检索结果-内蒙古大学图书馆

Evaluation of the performance of classification algorithms for XFEL single-particle imaging data

IUCRJ 2019年第Pt 2期6卷 331-340页

作者： Shi, Yingchen Yin, Ke Tai, Xuecheng DeMirci, Hasan Hosseinizadeh, Ahmad Hogue, Brenda G. Li, Haoyuan Ourmazd, Abbas Schwander, Peter Vartanyants, Ivan A. Yoon, Chun Hong Aquila, Andrew Liu, Haiguang Tsinghua Univ Dept Engn Phys 30 Shuangqing Rd Beijing 100084 Peoples R China Beijing Computat Sci Res Ctr Complex Syst Div 8 E Xibeiwang Rd Beijing 100193 Peoples R China Huazhong Univ Sci & Technol Ctr Math Sci Wuhan 430074 Hubei Peoples R China Univ Bergen Dept Math POB 7800 N-5020 Bergen Norway SLAC Natl Accelerator Lab Biosci Div 2575 Sand Hill Rd Menlo Pk CA 94025 USA SLAC Natl Accelerator Lab Stanford PULSE Inst 2575 Sand Hill Rd Menlo Pk CA 94025 USA Univ Wisconsin Dept Phys Milwaukee WI 53201 USA Arizona State Univ Biodesign Inst Biodesign Ctr Immunotherapy Vaccines & Virotherap Tempe AZ 85287 USA SLAC Natl Accelerator Lab Linac Coherent Light Source 2575 Sand Hill Rd Menlo Pk CA 94025 USA Stanford Univ Dept Phys 450 Serra Mall Stanford CA 94305 USA Deutsch Elektronen Synchrotron DESY Notkestr 85 D-22607 Hamburg Germany Natl Res Nucl Univ MEPhI Moscow Engn Phys Inst Kashirskoe Shosse 31 Moscow 115409 Russia

Using X-ray free-electron lasers (XFELs), it is possible to determine three-dimensional structures of nanoscale particles using single-particle imaging methods. classification algorithms are needed to sort out the single-particle diffraction patterns from the large amount of XFEL experimental data. However, different methods often yield inconsistent results. This study compared the performance of three classification algorithms: convolutional neural network, graph cut and diffusion map manifold embedding methods. The identified single-particle diffraction data of the PR772 virus particles were assembled in the three-dimensional Fourier space for real-space model reconstruction. The comparison showed that these three classification methods lead to different datasets and subsequently result in different electron density maps of the reconstructed models. Interestingly, the common dataset selected by these three methods improved the quality of the merged diffraction volume, as well as the resolutions of the reconstructed maps.

关键词： X-ray free-electron lasers (XFELs) single-particle imaging classification algorithms electron-density map reconstruction

来源：评论

学校读者我要写书评

暂无评论

classification and Regression algorithms for Brain Computer Interfacing

Classification and Regression Algorithms for Brain Computer ...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： P. Yogendra Prasad M. Ramu Gangavaram Sree Varshini Dasari Keerthi Kaduru Jyothsna Chirangi K Neeraja Dept of CSSE Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India Dept of CSSE Annamacharya Institute of Technology & Sciences Tirupati India

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

The Brain-Computer Interface (BCI) stands as a groundbreaking technology, establishing a direct communication channel linking the human brain and external devices, enabling seamless interaction and control. This project focuses on the development of a BCI system utilizing machine learning techniques, specifically classification and regression algorithms. The brain-computer interface (BCI) facilitates a connection between the brain and the external world by interpreting physiological information generated during cognitive activities. Recent progress in neuroscience and machine learning has catalyzed transformative developments in BCI technology. This research study explores the implementation of advanced algorithms, specifically focusing on classification and regression techniques to enhance the performance and accuracy of BCI systems.

