检索结果-内蒙古大学图书馆

Functional Knowledge Transfer for High-accuracy Prediction of Under-studied Biological Processes

PLOS COMPUTATIONAL BIOLOGY 2013年第3期9卷 1-14页

作者： Park, Christopher Y. Wong, Aaron K. Greene, Casey S. Rowland, Jessica Guan, Yuanfang Bongo, Lars A. Burdine, Rebecca D. Troyanskaya, Olga G. Princeton Univ Dept Comp Sci Princeton NJ 08544 USA Princeton Univ Lewis Sigler Inst Integrat Genom Princeton NJ 08544 USA Princeton Univ Dept Mol Biol Princeton NJ 08544 USA Univ Michigan Dept Computat Med & Bioinformat Ann Arbor MI 48109 USA Univ Tromso Dept Comp Sci Tromso Norway

A key challenge in genetics is identifying the functional roles of genes in pathways. Numerous functional genomics techniques (e.g. machine learning) that predict protein function have been developed to address this question. These methods generally build from existing annotations of genes to pathways and thus are often unable to identify additional genes participating in processes that are not already well studied. Many of these processes are well studied in some organism, but not necessarily in an investigator's organism of interest. Sequence-based search methods (e.g. BLAST) have been used to transfer such annotation information between organisms. We demonstrate that functional genomics can complement traditional sequence similarity to improve the transfer of gene annotations between organisms. Our method transfers annotations only when functionally appropriate as determined by genomic data and can be used with any prediction algorithm to combine transferred gene function knowledge with organism-specific high-throughput data to enable accurate function prediction. We show that diverse state-of-art machine learning algorithms leveraging functional knowledge transfer (FKT) dramatically improve their accuracy in predicting gene-pathway membership, particularly for processes with little experimental knowledge in an organism. We also show that our method compares favorably to annotation transfer by sequence similarity. Next, we deploy FKT with state-of-the-art SVM classifier to predict novel genes to 11,000 biological processes across six diverse organisms and expand the coverage of accurate function predictions to processes that are often ignored because of a dearth of annotated genes in an organism. Finally, we perform in vivo experimental investigation in Danio rerio and confirm the regulatory role of our top predicted novel gene, wnt5b, in leftward cell migration during heart development. FKT is immediately applicable to many bioinformatics techniques and will hel

关键词： Genome annotation Gene prediction machine learning Heart Gene ontologies machine learning algorithms Zebrafish Genetic networks

来源：评论

学校读者我要写书评

暂无评论

WhatsNextApp: LSTM-Based Next-App Prediction With App Usage Sequences

引用

IEEE ACCESS 2022年 10卷 18233-18247页

作者： Katsarou, Katerina Yu, Geunhye Beierle, Felix Tech Univ Berlin Serv Ctr Networking D-10587 Berlin Germany Univ Wurzburg Inst Clin Epidemiol & Biometry D-97080 Wurzburg Germany

Next app prediction can help enhance user interface design, pre-loading of apps, and network optimizations. Prior work has explored this topic, utilizing multiple different approaches but challenges like the user cold-start problem, data sparsity, and privacy concerns related to contextual data like location histories, persist. The user cold-start problem occurs when a user has recently registered to the smartphone app system and there is not enough information about his/her preferences and his/her history of smartphone usage. In this work, we try to address the above issues. We introduce WhatsNextApp, an approach based on LSTM (Long Short-Term Memory) networks using sequences of app usage logs. Our approach is inspired by Word Embeddings and treats sequences of app usage logs as sequences of words. We collect a real-life data set consisting of 975 Android users with over 22 million app usage events. We build a generic (user-independent) WhatsNextApp model and the evaluation with our data set shows that it outperforms related studies for existing users where we achieve a recall@8 (recall for the top 8 apps) of 92%. For the user cold-start problem with the 500 most frequent apps, we achieve a recall@8 of 82.7%.

