Surface Defect Inspection in Images Using Statistical Patches Fusion and Deeply Learned Features

Defect detection in images is a challenging task due to the existence of tiny and noisy patterns on surface images. To tackle this challenge, a defect detection approach is proposed in this paper using statistical data fusion. First, the proposed approach breaks a large image that contains multiple separate defects into smaller overlapping patches to detect the existence of defects in each patch, using the conventional convolutional neural network approach. Then, a statistical data fusion approach is proposed to maintain the spatial coherence of cracks in the image and aggregate the information extracted from overlapping patches to enhance the overall performance and robustness of the system. The proposed approach is evaluated using three benchmark datasets to demonstrate its superior performance in terms of both individual patch inspection and the whole image inspection.

Integrative pathway enrichment analysis of multivariate omics data

ABSTRACTMulti-omics datasets quantify complementary aspects of molecular biology and thus pose challenges to data interpretation and hypothesis generation. ActivePathways is an integrative method that discovers significantly enriched pathways across multiple omics datasets using a statistical data fusion approach, rationalizes contributing evidence and highlights associated genes. We demonstrate its utility by analyzing coding and non-coding mutations from 2,583 whole cancer genomes, revealing frequently mutated hallmark pathways and a long tail of known and putative cancer driver genes. We also studied prognostic molecular pathways in breast cancer subtypes by integrating genomic and transcriptomic features of tumors and tumor-adjacent cells and found significant associations with immune response processes and anti-apoptotic signaling pathways. ActivePathways is a versatile method that improves systems-level understanding of cellular organization in health and disease through integration of multiple molecular datasets and pathway annotations.

The Development of an Infrastructure Quality Index for Nigerian Metropolitan Areas Using Multivariate Geo-Statistical Data Fusion

Nigeria recently witnessed a decade of urban, economic, and social transformation. However, certain features of the Nigerian business environment act as constraints on economic growth. These characteristics also deter investment and exasperate business competitiveness. Inadequate infrastructure is identified as a major constraint to growth and competitiveness. This article summarises the technical development of a City Infrastructure Quality Index (CIQI) aimed at providing a relative measure of performance in urban infrastructure in Nigeria, focusing specifically on factors of production and resources for inclusive economic growth and development. The design of the CIQI adopts quality assurance principles undergirded by a five-stage systematic integration and calibration of spatial statistics derived from secondary data sources. The results have allowed for the piloting of a comparative framework for gauging good practice, excellence and adherence to recognisable standards in the provision of infrastructure across 37 Nigerian urban and metropolitan areas.