关键词： Machine learning algorithms Computational modeling Linear regression Brain modeling Brain-computer interfaces Physiology classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Early prediction of ICU readmissions using classification algorithms

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2020年第0期118卷 103636-000页

作者： Loreto, Melina Lisboa, Thiago Moreira, Viviane P. Univ Fed Rio Grande do Sul Porto Alegre RS Brazil Univ Fed Rio Grande do Sul Hosp Clin Porto Alegre Programa Posgrad Ciencias Pneumol Porto Alegre RS Brazil Univ LaSalle Canoas RS Brazil

Context: Determining which patients are ready for discharge from an Intensive Care Unit (ICU) presents a huge challenge, as ICU readmissions are associated with several negative outcomes such as increased mortality, length of stay, and cost compared to those patients who are not readmitted during their hospital stay. For these reasons, enhancing risk stratification in order to identify patients at high risk of clinical deterioration might benefit and improve the outcomes of critically ill hospitalized patients. Existing work on predicting ICU readmissions relies on information available at the time of discharge, however, in order to be more useful and to prevent complications, predictions need to be made earlier. Goals: In this work, we investigate the hypothesis that the basal characteristics and information collected at the time of the patient's admission can enable accurate predictions of ICU readmission. Materials and Methods: We analyzed an anonymized dataset of 11,805 adult patients from three ICUs in a Brazilian university hospital. After excluding 1879 patients who died during their first ICU admission, our final dataset contained 9,926 patients. Of these, 658 patients (6.6%) had been readmitted to the ICU. The original dataset had 185 attributes, including demographics, length of stay prior to ICU admission, comorbidities, severity indexes, interventions, organ support care during ICU stay and laboratory results. The problem of predicting ICU readmissions was modeled as a binary classification task. We tested eight classification algorithms (including Bayesian algorithms, decision trees, rule-based, and ensemble methods) over different sets of attributes and evaluated their results based on six metrics. Results: Predictions made solely based on the attributes collected at the admission are highly accurate. Their quality in terms of prediction is no different from predictions made using the complete set of attributes for our dataset and for a subset of attri

关键词： ICU readmission Machine learning classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of Malicious Software classification and Recognition algorithms Based on Graph Theory in Computer Networks

Design of Malicious Software Classification and Recognition ...

引用

Interactive Intelligent Systems and Techniques (IIST), International Conference on

作者： Yang Huang Dan Li Wuhan Maritime Communication Research Institute Wuhan China Faculty of Management Wuhan Donghu University Wuhan China

ISBN: (数字)9798350374421

ISBN: (纸本)9798350374438

The rapid growth of the Internet has greatly improved the efficiency and convenience of social operation, but also brought about increasingly serious computer network security problems. With the rapid growth of Internet, mobile network and Internet of Things technology, a large number of malicious codes and their variants pour into cyberspace every day, posing a serious threat to network security. In this context, this article proposes a malicious software classification and recognition algorithm based on graph theory and deep learning (DL). The algorithm first collects and analyzes malicious software samples to construct a graph structure that can reflect the behavioral characteristics of the software. These graph structures not only contain static features of software behavior, but also incorporate temporal information during dynamic execution, thus enabling a more comprehensive characterization of the behavior patterns of malicious software. Next, the algorithm utilizes the DL model to learn and process the constructed graph structure, improving classification accuracy and efficiency by extracting deep level features of the graph. The experimental results show that the algorithm proposed in this paper has high classification accuracy and recognition rate, and can maintain good detection performance in different network environments and malicious software samples.

关键词： Accuracy Heuristic algorithms Prevention and mitigation Software algorithms Network security Feature extraction Malware Graph theory classification algorithms Protection

来源：评论

学校读者我要写书评

暂无评论

Hybridization of classification ML algorithms to Predict Alzheimer Disease

Hybridization of Classification ML Algorithms to Predict Alz...

