ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer

หน่วยงาน Universiti Sains Malaysia, Malaysia

รายละเอียด

ชื่อเรื่อง : Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer
นักวิจัย : Abdullah, Rosni , Venkat, Ibrahim , Mohamed Yusoff, Syarifah Adilah
คำค้น : QA75.5-76.95 Electronic computers. Computer science
หน่วยงาน : Universiti Sains Malaysia, Malaysia
ผู้ร่วมงาน : -
ปีพิมพ์ : 2558
อ้างอิง : http://eprints.usm.my/31048/1/Bio%2DInspired_Optimization_Method_for_feature_selection_of_Mass_Spectrometry_Analysis_in_Biomarker_Identification.pdf , Abdullah, Rosni and Venkat, Ibrahim and Mohamed Yusoff, Syarifah Adilah (2015) Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer. Project Report. Universiti Sains Malaysia.
ที่มา : -
ความเชี่ยวชาญ : -
ความสัมพันธ์ : http://eprints.usm.my/31048/
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

Mass spectrometry technique is gradually gaining momentum among the recent techniques deployed by several analytical research labs, especially to study biological or chemical properties of complex structures such as protein sequences. This advancement also embarks the discovery of biomarkers through accessible body fluid such as serum, saliva and urine. Due to high-throughput data, a given molecule species can give rise to a seriesiof inter-related peaks in a mass spectrum. A sample data can result in a very complex spectrum with many interrelate~ and overlapping peaks. This scenario will degrade the potential features to be extracted from the spectrum. The ~pectrum also suffers from high dimensionality data relative to small samples size. Constructing a good classification model to predict biomarkers from disease and normal cases requires well-discriminated and independent potential features. This study focused on feature selection method inspired by bio-inspired algorithm for biomarker discovery process. Generally, the proposed feature selection was developed using wrapper techniques to search for parsimonious Ifeatures through a learning model. A sophisticated computational technique that mimics survival and natural proces~ing known as Artificial Bee Colony (ABC) and Differential Evolution (DE) were hybridised as deABC and further integrated with linear SVM classifier for this biomarker discovery analysis. The proposed method was successfully tested with real-world mass spectrometry datasets such as ovarian, liver and TOX dataset to evaluate the discrimination power, accuracy, sensitivity and also specificity. Future research should consider to integrate the proposed deABC with othet type of classification to validate robustness of the algorithm. Further, this method can be extended to other domains of s~udy instead of mass spectrometry.

บรรณานุกรม :
Abdullah, Rosni , Venkat, Ibrahim , Mohamed Yusoff, Syarifah Adilah . (2558). Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer.
    กรุงเทพมหานคร : Universiti Sains Malaysia, Malaysia.
Abdullah, Rosni , Venkat, Ibrahim , Mohamed Yusoff, Syarifah Adilah . 2558. "Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer".
    กรุงเทพมหานคร : Universiti Sains Malaysia, Malaysia.
Abdullah, Rosni , Venkat, Ibrahim , Mohamed Yusoff, Syarifah Adilah . "Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer."
    กรุงเทพมหานคร : Universiti Sains Malaysia, Malaysia, 2558. Print.
Abdullah, Rosni , Venkat, Ibrahim , Mohamed Yusoff, Syarifah Adilah . Bio-Inspired Optimization Method For Feature Selection Of Mass Spectrometry Analysis In Biomarker Identification Of Ovarian Cancer. กรุงเทพมหานคร : Universiti Sains Malaysia, Malaysia; 2558.