Search or add a thesis

Advanced Search (Beta)
Home > Hierarchical Multi-Label Document Classification Using Swarm Intelligence

Hierarchical Multi-Label Document Classification Using Swarm Intelligence

Thesis Info

Access Option

External Link

Author

Tariq Ali

Program

PhD

Institute

Abasyn University

City

Peshawar

Province

KPK

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/11383/1/TARIQ%20ALI%20Computer%20Science%202019.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727767279

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Document classification is one of the important fields of text mining. At present, category identification using taxonomy for scientific publications is a manual task. These taxonomies support authors which contain a large number of classes organized in the form of hierarchy that becomes quite difficult to choose a relevant category or categories for their work. Due to the amalgamation of research work in multiple domains, the problem becomes a multi-label classification (MLC). MLC is broadly solved using two different approaches (Problem Transformation and algorithm adaptation). In literature, a lot of single label classifiers are available to deal with single label dataset such as Support Vector Machine (SVM), K Nearest Neighbour (KNN), Naive Bayes and many more, these classifiers have low accuracy on text datasets due to the similarity measures and inappropriate selection of features. Similar approaches exist, which transform the multi label dataset into binary classification problems such as Binary Relevance (BR), Classifier Chain (CC), Probabilistic Classifier Chain (PCC) and many more. These algorithms also have a very low accuracy for text data. The issue which has not given proper importance is the order in which the binary classifiers are executed. Algorithm adaptation techniques such as decision trees, SVM, Multi-label K Nearest Neighbour (ML-KNN) and neural network also exist for MLC but have low accuracy due to similar weightage of features for all labels and have never been tested for a scientific publication datasets. The algorithm adaptation approaches have never been studied with feature weighting as all the features may not play the same role for each label in the MLC. We argue that all the approaches to deal with MLC for scientific documents suffer from low accuracy.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

خدا کا آخری پیغام لے کر آنے والے آپ ؐ


خدا کا آخری پیغام لے کر آنے والے آپؐ
جہاں میں رونقِ اسلام لے کر آنے والے آپؐ

جہاں پر نور اور ظلمت میں کچھ تفریق ہی نہ تھی
وہاں تفریقِ صبح و شام لے کر آنے والے آپؐ

منات و لات و عزّی کا تھا صدیوں سے وہاں قبضہ
خدا کے گھر خدا کا نام لے کر آنے والے آپؐ

بہارِ جاوداں دنیا کے ویرانوں سے پھوٹی ہے
جہانِ خار میں گلفام لے کر آنے والے آپؐ

سحابِ رحمتِ کُل ؛ کھل کے برسا دشت و صحرا پر
خدا کی رحمتیں ہر گام لے کر آنے والے آپؐ

کلامِ گُل فشاں سے باغِ اقرا میں بہار آئی
خزانہ لوح کا بے دام لے کر آنے والے آپؐ

سرِ کوثر ، لبِ عرفانؔ بھی سیراب ہو اے کاش
مئے توحید کا بھی جام لے کر آنے والے آپؐ

پاکستان میں بچوں پر جنسی تشدد اور فقہ السیرہ کی روشنی میں تدارک

Numerous crimes are being committed in present era. One of the most heinous crime amongst them is child abuse. Incidents of children who have been murdered after sexual abuse are rife in our nominal Islamic society. Moreover, videos and photos are also made during child abuse. Then these videos are posted on the social media. Both Muslim and non-Muslim communities are suffering from this brutal act i.e child abuse. In Pakistan, the reasons of increase in crime rates include psychological disorders, urge to fulfill one’s sexual desires, poverty, unemployment and detachment from religion. Such kind of abominable acts are becoming common in Pakistan day by day. According to Islamic jurisprudence rape is a punishable crime. Holy Prophet Muhammad (SAW) himself has punished the perpetrators for such acts of crime. Once in the era of Holy Prophet (SAW), a Jew crushed the head of a girl by placing it in between two stones. When Prophet (SAW) was informed about the incident, He (SAW) called upon the Jew who confessed his crime. Then Prophet (SAW) asked his companions to punish him by crushing his head with stones. It can be deduced from this narration that the culprits involved in such loathsome crimes should be punished publicly in order to wipe out this devilish act of crime from the society. The purpose of writing this research paper is to describe the reasons for the increase in rate of sexual abuse of children and its eradication in the light of Fiqh ul Seerah. This research paper followed descriptive and analytical methods

Synthesis, Charcterization and Antimicrobial Studies of Carbazoles

The work presented in this thesis involves the synthesis, characterization and antimicrobial studies of carbazoles. Carbazoles, both isolated and synthesized, are privileged heterocyclic compound that are dowered with exclusive properties as photoelectric material, florescent agent, dyes and have tremendous role in medicinal chemistry as antitumor, antimicrobial, antihistaminic, antineoplastic, antioxidative, anti-inflammatory, anti HIV agent etc. Carbazole nucleus has been stimulating the researchers to find new pathways for its synthesis and its novel derivatives because of their extensive biological properties especially their amazing pharmacological profile and their role as an emerging antibiotic. The current thesis work was designed based on the documented facts highlighting the incredible applications of carbazole derivatives in the field of chemistry. The work undertaken in this project was divided in two sections. The first portion of section I focuses on synthesis of some known potential carbazole derivatives (140-144 and 146-148) by adopting novel and feasible synthetic protocols affording comparably effective yield. While the second portion presents synthesis of some new carbazole derivatives with efficient synthetic protocols and novelty. Novel carbazoles (149-151) were synthesized and among these compounds 151 was found very reactive towards different functional which strongly assist its further role in design and development progress of carbazoles. 151 was further derivatized to successfully synthesize other novel carbazole derivatives such as 151-157, 163-164, 166-170. All the synthesized compounds were characterized from their spectral analysis i.e., UV, IR, 1 HNMR and mass spectrometry. Having succeeded in attempt to synthesize carbazoles, these compounds were evaluated and discussed for their antibacterial and anti-fungal activities in section II. For the purpose of primary screening by agar well diffusion method reference strains (ATCC) of three microbes Multi resistant staphylococcus aureus (gram positive bacteria), Salmonella typhi (gram negative bacteria) and Candida albicans (fungi) were used and then the minimum inhibitory concentration of each of the synthesized compounds to kill these pathogens was found by agar dilution assay using different clinical isolates of all three microbes. Synthesized carbazoles showed significant activities against the tested microbes ranging from 50mg/mL to 2μg/mL. Thesevii synthesized compounds were having potential to serve as important leads to fight against drug resistant microbes among biologically active carbazoles. O O N O N NH N HN N H NH O N H O 151 O 170 O O N N MeO N NH N H OMe 166 Some synthesized novel carbazoles