一种高动态范围图像可视化算法*

提出的自适应HDR图像可视化算法中,输入图像被分解为基本层和细节层.该算法将整体明暗效果的显示看做整体问题,对表示亮度的基本层采用基于整体统计信息的直方图调整算法处理;可视细节信息的保持作为局部问题,算法采用自适应细节增强算法处理细节层.通过定义映射图对细节增强后的图像进行最终映射,将两方面结合起来得到最终结果.实验结果表明,该算法能对HDR图像进行较高视觉质量的显示.     

Optimization and evaluation of reduced graphene oxide hydrogel composite as a demulsifier for heavy crude oil-in-water emulsion

The rising production of produced water from oilfields had been proven to bring detrimental environmental effects. In this study, an efficient, recyclable, and environmental-friendly reduced graphene oxide immobilized κ-Carrageenan hydrogel composite(κCa GO) was fabricated as an alternative sorbent for crude oil-in-water demulsification. Polyethyleneimine(PEI) was employed to form a stable hydrogel composite. The conditions for the immobilization of graphene oxide(GO) on PEI-modified κ-Carrageenan(κC) beads were optimized appropriately. An immobilization yield of 77% was attained at 2% PEI, 2 h immobilization activation time, and p H6.5. Moreover, the synthesized κCa GO is capable of demulsification with an average demulsification efficiency of 70%. It was found that the demulsification efficiency increases with salinity and κCa GO dosage, and it deteriorates under alkaline condition. These phenomena can be attributed to the interfacial interactions between κCa GO and the emulsion. Furthermore, the κCa GO can be recycled to use for up to six cycles without significant leaching and degradation. As such, the synthesized κCa GO could be further developed as a potential sorbent substitute for the separation of crude oil from produced water.     

Evolving Least Squares Support Vector Machines for Stock Market Trend Mining

In this paper, an evolving least squares support vector machine (LSSVM) learning paradigm with a mixed kernel is proposed to explore stock market trends. In the proposed learning paradigm, a genetic algorithm (GA), one of the most popular evolutionary algorithms (EAs), is first used to select input features for LSSVM learning, i.e., evolution of input features. Then, another GA is used for parameters optimization of LSSVM, i.e., evolution of algorithmic parameters. Finally, the evolving LSSVM learning paradigm with best feature subset, optimal parameters, and a mixed kernel is used to predict stock market movement direction in terms of historical data series. For illustration and evaluation purposes, three important stock indices, S&P 500 Index, Dow Jones Industrial Average (DJIA) Index, and New York Stock Exchange (NYSE) Index, are used as testing targets. Experimental results obtained reveal that the proposed evolving LSSVM can produce some forecasting models that are easier to be interpreted by using a small number of predictive features and are more efficient than other parameter optimization methods. Furthermore, the produced forecasting model can significantly outperform other forecasting models listed in this paper in terms of the hit ratio. These findings imply that the proposed evolving LSSVM learning paradigm can be used as a promising approach to stock market tendency exploration.     

Credit scoring using support vector machines with direct search for parameters selection

Support vector machines (SVM) is an effective tool for building good credit scoring models. However, the performance of the model depends on its parameters’ setting. In this study, we use direct search method to optimize the SVM-based credit scoring model and compare it with other three parameters optimization methods, such as grid search, method based on design of experiment (DOE) and genetic algorithm (GA). Two real-world credit datasets are selected to demonstrate the effectiveness and feasibility of the method. The results show that the direct search method can find the effective model with high classification accuracy and good robustness and keep less dependency on the initial search space or point setting.     

Applications, techniques, and microfluidic interfacing for nanoscale biosensing

Biosensors based on nanotechnology are rapidly developing and are becoming widespread in the biomedical field and analytical chemistry. For these nanobiosensors to reach their potential, they must be integrated with appropriate packaging techniques, which are usually based on nano/microfluidics. In this review we provide a summary of the latest developments in nanobiosensors with a focus on label-based (fluorescence and nanoparticle) and label-free methods (surface plasmon resonance, micro/nanocantilever, nanowires, and nanopores). An overview on how these sensors interface with nano/microfluidics is then presented and the latest papers in the area summarized.     

A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms

Computational Visual Media - The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this...     

Microfluidic-based biosensors toward point-of-care detection of nucleic acids and proteins

This article reviews state-of-the-art microfluidic biosensors of nucleic acids and proteins for point-of-care (POC) diagnostics. Microfluidics is capable of analyzing small sample volumes (10⁻⁹–10⁻¹⁸ l) and minimizing costly reagent consumption as well as automating sample preparation and reducing processing time. The merger of microfluidics and advanced biosensor technologies offers new promises for POC diagnostics, including high-throughput analysis, portability and disposability. However, this merger also imposes technological challenges on biosensors, such as high sensitivity and selectivity requirements with sample volumes orders of magnitude smaller than those of conventional practices, false response errors due to non-specific adsorption, and integrability with other necessary modules. There have been many prior review articles on microfluidic-based biosensors, and this review focuses on the recent progress in last 5 years. Herein, we review general technologies of DNA and protein biosensors. Then, recent advances on the coupling of the biosensors to microfluidics are highlighted. Finally, we discuss the key challenges and potential solutions for transforming microfluidic biosensors into POC diagnostic applications.     

Genetic Parallel Programming: design and implementation

This paper presents a novel Genetic Parallel Programming (GPP) paradigm for evolving parallel programs running on a Multi-Arithmetic-Logic-Unit (Multi-ALU) Processor (MAP). The MAP is a Multiple Instruction-streams, Multiple Data-streams (MIMD), general-purpose register machine that can be implemented on modern Very Large-Scale Integrated Circuits (VLSIs) in order to evaluate genetic programs at high speed. For human programmers, writing parallel programs is more difficult than writing sequential programs. However, experimental results show that GPP evolves parallel programs with less computational effort than that of their sequential counterparts. It creates a new approach to evolving a feasible problem solution in parallel program form and then serializes it into a sequential program if required. The effectiveness and efficiency of GPP are investigated using a suite of 14 well-studied benchmark problems. Experimental results show that GPP speeds up evolution substantially.