorithm. We have evaluated the results using CIFAR-10, CIFAR-100, and Web-Crawled misc 1 and Web-Crawled misc 2 datasets. The highest accuracy levels of 98% for CIFAR-10, 98.24% for CIFAR-100, 98.05, 97.87% for Web-crawled misc 1, and 97.4% for Web-crawled misc 1, respectively, have been achieved using the proposed model. Along with that, comparison with others has done and this technique has got better accuracy than their results.

关键词： Automated ranking Probabilistic latent network gradient boosting algorithm Markov chain rule Content-based image retrieval

来源：评论

学校读者我要写书评

暂无评论

Identifying new earnings management components: a machine learning approach

引用

ACCOUNTING RESEARCH JOURNAL 2024年第4期37卷 418-435页

作者： Almasarwah, Adel Aram, Khalid Y. Alhaj-Yaseen, Yaseen S. Georgia Coll & State Univ Dept Accounting Milledgeville GA 31061 USA Emporia State Univ Dept Business Emporia KS USA Middle Georgia State Coll Dept Finance Macon GA USA

PurposeThis study aims to apply machine learning (ML) to identify new financial elements managers might use for earnings management (EM), assessing their impact on the Standard Jones Model and modified Jones model for EM detection and examining managerial motives for using these ***/methodology/approachUsing eXtreme gradient boosting on 23,310 the US firm-year observations from 2012 to2021, the study pinpoints nine financial variables potentially used for earnings manipulation, not covered by traditional accruals *** of goods sold and earnings before interest, taxes, depreciation and amortization are identified as the most significant for EM, with relative importances of 40.2% and 11.5%, *** limitations/implicationsThe study's scope, limited to a specific data set and timeframe, and the exclusion of some financial variables may impact the findings' broader *** implicationsThe results are crucial for researchers, practitioners, regulators and investors, offering strategies for detecting and addressing *** implicationsInsights from the study advocate for greater financial transparency and integrity in ***/valueBy incorporating ML in EM detection and spotlighting overlooked financial variables, the research brings fresh perspectives and opens new avenues for further exploration in the field.

关键词： Earnings management Machine learning Accrual manipulation gradient boosting algorithm

来源：评论

学校读者我要写书评

暂无评论

Markov chain latent space probabilistic for feature optimization along with Hausdorff distance similarity matching in content-based image retrieval

引用

IMAGING SCIENCE JOURNAL 2022年第5期70卷 300-314页

作者： Kaur, Ramandeep Devendran, V. Lovely Profess Univ Dept Comp Sci & Engn Phagwara Punjab India

Content-Based Image Retrieval involves searching a database of photographs for the pictures that look like the query picture. With the help of Feature Extraction Technique, number of required images can be extracted from the database based on the query image. Fuzzy Cmean, Kmean, Gray-Level Co-Occurrence Matrix, Local Binary Pattern, Principal Component Analysis and Scale Invariant Feature transform are used to extract features. The main motive of this work is to improve the efficiency of Content-Based Image Retrieval system by eliminating characteristics from query and database images. The Markov Chain Rule Feature Optimization approach is used to choose the informative features from the features. For similarity search, Hausdarff Distance along with gradient boosting machine learning techniques improves matching accuracy and retrieval speed. To compare to the state of the art, we have got 97.71% accuracy and they got 93.89% and 94.79%.

关键词： gradient boosting algorithm Content-Based Image Retrieval Fuzzy C mean Markov chain rule based optimization Hausdorff distance

来源：评论

学校读者我要写书评

暂无评论

AI Based Diagnosis of Pneumonia

引用

WIRELESS PERSONAL COMMUNICATIONS 2022年第4期126卷 3677-3692页

作者： Vidhya, B. Nikhil Madhav, M. Suresh Kumar, M. Kalanandini, S. Dr NGP Inst Technol Dept Biomed Engn Coimbatore Tamil Nadu India Sri Shakthi Inst Engn & Technol Dept Comp Sci Engn Coimbatore Tamil Nadu India

Pneumonia is a lung infection caused by bacteria, viruses and fungi. In this infection, the air sac (alveoli) of the lungs gets inflamed and breathing becomes difficult which causes mild to severe illness among people. They are diagnosed by performing chest X-ray, blood test, pulse oximetry. Pneumonia can also be identified using lung sounds that are recorded in the digital stethoscope. In this proposed work, a software is developed to diagnose pneumonia from the lung sound using gradient boosting algorithm. Lung sounds give enough symptoms for pneumonia identification. Lung sounds are recorded by doctors using Electronic Stethoscope. The recorded lung sounds are processed using audacity software. This software separates the required sound from unwanted noises. The healthy individual's audio files are labelled as 0 and the pneumonia patient's audio files are labelled as 1 for training the algorithm. During diagnosis study and the performance evaluation with various machine learning algorithms like support vector machine and k-nearest neighbours (KNN) algorithms, it was observed that the gradient boosting algorithm exhibits good identification property with 97 percent accuracy. This proposed method also reveals excellent diagnoses of pneumonia over other artificial intelligence and deep learning techniques. This method can also be used to predict Covid affected lungs sounds.

