Search or add a thesis

Advanced Search (Beta)
Home > Novel Disease Named Entity Recognition Dner & Hybrid Relation Extraction Hre Frameworks for Biomedical Text

Novel Disease Named Entity Recognition Dner & Hybrid Relation Extraction Hre Frameworks for Biomedical Text

Thesis Info

Access Option

External Link

Author

Muzaffar, Abdul Wahab

Program

PhD

Institute

National University of Sciences & Technology

City

Islamabad

Province

Islamabad

Country

Pakistan

Thesis Completing Year

2017

Thesis Completion Status

Completed

Subject

Applied Sciences

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/8002/1/Abdul_Wahab_Muzaffar_Softwar_Engineering_2017_HSR_NUST_22.06.2017.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676726766581

Similar


Biomedical knowledge is usually presented in the form of unstructured segments; making the extraction of such information a complex task. Although, manual information extraction often produces the best results, it is harder to manage biomedical data extraction manually, because its data size is rising exponentially. Thus, there is a need for automatic tools and techniques for information extraction and knowledge discovery in biomedical text mining. Named entity recognition and relation extraction are focused areas of research in biomedical information extraction systems. Relation Extraction hinders the known relationship between Named Entities and in some way these are dependent on each other yet research also takes both these steps in an independent manner also. A lot of work has been done on biomedical named entity recognition focusing mostly on supervised and semi supervised solutions but very less attention work is done on unsupervised methods. Due to limited availability of annotated corpora the researchers now directed their efforts towards achievement of unsupervised named entity recognition systems. Named Entity Recognition from annotated corpora has been matured and there is very less margin for performance optimization. The challenge is still alive for the named entity recognition from unannotated corpora in all domains generally and for biological and biomedical domain specifically. Biomedical text exhibits relationships between different entities which are important for practitioners and researchers. Relation extraction is a significant area in biomedical knowledge, which has gained much importance in the last two decades. A lot of work has been done on biomedical relation extraction and identification focusing on two major areas: 1) rule based technique and 2) machine learning technique. In the last decade, focus has changed to hybrid approaches which have shown better results. This research presents an unsupervised named entity recognition framework along with a hybrid feature set for classification of relations between biomedical entities. Our Named Entity Recognition uses UMLS concepts and creates signatures that automate signature vectors. The vectorization of UMLS concepts ensures application of the framework in a generic way. Our framework differs with previous un-supervised methods in a way that we rely on UMLS for vector space creation instead of corpus statistics. The Relation Extraction approach uses bag of word feature, along with Natural Language Processing (NLP) to identify the noun and verb phrases and semantic features based on UMLS concepts. This hybrid feature set is a better representation of the relation extraction task. The main contribution in this hybrid features is the addition of semantic feature xi | P a g e set where verb phrases are ranked using Unified Medical Language System (UMLS), and a ranking algorithm is designed to get the most suitable concepts as features for the classifier. For Named Entity Recognition, we used Arizona Disease Corpus (AZDC) a gold standard corpus for this task. Our framework achieved accuracy of 72.56% which is competitive with supervised techniques on the same corpus. Our Relation Extraction approach has been validated on standard biomedical text corpus obtained from MEDLINE 2001, an accuracy of 96.19%, 97.45%, 96.49% and F-measure of 98.05%, 93.55%, 88.89% has been achieved for the cure, prevent and side effect relations respectively.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

45. Al-Jathiyah/The Kneeling Down

45. Al-Jathiyah/The Kneeling Down

I/We begin by the Blessed Name of Allah

The Immensely Merciful to all, The Infinitely Compassionate to everyone.

45:01
a. Ha. Mim.

45:02
a. The sending down of this Book - The Divine Qur’an - is from Allah,
b. The Almighty, The All-Wise.

45:03
a. Indeed, there are Wonders of Allah’s Creative Power throughout the celestial realm and the terrestrial world for all who are willing to believe.

45:04
a. And as they exist in your own creation and in the creation of a variety of other living creatures,
b. that HE scatters throughout the terrestrial world are Wonders for a people who are firm in
belief.

45:05
a. And so too in the alternation of the nighttime and the daytime,
b. and in the means of livelihood which Allah sends down from the sky clouds then HE enlivens the land after it had been made lifeless by prolonged exposures to drought,
c. and in the changing of direction, velocity, and temperature of the winds,
d. in all these are Wonders of Allah’s Creative Power for a people who understand.

45:06
a. These are the Messages of Allah,
b. that WE recite/convey to you in all truth.
c. So then in what other kind of a discourse will they ever believe if not in Allah and HIS Messages?

45:07
a. Woe to every impulsive liar and the sinful……

45:08
a. …. who hears Allah’s Messages in The Qur’an being recited to him,
b. and yet he persists in disbelief arrogantly as if he had never heard them.
c. So give him the good...