关键词： Markov processes Data models Predictive models Computational modeling Training data Prediction algorithms Licenses Human-centered computing smartphone machine learning algorithms LSTM

来源：评论

学校读者我要写书评

暂无评论

Tracking Buggy Files: New Efficient Adaptive Bug Localization Algorithm

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2021年第7期48卷 2557-2569页

作者： Fejzer, Mikolaj Narebski, Jakub Przymus, Piotr Stencel, Krzysztof Nicolaus Copernicus Univ Torun Fac Math & Comp Sci PL-87100 Torun Poland Nicolaus Copernicus Univ Torun PL-87100 Torun Poland Univ Warsaw PL-00927 Warsaw Poland

Upon receiving a new bug report, developers need to find its cause in the source code. Bug localization can be helped by a tool that ranks all source files according to how likely they include the bug. This problem was thoroughly examined by numerous scientists. We introduce a novel adaptive bug localization algorithm. The concept behind it is based on new feature weighting approaches and an adaptive selection algorithm utilizing pointwise learn-to-rank method. The algorithm is evaluated on publicly available datasets, and is competitive in terms of accuracy and required computational resources compared to state-of-the-art. Additionally, to improve reproducibility we provide extended datasets that include computed features and partial steps, and we also provide the source code.

关键词： Computer bugs Location awareness Software History Software algorithms machine learning algorithms Training Bug reports software maintenance learning to rank

来源：评论

学校读者我要写书评

暂无评论

An Integrated Novel Framework for Coping Missing Values Imputation and Classification

引用

IEEE ACCESS 2022年 10卷 69373-69387页

作者： Jena, Monalisa Dehuri, Satchidananda Fakir Mohan Univ Dept Comp Sci Balasore 756019 Odisha India

This work presents an integrated framework for imputation of missing values and prediction of class label of unseen samples by using the best features of rule based inductive decision tree (DT) and Support Vector machine (SVM) classifier (DT-SVM). In this work, the decision tree is used for imputation of missing values of the datasets containing both categorical and numerical valued attributes. In addition, some of the other popular and simple missing value imputation techniques like drop, mean, median, mode, and k-nearest neighbor (kNN) are used for a comparative analysis. The imputed datasets are then classified using SVM. The performance of the proposed integrated novel framework DT-SVM has been compared with Drop-SVM, Mean-SVM, Median-SVM, Mode-SVM, and kNN-SVM and it is found that DT-SVM outperforms others. Further, a new variant of kNN named it as approximated kNN (A-kNN) has been proposed to overcome some of the shortcomings of canonical kNN while learning from a training set imputed by DT. Unlike canonical kNN, A-kNN does not scan the entire training set. Instead, it processes some of the representative instances from the training dataset to identify the nearest neighbor. The class centroid approach is adopted to find the representative instances of the training set. The effectiveness in term of accuracy as well as computational time of A-kNN is examined by comparing with canonical kNN. It is found that computational time of the proposed A-kNN is drastically reduced as compared to canonical kNN without compromising with the classification accuracy.

关键词： Decision trees Support vector machines Correlation Training Data mining machine learning algorithms Licenses Classification data mining decision tree kNN classifier missing values imputation SVM

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection System for Web-Based Attacks Using IBM Watson

引用

IEEE LATIN AMERICA TRANSACTIONS 2022年第2期20卷 191-197页

作者： da Silva, Ricardo C. C. Camargo, Marcos P. de O. Quessada, Matheus S. Lopes, Anderson C. Ernesto, Jacinto D. M. da Costa, Kelton A. P. Univ Estadual Paulista Sao Jose Do Rio Preto SP Brazil Univ Estadual Paulista Rio Claro SP Brazil Univ Estadual Paulista Bauru SP Brazil

The internet and web applications have been growing steadily and together with the increasing number of cyber attacks. These attacks are carried out through requests that are considered normal or abnormal (attack requests). Therefore, an intrusion attack can be considered as a classification problem. machine learning algorithms are used as a way to train models to classify these requests in order to increase the security of web systems. The data used to carry out the training and tests in this work come from the CSIC 2010 dataset. The J48, Naive Bayes, OneR, Random Forest and IBM Watson LGBM algorithms were tested. The metrics used were t-rate, precision, recall and f measure. The results showed that the algorithm used by the Watson tool (LGBM) was the one that did the best in all metrics when compared to the other algorithms in the literature.

