首页 > 最新文献

Future Computing and Informatics Journal最新文献

英文 中文
Depth-based human activity recognition: A comparative perspective study on feature extraction 基于深度的人类活动识别:特征提取的比较视角研究
Pub Date : 2018-06-01 DOI: 10.1016/j.fcij.2017.11.002
Heba Hamdy Ali , Hossam M. Moftah , Aliaa A.A. Youssif

Depth Maps-based Human Activity Recognition is the process of categorizing depth sequences with a particular activity. In this problem, some applications represent robust solutions in domains such as surveillance system, computer vision applications, and video retrieval systems. The task is challenging due to variations inside one class and distinguishes between activities of various classes and video recording settings. In this study, we introduce a detailed study of current advances in the depth maps-based image representations and feature extraction process. Moreover, we discuss the state of art datasets and subsequent classification procedure. Also, a comparative study of some of the more popular depth-map approaches has provided in greater detail. The proposed methods are evaluated on three depth-based datasets “MSR Action 3D”, “MSR Hand Gesture”, and “MSR Daily Activity 3D”. Experimental results achieved 100%, 95.83%, and 96.55% respectively. While combining depth and color features on “RGBD-HuDaAct” Dataset, achieved 89.1%.

基于深度图的人类活动识别是对具有特定活动的深度序列进行分类的过程。在这个问题中,一些应用程序在诸如监视系统、计算机视觉应用程序和视频检索系统等领域中代表了健壮的解决方案。由于一个班级内部的变化,以及不同班级的活动和视频录制设置的区别,这项任务具有挑战性。在本研究中,我们详细介绍了目前基于深度图的图像表示和特征提取过程的研究进展。此外,我们还讨论了最新的数据集和随后的分类过程。此外,对一些更流行的深度图方法的比较研究提供了更详细的信息。在三个基于深度的数据集“MSR Action 3D”、“MSR Hand Gesture”和“MSR Daily Activity 3D”上对所提出的方法进行了评估。实验结果分别达到100%、95.83%和96.55%。在“RGBD-HuDaAct”数据集上结合深度和颜色特征,达到89.1%。
{"title":"Depth-based human activity recognition: A comparative perspective study on feature extraction","authors":"Heba Hamdy Ali ,&nbsp;Hossam M. Moftah ,&nbsp;Aliaa A.A. Youssif","doi":"10.1016/j.fcij.2017.11.002","DOIUrl":"10.1016/j.fcij.2017.11.002","url":null,"abstract":"<div><p>Depth Maps-based Human Activity Recognition is the process of categorizing depth sequences with a particular activity. In this problem, some applications represent robust solutions in domains such as surveillance system, computer vision applications, and video retrieval systems. The task is challenging due to variations inside one class and distinguishes between activities of various classes and video recording settings. In this study, we introduce a detailed study of current advances in the depth maps-based image representations and feature extraction process. Moreover, we discuss the state of art datasets and subsequent classification procedure. Also, a comparative study of some of the more popular depth-map approaches has provided in greater detail. The proposed methods are evaluated on three depth-based datasets “MSR Action 3D”, “MSR Hand Gesture”, and “MSR Daily Activity 3D”. Experimental results achieved 100%, 95.83%, and 96.55% respectively. While combining depth and color features on “RGBD-HuDaAct” Dataset, achieved 89.1%.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"3 1","pages":"Pages 51-67"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.11.002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84946919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 38
A robust 3D mesh watermarking algorithm utilizing fuzzy C-Means clustering 一种基于模糊c均值聚类的鲁棒三维网格水印算法
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.10.007
Ola M. El Zein , Lamiaa M. El Bakrawy , Neveen I. Ghali

A new robust 3D watermarking algorithm utilizing Fuzzy C-Means (FCM) clustering technique is presented. FCM clusters 3D mesh vertices into suitable and unsuitable choices to insert the watermark without occasioning visible deformation, and also it is tough for the attacker to determine places of the watermark insertion. Two watermarking processes are offered to insert the watermark into 3D mesh models. The first process utilizes topical statistical measurements like average and standard deviation in order to alter the values of vertices to secret watermark data into 3D mesh models, however, the second process utilizes a jumbled insertion planning to insert the watermark inside 3D mesh models utilizing the topical statistical measurements and altering 3D mesh vertices together. Simulation results show that the proposed algorithm is robust. The watermarked 3D mesh models are resistant to several attacks like similarity transforms, noise addition, cropping and mesh smoothing.

