Automated Diabetic Retinopathy Detection Using Bag of Words Approach

Imaging and computer vision systems offer the ability to study quantitatively on human physiology. On contrary, manual interpretation requires tremendous amount of work, expertise and excessive processing time. This work presents an algorithm that integrates image processing and machine learning to diagnose diabetic retinopathy from retinal fundus images. This automated method classifies diabetic retinopathy (or absence thereof) based on a dataset collected from some publicly available database such as DRIDB0, DRIDB1, MESSIDOR, STARE and HRF. Our approach utilizes bag of words model with Speeded Up Robust Features and demonstrate classification over 180 fundus images containing lesions (hard exudates, soft exudates, microaneurysms, and haemorrhages) and non-lesions with an accuracy of 94.4%, precision of 94%, recall and f1-score of 94% and AUC of 95%. Thus, the proposed approach presents a path toward precise and automated diabetic retinopathy diagnosis on a massive scale.

How New Words Are Formed

With the development of the society and culture, English vocabulary change rapidly. English has always been in a state of evolution. In recent years new words enter the English language at an increasing rate. This paper makes an attempt to analyze eight ways of new English word formation, creating, blending, shortening, functional shift, back- formation, affixation, compounding and borrowing — by presenting mainly English examples.

Helps Towards Correct English Word-Order

ＨｅｌｐｓＴｏｗａｒｄｓＣｏｒｒｅｃｔＥｎｇｌｉｓｈＷｏｒｄ－ＯｒｄｅｒＬｉＺｅｃｈｅｎｇ（ＤｅｐａｒｔｍｅｎｔｏｆＦｏｒｅｉｇｎＬａｎｇｕａｇｅｓ，ＫｕｎｍｉｎｇＩｎｓｔｉｔｕｔｅｏｆＴｅｃｈｎｏｌｏｇｙ，Ｋｕｎｍｉｎｇ６５００９３）ＨｅｌｐｓＴｏ...

利用Microsoft Word编辑与保存书评长文档的方法与技巧

MicrosoftWord是目前应用最广泛的文字处理软件 ,其中一些用于编辑长文档的功能具有很高的实用价值。在图书馆开展的书评活动中 ,经常遇到编辑与保存长文档的情况 ,本文介绍一些方法和技巧 。

Automation技术在Word联机考试系统中的应用

以COM为基础的Automation技术为高级语言使用组件模块提供了一条有效的途径。Word联机考试系统根据Word作为组件软件的特点,利用Automation技术实现与Word应用软件之间的信息交互。该系统允许考生在真实的Word软件环境中自由操作答题。出题时,将题目要求的实现结果保存在Word文档中同时将包含考查要点的评分规则存入数据库。评分时,系统调出数据库中的评分规则与考生的答案文档进行对比得出分值。面向对象和组件技术的发展使得许多应用软件支持Automation,因此基于Automation技术的此类考试系统的应用范围会更广泛。

Mapping theme trends and knowledge structures for human neural stem cells:a quantitative and co-word biclustering analysis for the 2013-2018 period

Neural stem cells,which are capable of multi-potential differentiation and self-renewal,have recently been shown to have clinical potential for repairing central nervous system tissue damage.However,the theme trends and knowledge structures for human neural stem cells have not yet been studied bibliometrically.In this study,we retrieved 2742 articles from the PubMed database from 2013 to 2018 using "Neural Stem Cells" as the retrieval word.Co-word analysis was conducted to statistically quantify the characteristics and popular themes of human neural stem cell-related studies.Bibliographic data matrices were generated with the Bibliographic Item Co-Occurrence Matrix Builder.We identified 78 high-frequency Medical Subject Heading(MeSH)terms.A visual matrix was built with the repeated bisection method in gCLUTO software.A social network analysis network was generated with Ucinet 6.0 software and GraphPad Prism 5 software.The analyses demonstrated that in the 6-year period,hot topics were clustered into five categories.As suggested by the constructed strategic diagram,studies related to cytology and physiology were well-developed,whereas those related to neural stem cell applications,tissue engineering,metabolism and cell signaling,and neural stem cell pathology and virology remained immature.Neural stem cell therapy for stroke and Parkinson’s disease,the genetics of microRNAs and brain neoplasms,as well as neuroprotective agents,Zika virus,Notch receptor,neural crest and embryonic stem cells were identified as emerging hot spots.These undeveloped themes and popular topics are potential points of focus for new studies on human neural stem cells.

Design and Implementation of a New Chinese Word Segmentation Dictionary for the Personalized Mobile Search

Chinese word segmentation is the basis of natural language processing. The dictionary mechanism significantly influences the efficiency of word segmentation and the understanding of the user’s intention which is implied in the user’s query. As the traditional dictionary mechanisms can't meet the present situation of personalized mobile search, this paper presents a new dictionary mechanism which contains the word classification information. This paper, furthermore, puts forward an approach for improving the traditional word bank structure, and proposes an improved FMM segmentation algorithm. The results show that the new dictionary mechanism has made a significant increase on the query efficiency and met the user’s individual requirements better.