أثر أنظمة المعلومات التقنية في تعزيز فاعلية وكفاءة البيانات المحاسبية في البنوك الكويتية

هدفت الدراسة لمعرفة العوامل التقنية على فاعلية وكذل كفاءة البيانات المحاسبية في البنوك الكويتي وكيف تؤثر العوامل القانونية وكذلك الضوابط المهنية على فاعلية وكفاءة البيانات المحاسبية في البنوك الكويتية وكيف تؤثر العوامل الإدارية على فاعلية وكفاءة البيانات المحاسبية المحوسبة في البنوك الكويتية وكيف تؤثر العوامل الثقافية والاجتماعية على فاعلية وكفاءة البيانات المحاسبية في البنوك الكويتية وكيف تؤثر العوامل الاقتصادية على فاعلية وكفاءة البيانات المحاسبية في البنوك الكويتية، تكون مجتمع الدراسة من العاملين في الدوائر أو الأقسام التي تركز في أدائها لعملها على أنظمة البيانات المحاسبية في البنوك في الكويت وعددهم 120، اعتمدت الدراسة على المنهج الوصفي التحليلي، وأسفرت النتائج بأن البيانات المحاسبية المحوسبة ذات فاعلية عالية مما يعني أن المصارف التجارية في الكويت تعمل على زيادة الاهتمام بنظم المعلومات من منطلق دورها الأساسي في زيادة فاعلية وكفاءة تلك النظم، وأوصت الدراسة بالعمل على توسيع دائرة الاستفادة من البيانات المحاسبية المصرفية لتشمل كافة الإدارات والأقسام والأنظمة الفرعية والربط بين فروع المصارف وتمكين عملائها من تحقيق أقصى درجات الاستفادة منها

Islamic Studies for Engineering Program: A Topical Framework

Islamic Studies is taught at undergraduate level as compulsory core subject in engineering programs following the recommendations of national educational policies of Islamic Republic of Pakistan and Higher Education Commission (HEC) Pakistan, but the contents of the course are only the repetition of what student had studied earlier in their course of studies from beginning, also the topics selection do not match with the cognitive maturity of learners neither their professional needs. This exploratory study was to find the need for revision in the content of Islamic Studies course at undergraduate level in engineering discipline. A cross- sectional exploratory survey was conducted to discover the needs for the topics of interest for the subject of Islamic Studies at undergraduate engineering program. Needs in the current study are considered as gaps between the existing course contents and preferred contents or topics by the respondents. The data was collected through purposive sampling from 808 research respondents of engineering (from both Public and Private Higher Education Commission (HEC) recognized, and Pakistan Engineering Council (PEC) institutions of Karachi as well as general universities, total 12 universities). The sample comprised of five categories: students of engineering discipline (541), teachers of engineering discipline (170), Teachers of Islamic studies (experts) teaching in Engineering discipline,Teachers (experts) of Islamic Studies that are teaching to wide range of academic disciplines (32), and engineers who are working as professionals (65). The gender representation in the sample remained 66% (male), and 34% female respondents. A questionnaire using extent data analysis technique for structure and content was developed to collect data. Face and content validity of the tool were determined firstly through self-validation, secondly it was determined through expert validation; the questionnaire was presented to three experts of Islamic studies. Against 92 items 78 items received positive agreement. Two items showed negative agreement, and fourteen items showed no agreement. Percentage of overall agreement was 0.898549_ Kappa, suggestions of one of the three experts were incorporated. Thirdly a small scale pre-test was conducted to further ensure the validity of the tool. Informal pre-test was applied on a small, non-probability sample of45 Electrical Engineering undergraduate students of 7th semester, 09 Polymer & Petrochemical Engineeringundergraduate students’ of 7th semesters and 02 graduates of Mechanical Engineering of public sector University of Engineering and Technology. Responses of 12 teachers from Electrical and Polymer & Petrochemical departments (6 from each) were also recorded. Findings of pre-test related to structure, layout and vocabulary were used to make necessary changes before the pilot study. Questionnaire was also translated into national language Urdu.It went through Expert Validation with three Language Experts. Against 85 items the percentage of overall agreement remained Kappa Po: 0.882351. All suggestions were incorporated accordingly. The questionnaire was a blend of quantitative (closed questions with a prescribed range of answers), and qualitative (two open ended) questions. In piloting phase, data was collected from 65 (47 male (72%) and 18 females (28%) respondents of public sector university of Engineering and Technology and private sectorUniversity of Engineering and Technology, the two Major public and private sector Engineering Universities. Frequency of responses showed the content validity. Data for the main study was collected in two phases: at first stage the data was collected from 808 respondents during March 2013 to July 2013. Cumulative results of hypotheses testing disclosed that nine themes out of thirteen themes received unanimous agreement from all four groups of respondents. However, four themes i.e. theme three four, nine and twelve did not receive unanimous agreement of respondents although the percentages of agreement remains higher. In response of the qualitative query regarding “suggested topics if any other than surveyed items” various topics received from respondents which were divided and merged by the researcher in the 32 appropriate themes. From the categories; 93 out of 541 (17.19%) students,24 out of 170 (13.95%) teachers of engineering discipline,19 out of 32 (59.37%) teachers of Islamic Studies discipline, and 15 out of 65 (23.07%) engineering professionals proposed topics of repetitive nature. Either these were already in the survey form or proposed by respondents uniformly. Subjective analysis revealed that interest of society is influenced by the socio-political aspects of the country.124 out of 541 students, 62 out of 170 teachers of engineering discipline, and 15 out of 65 professionals commented positively in response to last opinionated question. After analyzing the data, it was presented to three subject experts for endorsement at second stage. Experts endorsed the final list of topics presented to them for comments. Each of them positively commented towards the research outcomes. Thirdly, data was also collected from 90 participants (professional Engineers) working in core fields outside Karachi. At the time of data collection (July, 2013), these Professionals were working with private sector Limited Company. This further validated the results. The finding of the study proves the notion of needs as gaps. Cumulative results indicates thatnine themes out of thirteen themes are taken as ‘needs of the research participants’ across categories while significant variation in agreement observed for the remaining four themes with above 75% agreement . Moreover, comments received from participants proved their interest towards subject of Islamic Studies as academic discipline.