Retinal Vessel Extraction Framework Using Modified Adaboost Extreme Learning Machine

An explicit extraction of the retinal vessel is a standout amongst the most significant errands in the field of medical imaging to analyze both the ophthalmological infections, for example, Glaucoma, Diabetic Retinopathy (DR), Retinopathy of Prematurity (ROP), Age-Related Macular Degeneration (AMD) as well as non retinal sickness such as stroke, hypertension and cardiovascular diseases. The state of the retinal vasculature is a significant indicative element in the field of ophthalmology. Retinal vessel extraction in fundus imaging is a difficult task because of varying size vessels, moderately low distinction, and presence of pathologies such as hemorrhages, microaneurysms etc. Manual vessel extraction is a challenging task due to the complicated nature of the retinal vessel structure, which also needs strong skill set and training. In this paper, a supervised technique for blood vessel extraction in retinal images using Modified Adaboost Extreme Learning Machine (MAD-ELM) is proposed. Firstly, the fundus image preprocessing is done for contrast enhancement and in-homogeneity correction. Then, a set of core features is extracted, and the best features are selected using “minimal Redundancy-maximum Relevance (mRmR).” Later, using MAD-ELM method vessels and non vessels are classified. DRIVE and DR-HAGIS datasets are used for the evaluation of the proposed method. The algorithm’s performance is assessed based on accuracy, sensitivity and specificity. The proposed technique attains accuracy of 0.9619 on the DRIVE database and 0.9519 on DR-HAGIS database, which contains pathological images. Our results show that, in addition to healthy retinal images, the proposed method performs well in extracting blood vessels from pathological images and is therefore comparable with state of the art methods.     

Impact of non‐solvent on regeneration of cellulose dissolved in 1‐(carboxymethyl)pyridinium chloride ionic liquid

Cellulose dissolved in ionic liquid (1‐(carboxymethyl)pyridinium chloride)/water (60/40 w/w) mixture is regenerated in various non‐solvents, namely water, ethanol, methanol and acetone, to gain more insight into the contribution of non‐solvent medium to the morphology of regenerated cellulose. To this end, the initial and regenerated celluloses were characterized with respect to crystallinity, thermal stability, chemical structure and surface morphology using wide‐angle X‐ray diffraction, thermogravimetric analysis, Fourier transform infrared spectroscopy and scanning electron microscopy. According to the results, regardless of non‐solvent type, all regenerated samples have the same chemical structure and lower crystallinity in comparison to the initial cellulose, making them a promising candidate for efficient biofuel production based on enzymatic hydrolysis of cellulose. The reduction in crystallinity of regenerated samples is explained based on the potential of the non‐solvent to break the hydrogen bonds between cellulose chains and ionic liquid molecules as well as the affinity of water and non‐solvent which can be evaluated based on Hansen solubility parameter. The latter also determines the phase‐separation mechanism during the regeneration process, which in turn affects surface morphology of the regenerated cellulose. The pivotal effect of regenerated cellulose crystallinity on its thermal stability is also demonstrated. Regenerated cellulose with lower crystallinity is more susceptible to molecular rearrangement during heating and hence exhibits enhanced thermal stability. © 2019 Society of Chemical Industry     

Applications of Diglycolamide Based Solvent Extraction Processes in Spent Nuclear Fuel Reprocessing,Part 1: TODGA

Over the last decade there has been much interest in the applications of diglycolamide (DGA) ligands for the extraction of the trivalent lanthanide and actinide ions from PUREX high active raffinates or dissolved spent nuclear fuel. Of the DGAs, the N,N,N’,N’-tetraoctyldiglycolamide (TODGA) is the best known and most widely studied. A number of new actinide separation processes have been proposed based on extraction with TODGA. This review covers TODGA-based processes and extraction data, specifically focusing on how phase modifiers have been used to increase metal loading and thus enhance the operating process envelopes. Effects of third phase formation and the organic phase speciation are reviewed in this context. Relevant aspects of the extraction chemistry of important solvents (TODGA-modifier-diluent combinations) are described and their performances demonstrated by a consideration of the published flowsheet tests. It is seen that modifiers are successfully enabling the use of TODGA in actinide separation processes but to date the identification and testing of suitable modifiers has been rather empirical. There is a growing understanding of the fundamental chemistry occurring in the organic phase and how that affects extractant speciation and metal loading capacity but studies are still needed if TODGA-based flowsheets are to become an industrially deployable option for minor actinide (MA) recovery processes.     

Using d-limonene as the non-aromatic and non-chlorinated solvent for the fabrications of high performance polymer light-emitting diodes and field-effect transistors

Aiming to environment protection, green solvents are crucial for commercialization of solution-processed optoelectronic devices. In this work, d-limonene, a natural product, was introduced as the non-aromatic and non-chlorinated solvent for processing of polymer light-emitting diodes (PLEDs) and organic field effect transistors (OFETs). It was found that d-limonene could be a good solvent for a blue-emitting polyfluorene-based random copolymer for PLEDs and an alternating copolymer FBT-Th₄(1,4) with high hole mobility (μ_h) for OFETs. In comparisons to routine solvent-casted films of the two conjugated polymers, the resulting d-limonene-deposited films could show comparable film qualities, based on UV–vis absorption spectra and observations by atomic force microscopy (AFM). With d-limonene as the processing solvent, efficient blue PLEDs with CIE coordinates of (0.16, 0.16), maximum external quantum efficiency of 3.57%, and luminous efficiency of 3.66 cd/A, and OFETs with outstanding μ_h of 1.06 cm² (V s)⁻¹ were demonstrated. Our results suggest that d-limonene would be a promising non-aromatic and non-chlorinated solvent for solution processing of conjugated polymers and molecules for optoelectronic device applications.     

Road Extraction from High Resolution Remote Sensing Image based on Shape Analysis with Gestalt Theory

Simulating the psychological experience of human vision，a road extraction model based on the format tower is proposed to extract the road in the high resolution remote sensing image from the perspective of morphology.Firstly，based on the spectral and texture information，the suspected road targets are extracted by using segmentation technology.Then these targets are classified according to their reliability and extract the road targets for each category.Finally，three types of identified road information are verified and merged，and the continuous smooth road extraction results are obtained.Experiments on real high resolution images show that the results are consistent with the visual perception of the human eye，and the overall classification accuracy is higher，indicating that the algorithm is effective and feasible and has good use value.     

因素空间理论下基点分类算法研究

目前，基于因素空间理论的背景基提取算法计算过程复杂，初始化必须依赖各因素极值，基点数量提取冗余等原因，未能在应用中取得很好效果。为此，结合内点判别法和知识可继承、可扩展的思想，提出一种计算简单、初始化独立、基点数量小的改进的背景基提取算法。然后，利用改进的背景基提取算法构造出一种全新的数据分类算法-基点分类算法，基点分类算法以提取每一类样本的背景基为预测模型，再通过新定义的λ-背景基，优化预测模型。数值实验表明:基点分类算法原理简单、构造难度小、分类模型泛化能力强，预测能力准确率高，同时严格的模型限定区域又能为识别新类别提供新方法。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.