Search or add a thesis

Advanced Search (Beta)
Home > The Classification of Multispectral and Statistical Texture Data Using Data Mining Techniques

The Classification of Multispectral and Statistical Texture Data Using Data Mining Techniques

Thesis Info

Access Option

External Link

Author

Qadri, Salman

Program

PhD

Institute

The Islamia University of Bahawalpur

City

Bahawalpur

Province

Punjab

Country

Pakistan

Thesis Completing Year

2017

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/13412/1/Final_Salman%20Qadri%20-%20PHD%20Thesis23-2-18.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727847307

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


The real-time information for land use/land cover (LU/LC) data is very important for resource management, future prediction, and crops growth assessment. Although conventionally LU/LC data is collected through field survey but remote sensing data collection has its own importance due to time, accuracy and transparency factors. During the last decade, advancement in spaceborne multispectral data has proven to be beneficial over airborne data for land monitoring due to their increased spectral resolution. The objective of this research is to compare and analyze the five types (Fertile, Green pasture, Desert-rangeland, Bare and Sutlej-river land) of LU/LC multispectral data (five bands) acquired by multispectral radiometer (MSR5) and digital photographic data acquired from high resolution 10.1 megapixel Nikon camera. All experimentation has been performed using MaZda software version 4.6 with WEKA data mining tool version 3.6.12 on Intel® Core i3 processor 2.4 gigahertz (GHz) with the the 64-bit operating system. This research is conducted at The Islamia University of Bahawalpur province Punjab (Pakistan), located at 29°23′44″N and 71°41′1″E. For photographic data, image pre-processing techniques are applied, i.e., grayscale conversion, enhanced the contrast and sharpening procedure. Extract the 229 statistical texture features of the LU/LC data of each 512×512 image size. Three feature selection techniques fisher (F), the probability of error plus average correlation coefficient (POE+ACC) and mutual information (MI) are combined together (F+PA+M) and extract thirty most discriminant features out of 229 features space of each photographic image. For feature reduction, non-linear discriminant analysis (NDA) for photographic data (texture data) and linear discriminant analysis (LDA) for remote sensing data (multispectral data) have shown better clustering as compared to principal component analysis (PCA) and raw data analysis (RDA). Finally, we have employed different data mining classifiers namely, Artificial Neural Network (ANN), Random Forest (RF), Naive Bayes (NB) and J48 for classification. It is observed that artificial neural network (ANN: n class) is applied for training and testing by cross-validation (80-20) on these texture and multispectral data. It showed comparative better 91.332% accuracy for texture dataset and 96.40% for multispectral (MSR5) dataset respectively among all the employed classifiers.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

مولوی فیروز الدین ڈسکوی کی ادبی خدمات

مولوی فیروز الدین ڈسکوی کی ادبی خدمات

مولوی فیروز الدین(۱۸۶۴ء۔۱۹۰۷ء) سیالکوٹ کے شہر ڈسکہ میں پیداہوئے۔ ان کی شاعری کے ساتھ ساتھ نثری ودینی  ادب میں بھی نمایاں خدمات  ہیں۔نثر میں وہ بہترین سوانح نگاروں میں شامل ہیں۔ سوانح نگاری کی صنف باقی اصنافِ نثر کے مقابلے میں اپنے ماحول اور اس کے رحجانات کی عکاسی زیادہ بہتر انداز میں کرتی ہے۔ اُردو میں سوانح نگاری کا آغاز عہد سر سید سے ہوتا ہے۔سرسید کا دور مذہبی مناظر ے اور بحث و مباحثے کا دور ہے لہٰذا اس دور کی سوانح عمریاں اپنے عہدکی عکاس ہیں۔اس دور کے مشہور سوانح نگاروں میں مرزا حیرت دہلوی، احمد حسن خان، عبدالحلیم شرر، منشی محمد الدین فوق، مولوی احمد دین ،احمد حسین الہٰ آباد، مولوی ذکاء اللہ ، سراجدین احمد ،نذیر احمد ،قاضی سلیمان ،عبدالرزاق کانپوری اور مولوی فیروز الدین ڈسکوی اہم ہیں۔
 مولوی فیروز الدین متعدد دینی و ادبی کتب  کے مصنف ہیں ۔فضائل اسلام فی ذکر خیر الانام المعروف سیرت النبیؐ یا تاریخ نبویؐ مولوی فیروز الدین کی پہلی باقاعدہ  تالیف ہے۔ اس کتاب کا پہلا ایڈیشن مفید عام پریس لاہور سے 1886ء میں شائع ہوا۔ ’’نماز اور اس کی حقیقت‘‘ان کی اہم تالیف ہے جو منشی فیض علی نے پنجاب پریس سیالکوٹ سے ۱۸۹۰ ء میں شائع کی۔ ’’تفسیر فیروزی پارہ اول‘‘1890ء میں سیالکوٹ مفید عام پریس سے شائع ہوئی۔ ’’تکذیب و ید‘‘1890ء میں پنجاب پریس سیالکوٹ سے شائع ہوئی۔ ’’تصدیق الا لہام‘‘  ان  کی مناظراتی  تصنیف ہے۔ جو 1890ء میں پنجاب پریس سیالکوٹ سے طبع ہوئی۔’’ دعائے گنج العرش و تعویز گنج العرش‘‘1891ء میں شائع ہوئی۔’’عشرہ کاملہ‘‘1891ء میں مفید عام پریس سیالکوٹ سے شائع ہو ئی۔’’سورت رحمن کی نادر تفسیر‘‘مولوی صاحب کی اہم  تصنیف ہے۔ جو 1892ء میں مطبع مفید عام پریس سیالکوٹ سے شائع ہوئی۔ ’’اسم اعظم ‘‘مولانا موصوف کی کتاب ہے جس میں...

