1,318 Hits in 5.9 sec


Tao Wang, Wenqing Chen, Bailing Wang
2014 International Journal on Smart Sensing and Intelligent Systems  
learning method for image classification, which is based on the concept of visual phrases combined with Multiple Instance Learning.  ...  Considering the traditional classification method based on Bag of Words model is vulnerable to the background, block and scalar variance of an image, we propose in this article a multiple visual words  ...  In addition, visual phrases contain the relations of visual words extracted from images, so they are more discriminative and descriptive than visual words.  ... 
doi:10.21307/ijssis-2017-716 fatcat:mfmxeyf55bewtjkvpeoh5hlo7u

Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features

A. Nikfarjam, A. Sarker, K. O'Connor, R. Ginn, G. Gonzalez
2015 JAMIA Journal of the American Medical Informatics Association  
However, the language in social media is highly informal, and userexpressed medical concepts are often nontechnical, descriptive, and challenging to extract.  ...  Our objective is to design a machine learning-based approach to extract mentions of adverse drug reactions (ADRs) from highly informal text in social media.  ...  Smith for supervising the annotation process and Pranoti Pimpalkhute, Swetha Jayaraman, and Tejaswi Upadhyaya for their technical support.  ... 
doi:10.1093/jamia/ocu041 pmid:25755127 pmcid:PMC4457113 fatcat:wrekcivgkrf3rbbgl5mdym2c4y

Constraint-based Ontology Induction from Online Customer Reviews

Thomas Lee
2006 Group Decision and Negotiation  
We present an unsupervised, domain-independent technique for inducing a product-specific ontology of product features based upon online customer reviews.  ...  ABSTRACT: We present an unsupervised, domain independent technique for inducing a product-specific ontology of product features based upon on-line customer reviews.  ...  Using the metaphor of learning relational schemas, each concept is a relation; the corresponding phrases, extracted from the text of customer reviews or product descriptions, are tuples of the relation  ... 
doi:10.1007/s10726-006-9065-3 fatcat:kmj7iop2endcxh653wsvumsci4

Automated identification of sensitive data from implicit user specification

Ziqi Yang, Zhenkai Liang
2018 Cybersecurity  
The sensitivity of information is dependent on the context of application and user preference. Protecting sensitive data in the cloud era requires identifying them in the first place.  ...  S3 achieves an average precision of 89.2%, and average recall 95.8% in identifying sensitive data.  ...  Availability of data and material The dataset supporting the conclusions of this article is available in the Dropbox repository  ... 
doi:10.1186/s42400-018-0011-x fatcat:46zzkshfprbufpeoj77ugllpga

Unsupervised Learning for Spam Email Filtering

Sambhangi Chandrahasa
2020 International Journal of Advanced Trends in Computer Science and Engineering  
A circa-processing period that mostly includes extraction of components and elimination of features in the sector of machine learning consequently plays a significant role in expediting or boosting processing  ...  The key benefit with accordance to the envisaged feature representation has always been its rigidity, that mostly empowers data types like those of Random Forest, Assistance Vector Machines, and constraint  ...  Research operation has affirmed the potential outcome of upgrading the email archiving concept of perspective-based categorisation model.  ... 
doi:10.30534/ijatcse/2020/107922020 fatcat:equx2pjprre7lmydoggmmr2o3u

COVID-19 Candidate Treatments, a Data Analytics Approach

Gerry Wolfe, Ashraf Elnashar, Will Schreiber, Izzat Alsmadi
2020 2020 Fourth International Conference on Multimedia Computing, Networking and Applications (MCNA)  
Our focus in this research is in evaluating a repository of research papers to extract knowledge related to COVID-19 and possible treatments.  ...  The data is broken up into four categories: (1) Mobility and Social Distancing, (2) COVID and Health, (3) Economic Impact, and (4) Vulnerable Population.  ...  It helped us focus directly on the most important features. 1) Feature Selection, Reduction, and Extraction We spent a significant amount of time in clustering, unsupervised models, supervised models  ... 
doi:10.1109/mcna50957.2020.9264290 fatcat:sctrrfab7bgdvkbs2yifecjn2y

An Automated, End-to-End Framework for Modeling Attacks From Vulnerability Descriptions [article]

Hodaya Binyamini, Ron Bitton, Masaki Inokuchi, Tomohiko Yagyu, Yuval Elovici, Asaf Shabtai
2020 arXiv   pre-print
Given a description of a security vulnerability, the proposed framework first extracts the relevant attack entities required to model the attack, completes missing information on the vulnerability, and  ...  We present a novel, end-to-end, automated framework for modeling new attack techniques from textual description of a security vulnerability.  ...  In contrast, our dataset, which is based on vulnerability descriptions present in the NVD, consists of 5.8M words.  ... 
arXiv:2008.04377v1 fatcat:7cb2hfh4anbx3lhgm7t257ojra

An Integrated Digital Library Server with OAI and Self-Organizing Capabilities [chapter]

Hyunki Kim, Chee-Yoong Choo, Su-Shing Chen
2003 Lecture Notes in Computer Science  
In this paper we propose an integrated DL system with OAI and self-organizing capabilities.  ...  The system provides two valueadded services, cross-archive searching and interactive concept browsing services, for organizing, exploring, and searching a collection of harvested metadata to satisfy users  ...  In the noun phrase extraction phase, we first took the description, subject, and title elements from the database and tokenized these elements based on the Penn Treebank tokenization scheme to detect sentence  ... 
doi:10.1007/978-3-540-45175-4_16 fatcat:p2h5vktgszcbhkk2zspm7f3m3y