提出了一种基于模糊c均值聚类技术的鲁棒三维水印算法。FCM将三维网格的顶点聚类成合适和不合适的位置来插入水印,而不会产生明显的变形,而且攻击者很难确定水印的插入位置。提出了两种将水印插入三维网格模型的方法。第一种方法利用局部统计测量,如平均值和标准差,以改变顶点值的秘密水印数据到三维网格模型中,然而,第二种方法利用一个混乱的插入计划,利用局部统计测量和改变三维网格顶点,将水印插入到三维网格模型中。仿真结果表明,该算法具有较好的鲁棒性。带水印的三维网格模型能够抵抗相似变换、噪声添加、裁剪和网格平滑等攻击。
{"title":"A robust 3D mesh watermarking algorithm utilizing fuzzy C-Means clustering","authors":"Ola M. El Zein ,&nbsp;Lamiaa M. El Bakrawy ,&nbsp;Neveen I. Ghali","doi":"10.1016/j.fcij.2017.10.007","DOIUrl":"10.1016/j.fcij.2017.10.007","url":null,"abstract":"<div><p>A new robust 3D watermarking algorithm utilizing Fuzzy C-Means (FCM) clustering technique is presented. FCM clusters 3D mesh vertices into suitable and unsuitable choices to insert the watermark without occasioning visible deformation, and also it is tough for the attacker to determine places of the watermark insertion. Two watermarking processes are offered to insert the watermark into 3D mesh models. The first process utilizes topical statistical measurements like average and standard deviation in order to alter the values of vertices to secret watermark data into 3D mesh models, however, the second process utilizes a jumbled insertion planning to insert the watermark inside 3D mesh models utilizing the topical statistical measurements and altering 3D mesh vertices together. Simulation results show that the proposed algorithm is robust. The watermarked 3D mesh models are resistant to several attacks like similarity transforms, noise addition, cropping and mesh smoothing.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 148-156"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.10.007","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86210599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 19
A thresholding based technique to extract retinal blood vessels from fundus images 基于阈值的眼底图像视网膜血管提取技术
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.10.001
Jyotiprava Dash, Nilamani Bhoi

Retinal imaging has become the significant tool among all the medical imaging technology, due to its capability to extract many data which is linked to various eye diseases. So, the accurate extraction of blood vessel is necessary that helps the eye care specialists and ophthalmologist to identify the diseases at the early stages. In this paper, we have proposed a computerized technique for extraction of blood vessels from fundus images. The process is conducted in three phases: (i) pre-processing where the image is enhanced using contrast limited adaptive histogram equalization and median filter, (ii) segmentation using mean-C thresholding to extract retinal blood vessels, (iii) post-processing where morphological cleaning operation is used to remove isolated pixels. The performance of the proposed method is tested on and experimental results show that our method achieve an accuracies of 0.955 and 0.954 on Digital retinal images for vessel extraction (DRIVE) and Child heart and health study in England (CHASE_DB1) databases respectively.