Infant and Young Child Feeding Practices among Mothers in Lahore, Pakistan: A Cross-Sectional Study

Background: Inadequate child feeding practices lead to malnutrition, higher under-five mortality rates and adverse effects on quality of life. This study aimed to assess the breastfeeding and complementary feeding practices of mothers as well as the influence of various sociodemographic factors on them in local families of Lahore. Methods: This is a cross-sectional, descriptive study. It was conducted in CMH (Combined Military Hospital), Lahore in 2018. It comprises a sample of 203 mothers with children of at least two years of age, from various urban areas of Lahore. The subjects were selected on the basis of the inclusion criteria. Mothers with psychiatric illnesses and children with congenital anomalies were excluded from the study. Mothers were approached in the paediatric outpatient departments of four tertiary care hospitals of Lahore. Responses were recorded using a modified version of the Action Contre La Faim (ACF) questionnaire. Independent sample t-test and chi-square test were applied for analysis of the data. Results: Early initiation of breastfeeding within one hour from birth was observed in 83.3% children. Most children were administered colostrum (69.5%). The rate of exclusive breastfeeding for the first six months was 45.3%.  A child was being breastfed 8.21 ± 6.67 (mean ± SD) times a day. Maternal educational status, total number of adults in a household, and access to free healthcare were identified as important factors influencing the practice of breastfeeding. Porridge, khichdi, eggs, fruit and yoghurt were the most frequently used complementary foods. Conclusions: A high rate of an early start of breastfeeding and a low rate of exclusive breastfeeding for at least six months were predominant in our population. Administration of colostrum was observed in approximately two-thirds of the study participants. Education of the mother, type of the family system (nuclear or combined), and access to free healthcare strongly influence the breastfeeding practices.

Integration of Proteomic and Bioinformatics Analysis to Understand the Plants Responses to Humic Substances

Humic substances (HS) are heterogeneous organic compounds well known for stimulation of plant growth and development. The current study was designed to get insights about the physiological and metabolic processes induced by HS. Arabidopsis plants, grown hydroponically for 28 days on controlled conditions, were treated with HS at 1 mg C/L solution for 8 hours. iTRAQ (Isobaric Tag for Relative and Absolute Quantification) coupled LCMS (liquid chromatography–mass spectrometry) of HS vs control roots resulted in identification of 902 proteins species. 92 proteins showed significantly differential expression pattern (p-value ≤ 0.05) with a fold change of ≥1.3 for up regulated and ≤-1.3 for down-regulated proteins. Bioinformatic tools such as GeneCodis3, KEGG, STRING, IIS and Cytoscape were applied to comprehend the biological processes, molecular functions and pathways most targeted and the interaction networks amongst the identified proteins. Functional characterization and pathway analysis classified the identified proteins into different functional categories including response to inorganic substances, redox homeostasis, energy metabolism, cell trafficking and division. Many proteins related to protein synthesis, processing and translocation were also differentially expressed under HS application, for example, HSP70s, BiP2, PDIs and PABs. Three proteins, DPP6 N-terminal domain-like protein, patellin-2 and aspartyl protease family protein showed highest expression of 2.3 foldchange while germin-like protein subfamily 1 member 17 (GLP1-17) and cysteine proteinase RD19a revealed the lowest expression of -2.2 fold-change. The proteinprotein interaction (PPI) analysis generated a complex network consisting of seven significant modules. The main module contains 90 different proteins mainly associated with translation and biosynthetic pathways. Centrality analysis of the network identified topoisomerase II (Top II) as the most enriched hub/and bottleneck protein of the network. The enhancement of protein ubiquitination and stimulation of redox homeostasis and secondary metabolic pathways may explain the stimulation of signaling pathways and augmented growth of plants treated with humic substances. The xii DEPs identified in recent proteomic study may give some clues about the targets of HS and act as a podium for future study but more researches both at molecular and physiological levels should be done for find out of the HS metabolic target. The results of our in-silico promoter analysis of HS responsive promoter coding genes (HSRPGs) coincides with the proteomic study via linking the most enriched cis-acting regulatory (CREs) with stress, hormones, growth and developments. These results highlight the understanding of the underlying mechanisms involved in HS-plant interactions.