Search or add a thesis

Advanced Search (Beta)
Home > Breast Cancer Detection Based on Hybrid Features Using Machine Learning Classification Techniques

Breast Cancer Detection Based on Hybrid Features Using Machine Learning Classification Techniques

Thesis Info

Access Option

External Link

Author

Ayaz Ahmed Hashmi

Institute

Virtual University of Pakistan

Institute Type

Public

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Software Engineering

Language

English

Link

http://vspace.vu.edu.pk/detail.aspx?id=337

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676721027384

Similar


The breast cancer in the women is most commonly diagnosed type of cancer. The mortality rate can be reduced if proper and early breast cancer treatment can be made. Masses and microcalcification contain very important diagnostic information in breast cancer. There is great variation in masses and micro-calcifications so, radiologists face difficulties in proper diagnosis of the breast cancer. Researchers in the past developed efficient systems based on computer aided diagnostic (CAD) systems. Moreover, relevant feature extraction plays a vital role in proper diagnostic and prognostic. Based on the diverse nature and variations in the breast cancer mammograms, we propose hybrid feature extraction approach including morphological, entropybased features, elliptic Fourier descriptors (EFDs), texture and scale invariant feature transform (SIFT). For improving the detection accuracy based on the extracted features, we applied machine learning classifiers including Support vector machine (SVM) alongwith its kernels such as Gaussian, radial base function (RBF), polynomial; Na?ve Bayes and Decision tree (DT). The validation was measured using 10-fold cross validation (CV) system. For a performance evaluation, we computed different metrics including specificity, sensitivity, false positive rate (FPR), negative predictive value (NPV), positive predictive value (PPV), and area under the receiver operating curve (AUC). Both combination and single feature are used as an input for classifiers. The results reveal that both single and combination of features provides higher detection results. Thus, the new feature extracting approach is more robust in early detection of breast cancer.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

مولانا مودودی ؒ کیلئےقیدوبند کی صعوبتیں

مولانا مودودی ؒ کو اپنے رفقاء سمیت اکتوبر ۱۹۴۸ء میں گرفتارکیا گیا۔آپ کونہ صرف گرفتار کیا گیا بلکہ آپ کی جماعت کے اخبارات " کوثر" ،" جہاں نو" اورروزنامہ " تسنیم " بھی بند کردیےگئے۔ اس وقت حکمران طبقہ پر استعماری غلبہ تھا ۔جبکہ مولانا مودودیؒ کاکہنا تھاکہ پاکستان کے قیام کااصل مقصد اسلامی نظام کاقیام ہے ۔ آپ پرجہادکشمیر کے مخالف ہونے کاالزام لگایا گیا ۔اپنی پہلی قید وبند کی صعوبت کاذکر مولانا نے اس طرح کیاہے :

"میں نے اپنی پہلی نظربندی میں لکھنے پڑھنے کا خاصا کام کیا ۔مسئلہ ملکیت زمین مرتب کی ۔ تفہیم کا مقدمہ لکھا۔حدیث کی کتاب ابوداؤد کاانڈکس تیارکیا۔کتاب" سود" اور"اسلام اورجدید معاشی نظریات" بھی وہیں مکمل کیں ۔ خداکاشکر ہے کہ میراوہاں ایک دن بھی ضائع نہیں ہوا " ۔[[1]]

مولانا مودودی ؒ کی سزا پر پوری دنیا سراپا احتجاج تھی۔لیکن مولانا مودودی ؒ فوجی عدالت کے فیصلے سے بالکل بھی نہ گھبرائے۔ مولانا ؒ نے اپنے ساتھیوں کو سزا کے خلاف رحم کی اپیل نہ کرنے دی۔مولانا نے فرمایا:

" نہیں ہرگز نہیں ! میں نہیں چاہتا کہ میری طرف سے یامیرے خاندان کے کسی فرد کی طرف سے یاخود جماعت کی طرف سے کوئی رحم کی درخواست پیش کی جائے" [[1]]