Prob2Vec: Mathematical Semantic Embedding for Problem Retrieval in Adaptive Tutoring [article]

Du Su, Ali Yekkehkhany, Yi Lu, Wenmiao Lu
2020 arXiv   pre-print
In addition, the sub-problem of concept labeling with imbalanced training data set is interesting in its own right.  ...  There are two challenges: First, like sentences, problems helpful to tutoring are never exactly the same in terms of the underlying concepts.  ...  We choose rule-based concept extractor for the abstraction step over any supervised/unsupervised classification methods for concept extraction because of two main reasons.  ... 
arXiv:2003.10838v1 fatcat:537dcmnle5fv7bofryfzcniodq

What are the attackers doing now? Automating cyber threat intelligence extraction from text on pace with the changing threat landscape: A survey [article]

Md Rayhanur Rahman, Rezvan Mahdavi-Hezaveh, Laurie Williams
2021 arXiv   pre-print
We propose a CTI extraction pipeline abstracted from these studies. We identify the data sources, techniques, and CTI sharing formats utilized in the context of the proposed pipeline.  ...  Our work finds ten types of extraction purposes, such as extraction indicators of compromise extraction, TTPs (tactics, techniques, procedures of attack), and cybersecurity keywords.  ...  In 33 , 34 , Mulwad et al., and Joshi et al. extracted the vulnerability and related keywords from vulnerability description in NVD, extracted their underlying concepts using ontology and online resource  ... 
arXiv:2109.06808v1 fatcat:tgb7swrslnhppbpg24cyub2sr4

Security Bug Report Usage for Software Vulnerability Research: A Systematic Mapping Study

Farzana Ahamed Bhuiyan, Md Bulbul Sharif, Akond Rahman
2021 IEEE Access  
Context: Security bug reports are reports from bug tracking systems that include descriptions and resolutions of security vulnerabilities that occur in software projects.  ...  Conclusion: Findings from our mapping study can be leveraged to identify research opportunities in the domains of software vulnerability classification and automated vulnerability repair techniques.  ...  For example, with lemmatization 'error', 'inaccurate', and 'false' is converted to 'error'. − Keyphrase extraction: Keyphrase extraction is a technique that identifies phrases that occur in a document  ... 
doi:10.1109/access.2021.3058067 fatcat:7sdyi3zjvjb6xcqf3ed3why4eu

A Survey on Opinion Reason Mining and Interpreting Sentiment Variations

Fuad Alattar, Khaled Shaalan
2021 IEEE Access  
As a result, there has been a lot of focus on Sentiment Analysis.  ...  Moreover, some studies took one step ahead by analyzing subjective texts further to understand possible motives behind extracted sentiments.  ...  [22] enhanced the Relation-Based method by using a phrase-dependency-parser to extract aspects which are noun-phrases or verb-phrases. Qui et al.  ... 
doi:10.1109/access.2021.3063921 fatcat:i32uuh5dnngy3bsmiuqk26tvim

SoK: Applying Machine Learning in Security - A Survey [article]

Heju Jiang, Jasvir Nagra, Parvez Ahammad
2016 arXiv   pre-print
Based on our survey, we also suggest a point of view that treats security as a game theory problem instead of a batch-trained ML problem.  ...  In this paper, we systematically study the methods, algorithms, and system designs in academic publications from 2008-2015 that applied ML in security domains. 98 percent of the surveyed papers appeared  ...  We survey cutting-edge research on applied ML in security, and provide a high-level overview taxonomy of ML paradigms and security domains. 2.  ... 
arXiv:1611.03186v1 fatcat:hfvc5hhu7ze77lrnjufslcg6gm

Knowledge mining of unstructured information: application to cyber-domain [article]

Tuomas Takko, Kunal Bhattacharya, Martti Lehto, Pertti Jalasvirta, Aapo Cederberg, Kimmo Kaski
2021 arXiv   pre-print
Cyber intelligence is widely and abundantly available in numerous open online sources with reports on vulnerabilities and incidents.  ...  In this paper we present and implement a novel knowledge graph and knowledge mining framework for extracting relevant information from free-form text about incidents in the cyber domain.  ...  TT acknowledges funding from the Vilho, Yrjö and Kalle Väisälä Foundation of the Finnish Academy of Science and Letters.  ... 
arXiv:2109.03848v2 fatcat:x3yac67kbbe3zefivjphiyt34e

Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph

Jingkang Yang, Weirong Chen, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang
2020 Proceedings of the 28th ACM International Conference on Multimedia  
In this paper, we propose an automatic label corrector VSGraph-LC based on the visual-semantic graph.  ...  VSGraph-LC starts from anchor selection referring to the semantic similarity between metadata and correct label concepts, and then propagates correct labels from anchors on a visual graph using graph neural  ...  ACKNOWLEDGMENTS The work described in this paper was partially supported by Innovation and Technology Commission of the Hong Kong Special Administrative Region, China (Enterprise Support Scheme under the  ... 
doi:10.1145/3394171.3413952 dblp:conf/mm/YangCFYZZ20 fatcat:iithcxh27rbcvov4m7uqa4hv4u
« Previous Showing results 1 — 15 out of 1,318 results