引用

Communication & Computing (WCONF), World Conference on

作者： Aakash Rampal Nitika Kapoor Ravinder Saini Computer Science and Engineering Department Chandigarh University Mohali India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

Alzheimer's Disease primarily known as AD is a neurodegenerative disorder disease which destroys the cognitive function of the brain and also decreases brain memory. This research paper explores the growth of a hybrid Machine Learning model for the classification of AD based on demographic and clinical features. The dataset utilized in this study comprises information from individuals diagnosed as either non-demented or demented, with features, including age, gender, and various cognitive test scores. The proposed model integrates multiple classifiers, including RF (Random Forest), LR (Logistic Regression), Support Vector Machines, KNN (K-Nearest Neighbours), and Decision Trees, using a soft voting ensemble approach. The effectiveness of the hybrid model was evaluated using classification reports and accuracy metrics. The results demonstrate promising performance, achieving an accuracy of 96.88% on the test dataset. Furthermore, the classification report illustrates high recall, F1 score, and precision for both non-demented as well as demented classes, indicating the robustness and generalization capability of the proposed approach in AD classification tasks.

关键词： Support vector machines Radio frequency Accuracy Scalability Predictive models Prediction algorithms Robustness classification algorithms Alzheimer's disease Random forests

来源：评论

学校读者我要写书评

暂无评论

Basic Tenets of classification algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review

引用

Journal of Data Analysis and Information Processing 2020年第4期8卷 341-357页

作者： Ernest Yeboah Boateng Joseph Otoo Daniel A. Abaye Department of Basic Sciences School of Basic and Biomedical Sciences University of Health and Allied Sciences Ho Ghana Department of Statistics and Actuarial Science University of Ghana Accra Ghana

In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.

关键词： classification algorithms Non-Parametric K-Nearest-Neighbor Neural Networks Random Forest Support Vector Machines

来源：评论

学校读者我要写书评

暂无评论

Influence of Boundary Extraction Operators on Boundary Shape classification algorithms Based on Complex Networks†

Influence of Boundary Extraction Operators on Boundary Shape...

引用

Chinese Automation Congress (CAC)

作者： Sheng-Qiao Bao Huibin Xu Hao Wang Jie Liu School of Mathematics and Computer Science Wuhan Textile University Wuhan School of Mathematics and Computer Science Wuhan Textile University Wuhan P R China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

As an important visual attribute for characterizing image objects, shape is always be investigated by researchers in pattern recognition and image analysis fields. It provides the most relevant information about objects for identification and classification tasks. By using the classical first-order and second-order operator algorithms, this brief paper extracts the shape boundaries of contour objects in several image sets. Then, generating explanatory variables based on the newly proposed complex network analysis method of the associated dynamic evolution boundaries network was carried out. Differences in the construction of high-dimensional feature interpretation vectors of boundary shapes based on network analysis are investigated. Our research shows that: the shape contour fingerprint vectors constructed by contour network construction algorithms based on different boundary extraction algorithms, can effectively represent the internal geometric figures of contour graphics features. The extracted digital feature vectors can be successfully used for graph classification tasks on the Etu10Silhouette database and Kimia216 database. There are some differences in CPU costs and classification accuracy. For the Etu10Silhouette database, it is recommended to use Sobel operator to extract the contours of the image shape, then use the algorithm mentioned in this paper to extract the fingerprint vector, combined with the KNN classification algorithm, one can get the best classification accuracy with almost the least time overhead. For the Kimia216 database, it is recommended to use the Laplacian operator to extract the contours of the image shape, with the boundary network fingerprint vector extraction algorithm, and combined with the LDA classification algorithm, one can obtain the best classification accuracy with almost the least time overhead. The comparative study on the classification algorithm based on deep learning method based on CNN also showed that, based on the g

关键词： Image edge detection Shape classification algorithms Complex networks Fingerprint recognition Feature extraction Low-pass filters

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Mobile Phone Products Reviews Using classification algorithms

Sentiment Analysis of Mobile Phone Products Reviews Using Cl...