关键词： Classification algorithms Passwords Measurement machine learning algorithms Intrusion detection IEEE transactions Electronic mail Web applications cyber attacks intrusion attack machine learning classification IBM Watson

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Method of Feature Extraction for Signatures Verification Using CNN and HOG a Multi-Classification Approach

引用

IEEE ACCESS 2023年 11卷 21873-21882页

作者： Alsuhimat, Fadi Mohammad Mohamad, Fatma Susilawati Univ Sultan Zainal Abidin Fac Informat & Comp Kuala Terengganu 21300 Malaysia

The offline signature verification system's feature extraction stage is regarded as crucial and has a significant impact on how well these systems perform because the quantity and calibration of the features that are extracted determine how well these systems can distinguish between authentic and fake signatures. In this study, we introduced a hybrid method for extracting features from signature images, wherein a Convolutional Neural Network (CNN) and Histogram of Oriented Gradients (HOG) were used, followed by the feature selection algorithm (Decision Trees) to identify the key features. Finally, the CNN and HOG methods were combined. Three classifiers were employed to evaluate the efficacy of the hybrid method (long short-term memory, support vector machine, and K-nearest Neighbor). The experimental findings indicated that our suggested model executed satisfactorily in terms of efficiency and predictive ability, with accuracies of (95.4%, 95.2%, and 92.7%) the UTSig dataset, and (93.7%, 94.1%, and 91.3%, respectively) with the CEDAR dataset. This accuracy is deemed to be of high significance, particularly given that we checked skilled forged signatures that are more difficult to recognize than other forms of forged signatures like (simple or opposite).

关键词： Feature extraction Convolutional neural networks Forgery Biometrics (access control) Deep learning machine learning algorithms Histograms Offline signature verification CNN HOG deep learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Algorithm Citation Functions in Scientific Literature

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2020年第10期32卷 1881-1896页

作者： Tuarob, Suppawong Kang, Sung Woo Wettayakorn, Poom Pornprasit, Chanatip Sachati, Tanakitti Hassan, Saeed-Ul Haddawy, Peter Mahidol Univ Fac Informat & Commun Technol Salaya Phutthamonthon 73170 Thailand Inha Univ Coll Engn Incheon 22212 South Korea Informat Technol Univ Lahore Pakistan

Computer sciences and related disciplines evolve around developing, evaluating, and applying algorithms. Typically, an algorithm is not developed from scratch, but uses and builds upon existing ones, which often are proposed and published in scholarly articles. The ability to capture this evolution relationship among these algorithms in scientific literature would not only allow us to understand how a particular algorithm is composed, but also shed light on large-scale analysis of algorithmic evolution through different temporal spans and thematic scales. We propose to capture such evolution relationship between two algorithms by investigating the knowledge represented in citation contexts, where authors explain how cited algorithms are used in their works. A set of heterogeneous ensemble machine-learning methods is proposed, where the combination of two base classifiers trained with heterogeneous feature types is used to automatically identify the algorithm usage relationship. The proposed heterogeneous ensemble methods achieve the best average F1 of 0.749 and 0.905 for fine-grained and binary algorithm citation function classification, respectively. The success of this study will allow us to generate a large-scale algorithm citation network from a collection of scholarly documents representing multiple time spans, venues, and fields of study. Such a network will be used as an instrument not only to answer critical questions in algorithm search, such as identifying the most influential and generalizable algorithms, but also to study the evolution of algorithmic development and trends over time.

关键词： Feature extraction machine learning algorithms Metadata Clustering algorithms Approximation algorithms machine learning Computer science Algorithm citation ensemble machine learning scholarly big data algorithmic evolution

来源：评论

学校读者我要写书评

暂无评论

HC-DTTSVM: A Network Intrusion Detection Method Based on Decision Tree Twin Support Vector machine and Hierarchical Clustering

引用

IEEE ACCESS 2023年 11卷 21404-21416页

作者： Zou, Li Luo, Xuemei Zhang, Yan Yang, Xiao Wang, Xiangwen Gansu Prov Meteorol Informat & Tech Support & Equi Gansu Meteorol Bur Lanzhou 730020 Peoples R China Northwest Normal Univ Coll Comp Sci & Engn Lanzhou 730070 Peoples R China