A New Approach of Time Series Variation Based on Power Links and Field Association Words

This paper has proposed a new methodology extracting stability classes of field association words depending on automatically power link analysis to enhance the precision of decision tree. In this paper, we have studied the effects of the time variation based on the frequencies of specific words called field association words that connected to documents using power link in a specific period. The stability classes have referred to the popularity of field association words based on the change of time in a given period. The new approach has evaluated by conducting experiments simulating results of 1575 files (about 5.16 MB). Based on these experiments, it has turned out that, the F-measure for ascending, stable and descending classes have achieved 93.6%, 99.8% and 75.7%, respectively. These results mean that F-measure was increasing by 12%, 4% and 34% than traditional methods because of the power link analysis.

A study of clinical psychological nursing research hotspots in China and variation trends based on word frequency analysis and visualization analysis

Objective: To analyze clinical psychological nursing research hotspots in China and variation trends in order to provide reference points on the current state of development of clinical psychological nursing and future research hotspots.Method: Clinical psychological nursing research literature sourced from Wanfang Data for the three periods of 2007-2009, 2010-2012, and 2013-2015 were selected as the research sample. A bibliographic co-occurrence analysis system(BICOMB software) was used to perform keyword word frequency analysis and generate a keyword co-occurrence matrix. In addition, Ucinet software's Netdraw tool was used to create visualized network diagrams.Results: A total of 27890 articles were retrieved, and word frequency analysis revealed that the highestfrequency keywords consisted of anxiety, depression, the elderly, expectant women, coronary heart disease, diabetes, breast cancer, perioperative period, quality of life, and psychological intervention.Research hotspot analysis revealed that consistent hotspots comprised anxiety, depression, health education, and perioperative period; expectant women became a hotspot during 2010-2012, and quality of life and efficacy became hotspots during 2013-2015.Conclusions: In addition to the care process, clinical psychological nursing research hotspots in China have increasingly included the effectiveness of psychological nursing and impact on patient quality of life. In addition, research hotspots have been influenced by the incidence of illnesses and people's health consciousness.

Next Words Prediction and Sentence Completion in Bangla Language Using GRU-Based RNN on N-Gram Language Model

We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuable time misspelling and retyping, and some people are not happy to type large sentences because they face unnecessary words or grammatical issues. So, for this reason, word predictive systems help to exchange textual information more quickly, easier, and comfortably for all people. These systems predict the next most probable words and give users to choose of the needed word from these suggested words. Word prediction can help the writer by predicting the next word and helping complete the sentence correctly. This research aims to forecast the most suitable next word to complete a sentence for any given context. In this research, we have worked on the Bangla language. We have presented a process that can expect the next maximum probable and proper words and suggest a complete sentence using predicted words. In this research, GRU-based RNN has been used on the N-gram dataset to develop the proposed model. We collected a large dataset using multiple sources in the Bangla language and also compared it to the other approaches that have been used such as LSTM, and Naive Bayes. But this suggested approach provides excellent exactness than others. Here, the Unigram model provides 88.22%, Bi-gram model is 99.24%, Tri-gram model is 97.69%, and 4-gram and 5-gram models provide 99.43% and 99.78% on average accurateness. We think that our proposed method profound impression on Bangla search engines.

Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words

Artificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%.

What Eye Movements Tell About Identifying Compound Words in Reading and Top-Down Effects in Reading Long Texts

Two lines of research on eye movements in reading are summarized. One line of research examines how adult readers identify compound words during reading. The other line of research deals with how a specific reading goal influences the way long expository texts are read. Both lines of research are conducted using Finnish as the source language. With respect to the first research question, it is demonstrated that compound words are recognized either holistically or via their components, depending on the length of the compound word. Readers begin to process whatever information is readily available in the foveal vision(i.e., either the whole-word form or the initial component). The second line of research demonstrates that(1)a specific reading goal is capable of exerting an early effect on readers’ eye fixation patterns,(2)time course analyses based on eye movement patterns can reveal interesting individual differences, and(3)working memory capacity is linked to the efficiency to strategically allocate attention as well as to encode information to and retrieve it from the long-term memory. It is concluded that the eye-tracking technique is an excellent research tool to tap into the workings of the human mind during the comprehension of written texts.