مولانا نے اپنے بیٹے عمر فاروق کو تسلی دی اور گھبرانے سے منع فرمایا۔ مولانا نے سزا کے خلاف کوئی اپیل دائر نہیں کی مولاناؒ کا کہنا تھا کہ اگر میں ظالم حکمرانوں کے سامنے دب گیا تو پھر ملک سے انصاف ختم ہوجائے گا ۔

آخر کار حکومت نے خود ہی سزائے موت کو ۱۴ سال کی قید میں تبدیل کردیا۔ جیل سے رہائی کے بعد مولانا مودودی ؒ نے دین کے کام کو آگے بڑھایا ۔

STUDENT'S READINESS TO CARRY OUT FACE-TO-FACE LEARNING AT KENDARI VOCATIONAL HIGH SCHOOL

The slowing spread of Covid-19 infections has brought positive changes in the education sector. The issue of implementing limited face to face learning begins to excite students in gaining knowledge. Online learning effects for approximately two years was relatively difficult to keep students away from themselves. This study time to determine how the level of student learning readiness in facing offline learning. This was quantitative research with a survey type. The population were State vocatoonal high school 2 Kendari students, totaling 558 students. The sample was drawn randomly with a magnitude estimated using the Slovin formula at a significance of 5% so that the total sample size was 233 students. Data were collected by learning readiness scale. Data were analyzed descriptively and comparative statistics. The results showed that the learning readiness of State vocatoonal high school Negeri 2 Kendari students was in the high category and female students had a higher level of learning readiness than male students.

Genetic History of Pakistani Cattle Breeds Using High Density Snp Array Genotyping

Human domesticated cattle genetic resources nearly 8,000 to 10,000 years ago. ). A total 1,019 cattle breed is present around the world. This study gives a detailed assessment of genetic diversity in Pakistani cattle breeds from different agro ecological zones and genotyped for 500,939 autosomal single nucleotide polymorphism (SNP). Mean minor allele frequency (MAF), which were 0.23, 0.20, 0.22, 0.22, 0.20, 0.18, 0.20, 0.22, 0.21 and 0.18 for Achi, Bhagnari, Cholistani, Dhanni, Dajal, Kankrej, Lohani, Red Sindi, Sahiwal and Tharparkar cattle, respectively. Across all breeds 64% SNP markers were observed polymorphic (MAF > 0.05) within breeds and remaining 36% were considered as monomorphic markers. Experiment 2 discussed the two different approaches, selective sweep and population differentiation index (FST), to identify selection signatures between and within breeds in Pakistan. First method was used to detect haplotypes fixation on genomic regions within breeds. Second, FST was used to identify genomic regions having different allele frequencies between these breeds. The melanocortin 1 receptor (MCIR) gene was found on BTA 18 at 147, 573, 32-147, 590, 82 bp for Lohanni breed. This gene was previously associated with an adaptive trait in Bos indicus. A number of putative genes linked with productive traits (LAP3, CAPN3, CYP19, SAR1B, and RPS6KA2), reproductive traits (PIK3CA, SPERT, and IGF1R), nervous system (KIT, FGF5, ASIP and HSPB9) and immune response (IL2, IL4, SERPINA3-8 and BOLA3) were identified as being under selection. Experiment 3 examined population genetic properties of copy number variations (CNV). High resolution results of CNV revealed genome wide admixture proportion and agro-ecological variation pattern within and among these breeds. We detected 53 CNV regions and these regions overlapped with genes involved in traits related to immune response, body size and parasitic resistance. This could provide possible genetic relationship among these Pakistani indigenous breeds and other cattle breeds of the world. It is important to mention that small sample size of this study may not be truly representative of the whole population and could lead erroneous conclusion about the entire population. This study might be used properly and conserved in order to manage with unpredictable future environments. Moreover, a genomic understanding of natural selection how and where has shaped the genetic pattern of these breeds in Pakistan was exposed by loci identified that are important to the development of these breeds. The results of this study make a foundation for more suitable application of selective breeding and conservation approaches of Pakistani cattle breeds.