视网膜成像由于能够提取与各种眼病相关的大量数据,已成为医学成像技术中的重要工具。因此,准确的血管提取是必要的,可以帮助眼科医生和眼科医生在早期阶段识别疾病。本文提出了一种从眼底图像中提取血管的计算机技术。该过程分三个阶段进行:(i)预处理,使用对比度有限的自适应直方图均衡化和中值滤波对图像进行增强;(ii)使用均值- c阈值分割提取视网膜血管;(iii)后处理,使用形态学清洗操作去除孤立像素。实验结果表明,该方法在英国儿童心脏健康研究数据库(CHASE_DB1)和用于血管提取的数字视网膜图像(DRIVE)上的准确率分别为0.955和0.954。
{"title":"A thresholding based technique to extract retinal blood vessels from fundus images","authors":"Jyotiprava Dash,&nbsp;Nilamani Bhoi","doi":"10.1016/j.fcij.2017.10.001","DOIUrl":"10.1016/j.fcij.2017.10.001","url":null,"abstract":"<div><p>Retinal imaging has become the significant tool among all the medical imaging technology, due to its capability to extract many data which is linked to various eye diseases. So, the accurate extraction of blood vessel is necessary that helps the eye care specialists and ophthalmologist to identify the diseases at the early stages. In this paper, we have proposed a computerized technique for extraction of blood vessels from fundus images. The process is conducted in three phases: (i) pre-processing where the image is enhanced using contrast limited adaptive histogram equalization and median filter, (ii) segmentation using mean-C thresholding to extract retinal blood vessels, (iii) post-processing where morphological cleaning operation is used to remove isolated pixels. The performance of the proposed method is tested on and experimental results show that our method achieve an accuracies of 0.955 and 0.954 on Digital retinal images for vessel extraction (DRIVE) and Child heart and health study in England (CHASE_DB1) databases respectively.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 103-109"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.10.001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73757787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 79
Informative gene selection using Adaptive Analytic Hierarchy Process (A2HP) 基于自适应层次分析法的信息基因选择
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.07.004
Abhishek Bhola, Shafa Mahajan, Shailendra Singh

Gene expression dataset derived from microarray experiments are marked by large number of genes, which contains the gene expression values at different sample conditions/time-points. Selection of informative genes from these large datasets is an issue of major concern for various researchers and biologists. In this study, we propose a gene selection and dimensionality reduction method called Adaptive Analytic Hierarchy Process (A2HP). Traditional analytic hierarchy process is a multiple-criteria based decision analysis method whose result depends upon the expert knowledge or decision makers. It is mainly used to solve the decision problems in different fields. On the other hand, A2HP is a fused method that combines the outcomes of five individual gene selection ranking methods t-test, chi-square variance test, z-test, wilcoxon test and signal-to-noise ratio (SNR). At first, the preprocessing of gene expression dataset is done and then the reduced number of genes obtained, will be fed as input for A2HP. A2HP utilizes both quantitative and qualitative factors to select the informative genes. Results demonstrate that A2HP selects efficient number of genes as compared to the individual gene selection methods. The percentage of deduction in number of genes and time complexity are taken as the performance measure for the proposed method. And it is shown that A2HP outperforms individual gene selection methods.