使用Visual Basic操纵Microsoft Word对象生成报表文档

在使用VisualBasic进行管理信息系统开发中,经常需要操纵MicrosoftWord在文档中特定位置填入从数据库中读取的数据资料来生成所需报表文档,以便于管理或打印输出。文章介绍了MicrosoftWord对象模型,以及在VisuaBasic应用程序中如何利用OLE引用MicrosoftWord对象。并且通过实例说明了在VisualBasic中利用MicrosoftWord对象的书签(Bookmark)和查找替换(Find、Replacement)两种方式向模板文档中填入数据实现报表文档的生成和保存的方法。

基于OLE Automation技术实现MS Word在上位机软件中的应用

介绍了借助OLE A utom ation技术实现Borland C++Bu ilder与M S W ord融合的方法。重点阐述了用编程手段在M SW ord文档中自动完成试验报告的排版和编写,并将试验数据直接导入M SW ord文档,填写在相应的表格里,并根据测试项目的要求探讨了试验报告的排版和格式。

The Study on the Differences of Sense of Words between English and Chinese in Translation

Translation is not only the process of transforming langue form, but also the process of interacting one thinking means and concept with another. Moreover, so as to ensure accuracy of translation, one needs to comprehend the sense of words in the source language correctly, and take appropriate approach to resolve the differences between Chinese and English through analyzing the causes. Therefore, this paper will study the differences of sense of words between English and Chinese in translation.

Origin of Dynamic Correlations of Words in Written Texts

In a previous study, we introduced dynamical aspects of written texts by regarding serial sentence number from the first to last sentence of a given text as discretized time. Using this definition of a textual timeline, we defined an autocorrelation function (ACF) for word occurrences and demonstrated its utility both for representing dynamic word correlations and for measuring word importance within the text. In this study, we seek a stochastic process governing occurrences of a given word having strong dynamic correlations. This is valuable because words exhibiting strong dynamic correlations play a central role in developing or organizing textual contexts. While seeking this stochastic process, we find that additive binary Markov chain theory is useful for describing strong dynamic word correlations, in the sense that it can reproduce characteristics of autocovariance functions (an unnormalized version of ACFs) observed in actual written texts. Using this theory, we propose a model for time-varying probability that describes the probability of word occurrence in each sentence in a text. The proposed model considers hierarchical document structures such as chapters, sections, subsections, paragraphs, and sentences. Because such a hierarchical structure is common to most documents, our model for occurrence probability of words has a wide range of universality for interpreting dynamic word correlations in actual written texts. The main contributions of this study are, therefore, finding usability of the additive binary Markov chain theory to analyze dynamic correlations in written texts and offering a new model of word occurrence probability in which common hierarchical structure of documents is taken into account.

Counting Types of Runs in Classes of Arborescent Words

An arborescence is a directed rooted tree in which all edges point away from the root. An arborescent word is obtained by replacing each element of the underlying set of an arborescence by an arbitrary letter of a given alphabet (with possible repetitions). We define a run in an arborescent word as a maximal sub-arborescent word whose letters are all identical. Various types of runs (e.g., runs of size ≤ k, linear runs, etc) are studied in the context of R-enriched arborescent words, where R is a given species of structures.

On the Translation of Chinese Four-character Idioms Loaded with Color Words

Chinese four-character idioms loaded with color words are the typical symbol of the Chinese culture and their transition is important to Chinese-English dictionaries.The quality of the dictionary and users' understanding are affected by the correctness and appropriateness of their translation.This paper mainly focuses on the translation of four-character Chinese idioms with color words in New Century Chinese-English Dictionary.The research shows that there are three strategies for Chinese fourcharacter idioms loaded with color words in the dictionaries:literal translation,free translation and the integration of literal translation and annotative translation.

使用Microsoft Word编排科技期刊时的几个关键问题

根据科技期刊的版式特点,分析Microsoft Word在科技期刊排版中的模板制作、字体选择、图表编排和公式插入等4个关键问题,并给出了解决方案。编排实践表明,将MicrosoftWord应用于科技期刊排版不仅可行而且有效。

基于改进的Bag of Visual Words算法的SAR图像目标分类

"视觉词袋"(Bag of Visual Words,BOV)算法是一种有效的基于语义特征表达的物体识别算法。针对传统BOV模型存在的不足,综合利用SAR图像的灰度和纹理特征,提出基于感兴趣目标(Target of Interest,TOI)的"视觉词袋"算法。首先,对训练图像进行TOI选取,用灰度共生矩阵模型提取TOI的纹理特征,再结合灰度特征,组成多维特征向量集,以簇内相似度最高、数据分布密度最大为准则,生成"视觉词袋"。其次,对测试图像,依据已生成的"视觉词袋",采用支持向量机(Support Vector Machine,SVM)分类器,实现SAR图像感兴趣目标的有效分类。实验结果表明,与传统的"视觉词袋"构建算法相比,该算法在分类正确率提高的同时,能够在训练图像较少的情况下达到良好的分类效果。