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.     

细节决定采输卤的成败

通过认真学习《细节决定成败》，结合井矿盐开采的实际，分别以生产过程中的三个细节为主，讨论了在采输卤生产技术控制中的细节的重要性。     

网络安全事件的关联分析方法的比较研究

随着当前攻击手段和技术的日益复杂化,一次入侵事件往往需要多个步骤才能完成,这些步骤都是彼此相关的。但是传统的入侵检测集中于检测底层的入侵或异常,所检测到的结果也仅仅是一次完整入侵的一部分,所以不能将不同的报警结合起来以发现入侵的逻辑步骤或者入侵背后的攻击策略。关联分析技术将不同分析器上产生的报警进行融合与关联分析,极大地减少了报警的数量,降低了入侵检测的误报率,并且适当的减少了入侵检测的漏报率。文中在对网络安全事件关联分析方法的系统结构进行分析后,着重介绍了当前比较流行的几种网络安全事件关联分析方法,最后对各种方法进行了比较研究。     

Extracting Light from Polymer Light‐Emitting Diodes Using Stamped Bragg Gratings

In this paper, we describe a method for increasing the external efficiency of polymer light‐emitting diodes (LEDs) by coupling out waveguided light with Bragg gratings. We numerically model the waveguide modes in a typical LED structure and demonstrate how optimizing layer thicknesses and reducing waveguide absorption can enhance the grating outcoupling. The gratings were created by a soft‐lithography technique that minimizes changes to the conventional LED structure. Using one‐dimensional and two‐dimensional gratings, we were able to increase the forward‐directed emission by 47 % and 70 %, respectively, and the external quantum efficiency by 15 % and 25 %.     

网络管理中事件关联检测机制的研究

网络事件的关联检测是网络管理需要解决的一个关键问题,本文根据分布式网络管理的特点,首次明确定义了网络事件的基本关联关系,在此基础上提出了一种基于Petri Net的事件关联检测机制,实现了基于事件内容的细粒度关联检测,并且在事件检测中充分考虑了时间因素,有效地提高了事件关联检测的准确性。     

利用信息融合方法的三维特征提取

本文提出了一种基于信息融合的物体三维特征的提取方法，该方法利用两幅互相配准的三维测距图像和灰度图像，来提取多面体的三维特征。首先，通过分析灰度图像中的灰度变化及测距图像中的测距值变化，分别求取各自图像中物体的特征点及特征边；然后，利用两配准图像之间的对应关系，求得所有特征点、面与多边形在三维测距图像中的三维表示；接着，通过分析三维测距图像中所测得的各候选平面上特定点与边处的曲率及法向，验证候选平面     

芝麻营养原液的开发与研究

本文对芝麻营养保健成分的提取进行了系统的研究。确定了芝麻营养原液的制取工艺。为充分发挥芝麻的营养保健作用开辟了新的途径。     

HPMBP与伯胺N_(1923)对希土元素(Ⅲ)的协同萃取

本文研究了HPMBP与伯胺N_(1923)的二甲苯溶液,从盐酸介质中协同萃取希土(Ⅲ)的机理。用斜率法、恒摩尔法确定了协萃配合物的组成为:RNH_3Ln(PMBP)_4。求得关于Pr(Ⅲ)协萃反应的平衡常数及协萃配合物的生成常数分别为:logK_(12)=-1.95;logβ_(12)=3.94。实验发现,协萃系数(R)随希土元素的原子序数(Z)递变而呈现“双峰效应”。还研究了协萃配合物的IR,NMR谱。     

CD++: a toolkit to develop DEVS models

The features of a toolkit for modeling and simulation based on the DEVS formalism are presented. The tool is built as a set of independent software pieces running on different platforms. Not only are the main characteristics of the environment presented, a focus on its use is also considered by inclusion of application examples for a variety of problems. Many models can be defined in an automated fashion, simplifying the construction of new models and easing their verification. The use of this formal approach has allowed the development of safe and cost‐effective simulations, significantly reducing development time. Copyright © 2002 John Wiley & Sons, Ltd.     

Protein Extraction from Heat-stabilized Defatted Rice Bran: II. The Role of Amylase, Celluclast, and Viscozyme

ABSTRACT: The effectiveness of 3 carbohydrases for protein extraction from heat-stabilized defatted rice bran (HDRB) was evaluated. Amylase, viscozyme and celluclast extracted a maximum of 45.4, 12.1, and 28.5% protein, respectively. Further study showed that extracted protein ranged from 9.5 to 58.4% under conditions of water to bran ratio (5:1 to 20:1), α-amylase (0 to 110000 units/10 g rice bran), temperature (35 to 55 °C), and time (1 to 8 h). The maximum protein extracted was 58.4% with a water to bran ratio of 17:1, 87637 units amylase, and 50.9 °C. These results suggest that impure food-grade amylase containing protease is more effective than celluclast and viscozyme in protein extraction from HDRB.