基因表达数据集由大量基因标记,包含不同样品条件/时间点下的基因表达值。从这些大数据集中选择信息基因是各种研究人员和生物学家主要关注的问题。在本研究中,我们提出了一种基因选择和降维方法,称为自适应层次分析法(A2HP)。传统的层次分析法是一种基于多准则的决策分析方法,其结果依赖于专家知识或决策者。它主要用于解决不同领域的决策问题。另一方面,A2HP是一种融合了5种个体基因选择排序方法(t检验、卡方方差检验、z检验、wilcoxon检验和信噪比)结果的融合方法。首先对基因表达数据集进行预处理,然后将得到的减少的基因数量作为A2HP的输入。A2HP利用定量因子和定性因子来选择信息基因。结果表明,与单个基因选择方法相比,A2HP选择了更有效的基因数量。以基因数目的扣除百分比和时间复杂度作为该方法的性能指标。结果表明,A2HP优于个体基因选择方法。
{"title":"Informative gene selection using Adaptive Analytic Hierarchy Process (A2HP)","authors":"Abhishek Bhola,&nbsp;Shafa Mahajan,&nbsp;Shailendra Singh","doi":"10.1016/j.fcij.2017.07.004","DOIUrl":"10.1016/j.fcij.2017.07.004","url":null,"abstract":"<div><p>Gene expression dataset derived from microarray experiments are marked by large number of genes, which contains the gene expression values at different sample conditions/time-points. Selection of informative genes from these large datasets is an issue of major concern for various researchers and biologists. In this study, we propose a gene selection and dimensionality reduction method called Adaptive Analytic Hierarchy Process (A2HP). Traditional analytic hierarchy process is a multiple-criteria based decision analysis method whose result depends upon the expert knowledge or decision makers. It is mainly used to solve the decision problems in different fields. On the other hand, A2HP is a fused method that combines the outcomes of five individual gene selection ranking methods t-test, chi-square variance test, z-test, wilcoxon test and signal-to-noise ratio (SNR). At first, the preprocessing of gene expression dataset is done and then the reduced number of genes obtained, will be fed as input for A2HP. A2HP utilizes both quantitative and qualitative factors to select the informative genes. Results demonstrate that A2HP selects efficient number of genes as compared to the individual gene selection methods. The percentage of deduction in number of genes and time complexity are taken as the performance measure for the proposed method. And it is shown that A2HP outperforms individual gene selection methods.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 94-102"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.07.004","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91414392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
An improved rank based disease prediction using web navigation patterns on bio-medical databases 基于生物医学数据库web导航模式的疾病预测改进排名
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.10.003
P. Dhanalakshmi , K. Ramani , B. Eswara Reddy

Applying machine learning techniques to on-line biomedical databases is a challenging task, as this data is collected from large number of sources and it is multi-dimensional. Also retrieval of relevant document from large repository such as gene document takes more processing time and an increased false positive rate. Generally, the extraction of biomedical document is based on the stream of prior observations of gene parameters taken at different time periods. Traditional web usage models such as Markov, Bayesian and Clustering models are sensitive to analyze the user navigation patterns and session identification in online biomedical database. Moreover, most of the document ranking models on biomedical database are sensitive to sparsity and outliers. In this paper, a novel user recommendation system was implemented to predict the top ranked biomedical documents using the disease type, gene entities and user navigation patterns. In this recommendation system, dynamic session identification, dynamic user identification and document ranking techniques were used to extract the highly relevant disease documents on the online PubMed repository. To verify the performance of the proposed model, the true positive rate and runtime of the model was compared with that of traditional static models such as Bayesian and Fuzzy rank. Experimental results show that the performance of the proposed ranking model is better than the traditional models.

