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.     

CuInS2/SiNWs/Si composite material for application as potential photoelectrode for photoelectrochemical hydrogen generation

This work aims at developing a new composite material based on nanosized semiconducting CuInS₂ (CIS) particles combined with silicon nanowires grown on a silicon substrate (SiNWs/Si) for photoelectrochemical (PEC)-splitting of water. The CIS particles were prepared via a colloidal method using N-methylimidazole (NMI) as the solvent and an annealing treatment. The SiNWs were obtained by chemical etching of silicon (100) substrates assisted by a metal. The CIS/SiNWs/Si composite material was obtained by deposition of an aliquot of a suspension of CIS particles onto the SiNWs/Si substrate, using spin coating followed by a drying step. The XRD pattern demonstrated that CuInS₂ grows in the tetragonal/chalcopyrite phase, while SiNWs/Si presents a cubic structure. The SEM images show semi-spherical particles (～10 nm) distributed on the surface of silicon nanowires (～10 μm). The EIS measurements reveal n-type conductivity for CIS, SiNWs/Si and CIS/SiNWs/Si materials, which could favour the oxidation reaction of water molecules.     

综合改进奇异谱分解和奇异值分解的齿轮故障特征提取方法

针对齿轮故障特征微弱，在强背景噪声下难以有效提取的问题，提出了一种改进奇异谱分解（ISSD）结合奇异值分解（SVD）的齿轮故障特征提取方法。针对奇异谱分解（SSD）算法中模态参数需凭经验选取的缺陷，基于散布熵优化算法对SSD算法进行了改进，在得到既定的一组奇异谱分量的基础上，根据峭度值最大准则筛选出了最佳奇异谱分量并进行了SVD处理，采用奇异值能量标准谱自适应地确定了信号重构阶数以还原信号和提高降噪效果。最后对信号进行包络解调以提取齿轮故障特征，将所提方法运用到仿真信号和齿轮实测信号中，并同传统包络谱、SSD包络谱以及经验模态分解结合SVD(EMD-SVD)方法进行了对比分析，结果表明，所提方法的降噪和特征提取效果更佳，能够更加有效地实现齿轮故障的判别。     

Geothermal energy utilization trends from a technological paradigm perspective

The use of geothermal energy and its associated technologies has been increasing worldwide. However, there has been little paradigmatic research conducted in this area. This paper proposes a systematic methodology to research the development trends for the sustainable development of geothermal energy. A novel data analysis system was created to research the geothermal energy utilization trends, and a technological paradigm theory was adopted to explain the technological changes. A diffusion velocity model was used to simulate and forecast the geothermal power generation development in the diffusion phase. Simulation results showed that the development of installed capacity for geothermal generation had a strong inertia force along with the S-curve. Power generation from geothermal power sources reached a peak in 2008 and is estimated to be saturated by 2030. Geothermal energy technologies in hybrid power systems based on other renewable energy sources look to be more promising in the future.     

基于特征融合的中文简历解析方法研究

针对基于规则和统计的传统中文简历解析方法效率低、成本高、泛化能力差的缺点，提出一种基于特征融合的中文简历解析方法，即级联Word2Vec生成的词向量和用BLSTM（Bidirectional Long Short-Term Memory）建模字序列生成的词向量，然后再结合BLSTM和CRF（Conditional Random Fields）对中文简历进行解析（BLSTM-CRF）。为了提高中文简历解析的效率，级联包含字序列信息的词向量和用Word2Vec生成的词向量，融合成一个新的词向量表示；再由BLSTM强大的学习能力融合词的上下文信息，输出所有可能标签序列的分值给CRF层；再由CRF引入标签之间约束关系求解最优序列。利用梯度下降算法训练神经网络，使用预先训练的词向量和Dropout优化神经网络，最终完成对中文简历的解析工作。实验结果表明，所提的特征融合方法优于传统的简历解析方法。     

基于颜色四通道及空间金字塔的鱼类图像检索

随着计算机视觉技术在海洋水产领域中的应用不断加深，鱼类图像检索在渔业资源调查、鱼类行为学分析等方面发挥了巨大的作用。通过研究发现，鱼类图像的背景信息会对鱼类图像检索造成极大干扰，而且鱼类图像中颜色、纹理、形状等特征由于空间位置信息的缺乏而使检索的准确率不高。为解决以上问题，提出了一种新的基于颜色四通道及空间金字塔的鱼类图像检索算法。首先，提取视觉显著性图将鱼类图像的前景和背景分开，从而减少图像背景对检索的干扰；其次，为了使图像特征包含一定的空间位置信息，利用空间金字塔的理论对图像进行分割，在此基础上，将图像转为HSVG四通道图并提取SURF特征；；最后，得到检索结果。为验证所提算法的有效性，在QUT_fish_data数据集和DLOU_fish_data数据集上对算法的查全率、查准率与经典的HSVG算法和显著性分块算法进行对比：在两个数据集上查准率分别比传统的HSVG算法最多分别提高12%和5%，查全率最多分别提高7%和22%；比传统的显著性分块算法查准率最多分别提高15%和5%，查全率最多分别提高36%和22%；从而证明所提算法是有效的，能有效提升鱼类图像的检索效果。     

带有方形肋及双倾斜肋片的细通道内流动、传热和熵产分析

为了探究带有方形肋及双倾斜肋片细通道的流动换热及熵产特性，设计了2种带有方形肋及双倾斜肋片的组合细通道(MCDS-L, MCDS-R)，然后采用数值模拟的方法分析其流动特性、传热特性和熵产特性，并将其分析结果同2种方形肋细通道(MCS-L, MCS-R)和一种双倾斜肋片细通道(MCD)进行对比。结果表明，在所研究的雷诺数范围内，组合通道的摩擦阻力系数基本一致且均高于其他3组通道(MCS-L, MCS-R, MCD) 。此外，组合通道的努塞尔数均高于其他3组通道，而熵产增大数均低于其他3组通道。其中，MCDS-L通道的努塞尔数最大，熵产增大数最低。表明MCDS-L通道的换热效果最佳，能量的综合利用程度最高。研究成果为微细通道热沉的设计提供参考。     

基于聚类的数据加权优化在犯罪预测中的应用

近年来，我国传统暴力犯罪与成年人犯罪呈下降态势，但是，犯罪案由层出不穷。为有效提升公安实践工作中犯罪预测能力，打击各类违法犯罪事件,本文针对犯罪数据，提出一种新型犯罪预测模型。利用密度聚类分析方法将犯罪数据分类，然后进行数据降维提取关键属性生成特征数据，继而对特征数据进行加权优化并采用机器学习的方式对特征数据进行学习，从而预测犯罪案由。实验结果表明，与传统方法相比，本文方法具有更好的预测效果，为公安实践工作中类似案件的侦破和预防，提供新的路径支撑。     

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.