No abstract

No abstract

No abstract

Occurrence of high imbalance in real-world domains is a direct result of rarity of interesting events, which results in skewed datasets. Without dataset rebalancing, the learning algorithm will encounter extremely low minority class samples therefore it gets biased towards the majority class in the classification tasks. Hence properly handling the imbalanced dataset is a crucial issue in the pattern recognition domain. We have employed bootstrapping by simultaneous oversampling of the minority class and undersampling of the majority class to build the ensemble of classifiers. Oversampling is partially guided by the extracted hidden patterns from minority class, which prevents its over-generalization and amplify subtle vital patterns. The proposed framework is evaluated on four highly imbalanced datasets with employing a series of classifiers like, support vector machine, logistic regression, nearest neighbor and Gaussian process classifier. Experimental results showed that the pattern classification performance for various tasks improves after rebalancing datasets using the proposed framework.

Summary Commercial high‐resolution optical microscopes are essential for microscopy imaging; however, they are expensive and bulky, which limits their use in point‐of‐care devices, resource‐limited areas, and real‐time imaging of a sample in a large apparatus. In this study, we report a novel compact (10 cm × 5 cm × 5 cm, without the light source) lightweight (∼0.5 kg) submicron‐resolution inverted optical microscope at low cost (∼$ 300). Our technique utilises the proximity of the image sensor to a commercial microscope objective lens for compactness of the microscope. The use of an image sensor with a small pixel size helps to reduce the information loss, which provides high‐resolution images. Moreover, our technique offers a freedom to tailor the design of microscope according to the required resolution, cost, and portability for specific applications, which makes it a suitable candidate for affordable point‐of‐care devices. Images of several micron‐to‐submicron scale patterns and spherical beads are acquired to observe the resolution and quality of the images obtained using our microscope. In addition, we demonstrate the applications of our microscope in various fields such as recording of high‐speed water microdroplet formation inside a microfluidic device, high‐resolution live cell imaging inside an incubator, and real‐time imaging of crack propagation in a sample under stretching by a material testing system (MTS). Therefore, this portable and inexpensive microscope provides the essential functionalities of a bulky expensive high‐performance microscope at a lower cost. Lay Description Microscope is an essential tool in research allowing for observation of microsized objects and life forms. Contemporary commercial high‐resolution microscopes have long optical paths involving series of lenses and filters. Although this configuration precisely corrects for optical distortions and produces clear images, it makes modern microscopes very costly and bulky, restricting their usage to low‐funded research laboratories and at remote places. We have developed a simple digital microscope with high‐resolution but with much smaller size and lighter in weight at low cost by removing the long optical terrain. Our microscope consists of a commercial microscope objective lens for magnification and semiconductor image sensor with small pixels placed right after the lens, both of which are affordable and easily available. The small pixel size helps to translate the magnified analogue sample image to high‐resolution digital image. In our paper, we show that our microscope can view micro and submicron‐sized patterns and beads. Moreover, our fist‐sized microscope can be placed inside an incubator for real‐time imaging of cells or rotated sideways for recording submicron‐sized crack generation due stretching of novel materials, both of which could not be accomplished with the 2 feet tall laboratory microscopes.