将机器学习技术应用于在线生物医学数据库是一项具有挑战性的任务,因为这些数据是从大量来源收集的,并且是多维的。此外,从大型存储库中检索相关文档(如基因文档)需要更多的处理时间和更高的假阳性率。一般来说,生物医学文献的提取是基于在不同时期对基因参数的先前观察流。传统的马尔可夫模型、贝叶斯模型和聚类模型对在线生物医学数据库中的用户导航模式分析和会话识别比较敏感。此外,大多数生物医学数据库的文献排序模型对稀疏度和离群值敏感。本文利用疾病类型、基因实体和用户导航模式,实现了一种新的用户推荐系统来预测排名靠前的生物医学文献。该推荐系统采用动态会话识别、动态用户识别和文档排序技术,从在线PubMed知识库中提取相关度高的疾病文档。为了验证该模型的性能,将该模型的真阳性率和运行时间与传统的静态模型(如贝叶斯和模糊秩)进行了比较。实验结果表明,该排序模型的性能优于传统的排序模型。
{"title":"An improved rank based disease prediction using web navigation patterns on bio-medical databases","authors":"P. Dhanalakshmi ,&nbsp;K. Ramani ,&nbsp;B. Eswara Reddy","doi":"10.1016/j.fcij.2017.10.003","DOIUrl":"10.1016/j.fcij.2017.10.003","url":null,"abstract":"<div><p>Applying machine learning techniques to on-line biomedical databases is a challenging task, as this data is collected from large number of sources and it is multi-dimensional. Also retrieval of relevant document from large repository such as gene document takes more processing time and an increased false positive rate. Generally, the extraction of biomedical document is based on the stream of prior observations of gene parameters taken at different time periods. Traditional web usage models such as Markov, Bayesian and Clustering models are sensitive to analyze the user navigation patterns and session identification in online biomedical database. Moreover, most of the document ranking models on biomedical database are sensitive to sparsity and outliers. In this paper, a novel user recommendation system was implemented to predict the top ranked biomedical documents using the disease type, gene entities and user navigation patterns. In this recommendation system, dynamic session identification, dynamic user identification and document ranking techniques were used to extract the highly relevant disease documents on the online PubMed repository. To verify the performance of the proposed model, the true positive rate and runtime of the model was compared with that of traditional static models such as Bayesian and Fuzzy rank. Experimental results show that the performance of the proposed ranking model is better than the traditional models.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 133-147"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.10.003","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83678070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
A novel fuzzy logic based reverse engineering of gene regulatory network 基于模糊逻辑的基因调控网络逆向工程
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.07.002
Raviajot Kaur, Abhishek Bhola, Shailendra Singh

Genes of an organism play a very crucial role in the working of various cellular activities. Genes and other biological molecules like DNA, RNA do not operate alone but they all are correlated. Their relationships are shown with the help of networks commonly known as Gene Regulatory Networks. Gene Regulatory Networks are complex control networks that show the map of interactions among the genes. They provide very useful contribution to the genomic science and increase the understanding of various biological processes. In this paper, fuzzy logic based method is proposed for the reverse engineering of gene regulatory network from microarray gene expression datasets. Pre-processing steps have been introduced to increase the efficiency of the method. Clustering technique is also employed to divide the problem into sub problems to reduce the computational complexity at some extent. Finally, the proposed method is tested on two different time course gene expression datasets of yeast having GEO accession number GDS37 and GDS3030. The results are validated by using Specificity, Sensitivity and F-score as parameters. Results of the proposed method are further compared with other existing method which was proposed by Al-Shobaili in 2014.

基因在生物体的各种细胞活动中起着至关重要的作用。基因和其他生物分子如DNA、RNA并不是单独起作用的,而是相互关联的。它们之间的关系是通过通常被称为基因调控网络的网络来显示的。基因调控网络是显示基因间相互作用图谱的复杂控制网络。它们为基因组科学提供了非常有用的贡献,并增加了对各种生物过程的理解。本文提出了一种基于模糊逻辑的基因调控网络逆向工程方法。为了提高该方法的效率,还引入了预处理步骤。采用聚类技术将问题分解为子问题,在一定程度上降低了计算复杂度。最后,在GEO加入号为GDS37和GDS3030的酵母基因表达数据集上对该方法进行了验证。以特异性、敏感性和f评分为参数对结果进行验证。将本文方法的结果与Al-Shobaili(2014)提出的其他现有方法进行了比较。
{"title":"A novel fuzzy logic based reverse engineering of gene regulatory network","authors":"Raviajot Kaur,&nbsp;Abhishek Bhola,&nbsp;Shailendra Singh","doi":"10.1016/j.fcij.2017.07.002","DOIUrl":"10.1016/j.fcij.2017.07.002","url":null,"abstract":"<div><p>Genes of an organism play a very crucial role in the working of various cellular activities. Genes and other biological molecules like DNA, RNA do not operate alone but they all are correlated. Their relationships are shown with the help of networks commonly known as Gene Regulatory Networks. Gene Regulatory Networks are complex control networks that show the map of interactions among the genes. They provide very useful contribution to the genomic science and increase the understanding of various biological processes. In this paper, fuzzy logic based method is proposed for the reverse engineering of gene regulatory network from microarray gene expression datasets. Pre-processing steps have been introduced to increase the efficiency of the method. Clustering technique is also employed to divide the problem into sub problems to reduce the computational complexity at some extent. Finally, the proposed method is tested on two different time course gene expression datasets of yeast having GEO accession number GDS37 and GDS3030. The results are validated by using Specificity, Sensitivity and F-score as parameters. Results of the proposed method are further compared with other existing method which was proposed by Al-Shobaili in 2014.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 79-86"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.07.002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75932586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Wavelet based transition region extraction for image segmentation 基于小波变换的图像分割过渡区提取
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.10.005
Priyadarsan Parida, Nilamani Bhoi