关键词： gradient boosting algorithm KNN Pneumonia Lungs Stethoscope

来源：评论

学校读者我要写书评

暂无评论

Cardiac Anomaly Detection using Embedded Attractors Reconstructed from Multichannel ECG 9

Cardiac Anomaly Detection using Embedded Attractors Reconstr...

引用

9th International Conference on Biomedical and Bioinformatics Engineering (ICBBE)

作者： Purkayastha, Basab Bijoy Hazarika, Anakhi Thomas, K. Amal Poddar, Soumyajit Indian Inst Technol Guwahati Gauhati India

ISBN: (纸本)9781450397223

The degree of complexity associated with the dynamics of the human heart is different for different categories of cardiac abnormalities. A quantitative measure of the complexities associated with cardiac dynamics can be obtained with a nonlinear study like a Multifractal analysis of the electrocardiogram signals. Here in this work, we have modeled the heart as a nonlinear dynamical system and obtained its phase space structure or embedded attractor reconstructed out of the ECG time series corresponding to four channels. Then, studied the multifractal behavior of the embedded attractor in order to quantify the degree of complexities associated with the dynamics of the heart. In particular, we have derived a few parameters out of the multifractal singularity spectrum and used them as a discriminative measure between various kinds of cardiac conditions. We have demonstrated a gradient boosting-based parametric classification model to discriminate between different kinds of arrhythmias and normal sinus rhythms. This work achieves considerably high accuracy in classifying different variants of cardiac disorders when trained with the parameters obtained from the multifractal singularity spectrum associated with the embedded attractor reconstructed out of the ECG time series.

关键词： Nonlinear dynamical system Multifractal singularity spectrum Cardiac dynamics Phase space structure Embedded attractor gradient boosting algorithm

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Insights into Social Media Behavior Using Predictive Modeling

引用

Procedia Computer Science 2025年 252卷 480-489页

作者： V. Selvakumar Nadipi Keerthana Reddy R. Sree Vardhini Tulasi Kunchala Rohit Kumar Department of Mathematics and Statistics Bhavan’s Vivekananda College of Science Humanities & Commerce Hyderabad Telangana India

This study proposes a statistical machine learning approach to predict social media usage across various demographic categories in India. The dataset comprises twenty-six features, including demographic attributes (age, gender, education, location), social media engagement metrics (number of followers, posts, time spent on platforms), and device-related information. It reflects real-world social media behavior on platforms such as WhatsApp, Facebook, and Instagram, capturing distinct patterns of weekday and weekend usage. Key variables such as time spent on each platform, the number of Instagram posts and followers, and overall social media usage were analyzed in detail. It is identified that significant predictors of user status categories through feature engineering, including Sabbatical, Self-Employed, Student, and Working Professional. Multiple regression models—Linear Regression, K-Nearest Neighbors, Decision Tree Regression, Random Forest Regression, gradient boosting, Naïve Bayes, and Support Vector Regression—were employed to assess their performance in predicting user status. Comparative analysis revealed that the gradient boosting algorithm outperformed other models with the highest accuracy. The machine learning workflow encompassed data pre-processing, feature engineering, model training, and evaluation, all implemented using Python. This study significantly advances the field by elucidating the key predictors of social media engagement and providing a thorough evaluation of the importance of features alongside a comparative analysis of predictive models.

关键词： Social Media Consumption Demographic Analysis gradient boosting algorithm Feature Engineering Social Media Engagement Metrics

来源：评论

学校读者我要写书评

暂无评论

Analysis of the severity of vehicle-bicycle crashes with data mining techniques

引用

JOURNAL OF SAFETY RESEARCH 2021年 76卷 218-227页

作者： Zhu, Siying Nanyang Technol Univ Sch Civil & Environm Engn Singapore Singapore

Introduction: Although cycling is increasingly being promoted for transportation, the safety concern of bicyclists is one of the major impediments to their adoption. A thorough investigation on the contributing factors to fatalities and injuries involving bicyclist. Method: This paper designs an integrated data mining framework to determine the significant factors that contribute to the severity of vehicle-bicycle crashes based on the crash dataset of Victorian, Australia (2013-2018). The framework integrates imbalanced data resampling, learning-based feature extraction with gradient boosting algorithm and marginal effect analysis. The top 10 significant predictors of the severity of vehicle-bicycle crashes are extracted, which gives an area under ROC curve (AUC) value of 0.8236 and computing time as 37.8 s. Results: The findings provide insights for understanding and developing countermeasures or policy initiatives to reduce severe vehicle-bicycle crashes. (C) 2020 National Safety Council and Elsevier Ltd. All rights reserved.

关键词： Safety Severity Vehicle-bicycle crashes Integrated data mining framework gradient boosting algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：