Network intrusion detection is an important technology in national cyberspace security strategy and has become a research hotspot in various cyberspace security issues in recent years. The development of effective and efficient intelligent network intrusion detection methods using advanced machine learning algorithms is of great importance for defending against various network intrusions in complex network environments. In this study, a network intrusion detection method based on decision tree twin support vector machine and hierarchical clustering, named HC-DTTWSVM, is proposed, which can effectively detect different categories of network intrusion. First, the hierarchical clustering algorithm is applied to construct the decision tree for network traffic data, where the bottom-up merging approach is used to maximize the separation of the upper nodes of the decision tree, which reduces the error accumulation in the construction of the decision tree. Then, twin support vector machines are embedded in the constructed decision tree to implement the network intrusion detection model, which can effectively detect the network intrusion category in a top-down manner. The detection performance of the proposed HC-DTTWSVM method is evaluated on NSL-KDD and UNSW-NB15 intrusion detection benchmark datasets. Experimental results show that HC-DTTWSVM can effectively detect different categories of network intrusion and achieves comparable detection performance compared to some of the recently proposed network intrusion detection methods.

关键词： Network intrusion detection Decision trees Security Support vector machines machine learning algorithms Cyberspace Training twin support vector machine hierarchical clustering decision tree

来源：评论

学校读者我要写书评

暂无评论

Pattern Reorder for Test Cost Reduction Through Improved SVMRANK Algorithm

引用

IEEE ACCESS 2020年 8卷 147965-147972页

作者： Song, Tai Liang, Huaguo Ni, Tianming Huang, Zhengfeng Lu, Yingchun Wan, Jinlei Yan, Aibin Hefei Univ Technol Sch Elect Sci & Appl Phys Hefei 230009 Peoples R China Anhui Polytech Univ Coll Elect Engn Wuhu 241000 Peoples R China Anhui Univ Sch Comp Sci & Technol Hefei 230601 Peoples R China

With the growing complexity of integrated circuits (IC), more and more test patterns are added to test set to test more defects, making the number of test pattern and individual test pattern length continues to increase as the size of IC gets larger, boosting test time and consequently test cost. To solve this problem, this paper proposes a kind of valid pattern identification method. The method uses machine learning to reorder the test pattern which can select the most effective patterns, to determine the optimal training set and test set first. Then, by means of the weighted SVMRANK algorithm to find the optimal pattern sequence. Experiment results demonstrate that the method only sacrifices 2% prediction accuracy in exchange for 3.89 times the time saving. The method aims at maximizing the accuracy of test, and minimizing the number of patterns. The proposed idea significantly improves the test time and test efficiency compared to conventional test flows. This is an innovative test cost reduction method with the growing complexity of IC.

关键词： Testing Integrated circuits Pressing Redundancy Complexity theory machine learning machine learning algorithms Adaptive test machine learning test reorder

来源：评论

学校读者我要写书评

暂无评论

A Unified Methodology to Predict Wi-Fi Network Usage in Smart Buildings

引用

IEEE ACCESS 2021年 9卷 11455-11469页

作者： Apostolo, Guilherme Henrique Bernardini, Flavia Magalhaes, Luiz C. Schara Muchaluat-Saade, Debora Christina MidiaCom Res Lab BR-24210240 Niteroi RJ Brazil Univ Fed Fluminense Inst Comp BR-24210310 Niteroi RJ Brazil Univ Fed Fluminense Telecommun Engn Dept BR-24210240 Niteroi RJ Brazil

People usually spend several hours per day inside buildings, and they require great amounts of energy and resources to operate. Although there are numerous studies about smart buildings, there is still a need for new intelligent techniques for efficient smart building management. This paper proposes the use of Wi-Fi network association information as a basis for the design of intelligent systems for smart buildings. We propose a unified experimental methodology to evaluate machine learning (ML) models on their capacity to accurately predict Wi-Fi access point demand for energy-efficient smart buildings. The evaluation involves the use of multiple classification and regression models using a variety of configurations and algorithms. We conducted an experimental analysis using our proposed methodology to determine which ML models provide the best performance results using data collected from a large scale Wi-Fi network located at Fluminense Federal University (UFF) over a period of 6 months. The proposed methodology enables the user to evaluate and to create ML models for energy efficient smart building management systems. We achieved 86.69% accuracy for occupancy prediction using classification techniques and RMSPE (Root Mean Squared Percentage Error) of 0.29 for occupancy count prediction using regression techniques.

关键词： Wireless fidelity Smart buildings machine learning algorithms machine learning Predictive models HVAC Wireless networks Access point occupancy prediction energy saving machine learning smart buildings Wi-Fi networks

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：