Transition region based approaches are recent hybrid segmentation techniques well known for its simplicity and effectiveness. Here, the segmentation effectiveness depends on robust extraction of transition regions. So, we have proposed a transition region method which initially decomposes the gray image in wavelet domain. Two existing transition region approaches are applied on approximate coefficients to extract transition region feature matrix. Using this feature matrix the corresponding prominent wavelet coefficients of different bands are found. Inverse wavelet transform are then applied on the modified coefficients to get edge image with more than one pixel width. Otsu thresholding is applied on it to get transition regions. Further, morphological operations are applied to extract the object regions. Finally, the objects are extracted using the object regions. The wavelet domain approach extracts robust transition regions resulting in better segmentation. The proposed method is compared with different existing image segmentation methods. Experimental results reveal that the proposed method achieve 0.95 overall segmentation accuracy. It also works well for extraction of single as well as multiple objects from images.

基于过渡区域的分割方法是一种新的混合分割方法,以其简单有效而著称。在这里,分割的有效性取决于对过渡区域的鲁棒提取。为此,提出了一种在小波域对灰度图像进行初始分解的过渡区域方法。利用现有的两种近似系数过渡区方法提取过渡区特征矩阵。利用该特征矩阵找到了不同波段对应的显著小波系数。然后对修正系数进行小波反变换,得到宽度大于1像素的边缘图像。对其进行Otsu阈值分割,得到过渡区域。在此基础上,应用形态学操作提取目标区域。最后,使用对象区域提取对象。小波域方法提取鲁棒过渡区域,得到更好的分割效果。将该方法与现有的图像分割方法进行了比较。实验结果表明,该方法总体分割精度达到0.95。它也可以很好地从图像中提取单个和多个对象。
{"title":"Wavelet based transition region extraction for image segmentation","authors":"Priyadarsan Parida,&nbsp;Nilamani Bhoi","doi":"10.1016/j.fcij.2017.10.005","DOIUrl":"10.1016/j.fcij.2017.10.005","url":null,"abstract":"<div><p>Transition region based approaches are recent hybrid segmentation techniques well known for its simplicity and effectiveness. Here, the segmentation effectiveness depends on robust extraction of transition regions. So, we have proposed a transition region method which initially decomposes the gray image in wavelet domain. Two existing transition region approaches are applied on approximate coefficients to extract transition region feature matrix. Using this feature matrix the corresponding prominent wavelet coefficients of different bands are found. Inverse wavelet transform are then applied on the modified coefficients to get edge image with more than one pixel width. Otsu thresholding is applied on it to get transition regions. Further, morphological operations are applied to extract the object regions. Finally, the objects are extracted using the object regions. The wavelet domain approach extracts robust transition regions resulting in better segmentation. The proposed method is compared with different existing image segmentation methods. Experimental results reveal that the proposed method achieve 0.95 overall segmentation accuracy. It also works well for extraction of single as well as multiple objects from images.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 65-78"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.10.005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89386267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 27
Feature level review table generation for E-Commerce websites to produce qualitative rating of the products 生成电子商务网站的特征级评价表,对产品进行定性评价
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.09.002
D.R. Kumar Raja, S. Pushpa