引用

International Conference on Promising Electronic Technologies (ICPET)

作者： Mohammed A. M. Salem Ashraf Y. A. Maghari Faculty of Information Technology Islamic University of Gaza Gaza Palestine

ISBN: (数字)9780738111391

ISBN: (纸本)9781665403818

Sentiment analysis or opinion mining is a process of analyzing opinions and emotions to infer the tendencies and impressions shown on the analyzed data and classify them as positive or negative. Sentiment analysis is extremely important because it helps companies and institutions to measure the scope of their customer's satisfaction with a specific product based on reviews in a very fast way. As the manual analysis of these reviews is very difficult because of the increase in the numbers of reviews on products day after day. This paper proposes a sentiment analysis model to classify product reviews as positive, neutral and negative. It applies five popular machine learning classifiers namely: Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor and Maximum Entropy with the aim to come up with the most efficient classifier. The dataset used consists of 82,815 reviews about mobile phone products, collected from Kaggle website. In order to evaluate the five classifiers, we used recall, precision, F1-mesaure and accuracy to measure the performance of each algorithm. The results show that Maximum Entropy and Naïve Bayes outperforms the other classifiers in term of accuracy in all experiments. Decision Tree algorithm gave the lowest results across all experiments in terms of accuracy.

关键词： Sentiment analysis Support vector machine classification Entropy Mobile handsets classification algorithms Decision trees Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Prediction of protein – peptide binding residues using classification algorithms

Prediction of protein – peptide binding residues using clas...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Shima Shafiee Abdolhossein Fathi Fardin Abdali Mohammadi RAZI UNIVERSITY Kermanshah Iran

ISBN: (数字)9781728195742

ISBN: (纸本)9781728195759

Peptide-binding proteins prediction is important in understanding biological interaction, protein performance analysis, cellular processes, drug design, and even cancer prediction, so using experimental predictive methods, despite their operational capabilities, has limitations such as being costly and need to spend more time, differences between unrecognized protein structures and sequences, so design and development of computational systems for maintenance, optimal models for representing biological knowledge, management and the analysis of big biological data is so important that the authors used machine learning-based techniques such as Support Vector Machine (SVM),Random Forest (RF),Decision Tree (C4.5), Decision Tree (ID3),Gradient Boosting classifiers, which evaluated experimental results to optimize Support Vector Machine(SVM) classifier (Radial Basis Function kernel) with significant evaluation parameters such as accuracy(ACC) is equal to 0.7401 and 0.7599 for 10-fold cross validation and independent test set and also specificity (SPE) is equal to 0.7966 and 0.8088 for 10-fold cross validation and independent test set (respectively) by using various Structure-Based and Sequence-Based features.

关键词： Proteins Support vector machine classification Vegetation Predictive models Prediction algorithms classification algorithms Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Webspam Detection Using classification algorithms and Optimizing the Performance of Classifiers by Selecting the Features

Webspam Detection Using Classification Algorithms and Optimi...

引用

Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), International Conference on

作者： Kumar Parmar Anand Trivedi Pratik Chauhan Krishna Suchak Marwadi University Rajkot India

ISBN: (数字)9781728172132

ISBN: (纸本)9781728172149

Web spam is one among the main problems of search engines because it reduces the standard of the online page. Web spam also effects economically because spammers / attackers provide an oversized free ad data or websites on the search engines that results in a rise within the web traffic. There are certain ways to tell apart such spam pages and one among them is using classification techniques. Relative examination of web spam detection using classification algorithms like, Random Forest and LAD Tree, C4.5 and Naive bayes is presented here during this paper. Analyses were completed on highlight sets of all around acknowledged dataset WEB SPAM UK-2007 utilizing WEKA. When classification was refrained from feature selection some classifier were high on false positive rate and time taken to create model but when feature selection was applied to datasets results were optimized and Random Forest outperformed on all the datasets altogether parameters that were selected.

关键词： Feature extraction classification algorithms Standards Training Information filters Forestry Unsolicited e-mail

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：