It is widely acknowledged today that E-Commerce business is growing rapidly. This is happened only because of people are completely depending on the ratings and reviews given by the customers who are already purchased and using the products. Online surveys, customer reviews on shopping sites are the key sources to understand customer requirements and feedback to help upgrade the product quality and achieve greater outcomes. Now the challenge is that whether those reviews came from product level or feature level will be the million dollar question. To overcome this problem we are proposing a new algorithm to give feature level rating for the product which is called Feature Level Review Rating Analysis (FLRRA) algorithm.

今天,人们普遍认为电子商务正在迅速发展。这种情况的发生仅仅是因为人们完全依赖于已经购买和使用产品的客户给出的评级和评论。在线调查和购物网站上的客户评论是了解客户需求和反馈的关键来源,有助于提升产品质量并取得更大的成果。现在的挑战是,这些评论是来自产品级别还是功能级别,这将是一个非常重要的问题。为了克服这一问题,我们提出了一种新的产品特征等级评价算法,即特征等级评价分析(FLRRA)算法。
{"title":"Feature level review table generation for E-Commerce websites to produce qualitative rating of the products","authors":"D.R. Kumar Raja,&nbsp;S. Pushpa","doi":"10.1016/j.fcij.2017.09.002","DOIUrl":"10.1016/j.fcij.2017.09.002","url":null,"abstract":"<div><p>It is widely acknowledged today that E-Commerce business is growing rapidly. This is happened only because of people are completely depending on the ratings and reviews given by the customers who are already purchased and using the products. Online surveys, customer reviews on shopping sites are the key sources to understand customer requirements and feedback to help upgrade the product quality and achieve greater outcomes. Now the challenge is that whether those reviews came from product level or feature level will be the million dollar question. To overcome this problem we are proposing a new algorithm to give feature level rating for the product which is called Feature Level Review Rating Analysis (FLRRA) algorithm.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 118-124"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.09.002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75149652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Pentagonal fuzzy number, its properties and application in fuzzy equation 五边形模糊数及其性质及其在模糊方程中的应用
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.09.001
Sankar Prasad Mondal, Manimohan Mandal

The paper presents an adaptation of pentagonal fuzzy number. Different type of pentagonal fuzzy number is formed. The arithmetic operation of a particular type of pentagonal fuzzy number is addressed here. The difference between two pentagonal valued functions is also addressed here. Demonstration of pentagonal fuzzy solutions of fuzzy equation is carried out with the said numbers. Additionally, an illustrative example is also taken with the useful graph and table for usefulness for attained to the proposed concept.

提出了一种五边形模糊数的自适应算法。形成了不同类型的五边形模糊数。本文讨论了一类特殊五边形模糊数的算术运算。两个五边形值函数之间的区别也在这里讨论。用上述数字对模糊方程的五边形模糊解进行了论证。此外,还以图示和表格为例说明了所提出概念的有效性。
{"title":"Pentagonal fuzzy number, its properties and application in fuzzy equation","authors":"Sankar Prasad Mondal,&nbsp;Manimohan Mandal","doi":"10.1016/j.fcij.2017.09.001","DOIUrl":"10.1016/j.fcij.2017.09.001","url":null,"abstract":"<div><p>The paper presents an adaptation of pentagonal fuzzy number. Different type of pentagonal fuzzy number is formed. The arithmetic operation of a particular type of pentagonal fuzzy number is addressed here. The difference between two pentagonal valued functions is also addressed here. Demonstration of pentagonal fuzzy solutions of fuzzy equation is carried out with the said numbers. Additionally, an illustrative example is also taken with the useful graph and table for usefulness for attained to the proposed concept.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 110-117"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.09.001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82414787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 26
A framework for safer driving in Mauritius 毛里求斯的安全驾驶框架
Pub Date : 2017-12-01 DOI: 10.1016/j.fcij.2017.10.002
V. Bassoo , V. Hurbungs , V. Ramnarain-Seetohul , T.P. Fowdur , Y. Beeharry

According to the National Transport Authority (NTA), there were 493,081 registered vehicles in Mauritius in April 2016, which represents a 1.4% annual increase compared to 2015. Despite the sensitization campaigns and the series of measures setup by the Minister of Public Infrastructure and Land Transport, the number of road accidents continues to rise. The three main elements that contribute to accidents are: road infrastructure, vehicle and driver. The driver has the highest contribution in collisions. If the driver is given the right information (e.g. driving behaviour, accident-prone areas and vehicle status) at the right time, he/she can make better driving decisions and react promptly to critical situations. This paper proposes a framework for safer driving in Mauritius that uses an on-board car diagnostic module (OBDII) to collect data such as vehicle average speed, engine revolution and acceleration. This module relays the data to a cloud environment where an adaptive algorithm analyses the data and predicts driver behaviour in real-time. Based on driving behaviour, mobile alerts can be sent to the driver in the form of messages, voice commands or beeps. A survey was also carried out to evaluate the acceptance rate of such a framework by people of different age groups in Mauritius.

根据国家交通管理局(NTA)的数据,2016年4月,毛里求斯有493,081辆注册车辆,比2015年增长1.4%。尽管公共基础设施和陆地运输部开展了宣传活动并采取了一系列措施,但道路事故的数量继续上升。造成事故的三个主要因素是:道路基础设施、车辆和驾驶员。司机对碰撞的贡献最大。如果在适当的时间向司机提供正确的信息(例如驾驶行为、易发生事故的地区和车辆状况),他/她可以做出更好的驾驶决策,并迅速对紧急情况作出反应。本文提出了一个框架,在毛里求斯更安全的驾驶,使用车载诊断模块(OBDII)收集数据,如车辆平均速度,发动机转速和加速度。该模块将数据转发到云环境,在云环境中,自适应算法分析数据并实时预测驾驶员的行为。根据驾驶行为,手机警报可以以信息、语音命令或哔哔声的形式发送给司机。还进行了一项调查,以评估毛里求斯不同年龄组的人对这种框架的接受率。
{"title":"A framework for safer driving in Mauritius","authors":"V. Bassoo ,&nbsp;V. Hurbungs ,&nbsp;V. Ramnarain-Seetohul ,&nbsp;T.P. Fowdur ,&nbsp;Y. Beeharry","doi":"10.1016/j.fcij.2017.10.002","DOIUrl":"10.1016/j.fcij.2017.10.002","url":null,"abstract":"<div><p>According to the National Transport Authority (NTA), there were 493,081 registered vehicles in Mauritius in April 2016, which represents a 1.4% annual increase compared to 2015. Despite the sensitization campaigns and the series of measures setup by the Minister of Public Infrastructure and Land Transport, the number of road accidents continues to rise. The three main elements that contribute to accidents are: road infrastructure, vehicle and driver. The driver has the highest contribution in collisions. If the driver is given the right information (e.g. driving behaviour, accident-prone areas and vehicle status) at the right time, he/she can make better driving decisions and react promptly to critical situations. This paper proposes a framework for safer driving in Mauritius that uses an on-board car diagnostic module (OBDII) to collect data such as vehicle average speed, engine revolution and acceleration. This module relays the data to a cloud environment where an adaptive algorithm analyses the data and predicts driver behaviour in real-time. Based on driving behaviour, mobile alerts can be sent to the driver in the form of messages, voice commands or beeps. A survey was also carried out to evaluate the acceptance rate of such a framework by people of different age groups in Mauritius.</p></div>","PeriodicalId":100561,"journal":{"name":"Future Computing and Informatics Journal","volume":"2 2","pages":"Pages 125-132"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.fcij.2017.10.002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79786989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
期刊
Future Computing and Informatics Journal
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1