发布求助
文献互助 智能选刊 最新文献

Comput. Sci. J. Moldova最新文献

筛选
英文 中文
Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray 胸部x线检测Covid-19的四联体丢失和挤压检测
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.12
Pranshav Gajjar, Naishadh Mehta, Pooja Shah
{"title":"Quadruplet loss and SqueezeNets for Covid-19 detection from Chest-X ray","authors":"Pranshav Gajjar, Naishadh Mehta, Pooja Shah","doi":"10.56415/csjm.v30.12","DOIUrl":"https://doi.org/10.56415/csjm.v30.12","url":null,"abstract":"The Coronavirus Pandemic triggered by SARS-CoV-2 has wreaked havoc on the planet and is expanding exponentially. While scanning methods, including CT scans and chest X-rays, are commonly used, artificial intelligence implementations are also deployed for COVID-based pneumonia detection. Due to image biases in X-ray data, bilateral filtration and Histogram Equalization are used followed by lung segmentation by a U-Net, which successfully segmented 83.2% of the collected dataset. The segmented lungs are fed into a Quadruplet Network with SqueezeNet encoders for increased computational efficiency and high-level embeddings generation. The embeddings are computed using a Multi-Layer Perceptron and visualized by T-SNE (T-Distributed Stochastic Neighbor Embedding) scatterplots. The proposed research results in a 94.6% classifying accuracy which is 2% more than the baseline Convolutional Neural Network and a 90.2% decrease in prediction time.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116310135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Identities and generalized derivatives of quasigroups 拟群的恒等式与广义导数
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.10
G. Horosh, N. Malyutina, A. Scerbacova, Victor Scerbacov
{"title":"Identities and generalized derivatives of quasigroups","authors":"G. Horosh, N. Malyutina, A. Scerbacova, Victor Scerbacov","doi":"10.56415/csjm.v30.10","DOIUrl":"https://doi.org/10.56415/csjm.v30.10","url":null,"abstract":"We associate a partial (autostrophical) identity with every generalized derivative. We research when a quasigroup that satisfies an autostrophic identity has a unit (left or/and right or/and middle).","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130230427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Domination Parameters on a kind of the regular honeycomb structure 一种规则蜂窝结构的控制参数
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.13
F. Movahedi, K. K. Choong, M. Akhbari
{"title":"The Domination Parameters on a kind of the regular honeycomb structure","authors":"F. Movahedi, K. K. Choong, M. Akhbari","doi":"10.56415/csjm.v30.13","DOIUrl":"https://doi.org/10.56415/csjm.v30.13","url":null,"abstract":"The honeycomb mesh, based on hexagonal structure, has enormous applications in chemistry and engineering. A major challenge in this field is to understand the unique properties of honeycomb structures, which depend on their properties of topology. One of the important concepts in graph theory is the domination number which can be used for network control and monitoring. In this paper, we investigate the domination number of the honeycomb network. For this purpose, the domination number, the total domination number, the independent domination number, the connected domination number and the doubly connected domination number of the honeycomb are obtained. Finally, in some honeycomb structures of real models, we obtain the exact amount of these parameters.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129230521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Degree of favoring in apportionments 分配中的偏爱程度
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.11
Ion Bolun
{"title":"Degree of favoring in apportionments","authors":"Ion Bolun","doi":"10.56415/csjm.v30.11","DOIUrl":"https://doi.org/10.56415/csjm.v30.11","url":null,"abstract":"To quantitatively estimate the degree of favoring the beneficiaries in proportional apportionments of entities of the same kind (seats, PCs, etc.), five quantitative criteria were defined. By computer simulation, the degree of favoring the large or small beneficiaries by 6 apportionment methods is identified. Thus, favoring large beneficiaries by the d’Hondt method can overpass 10.7-12.1 entities (entities in excess) and that of small beneficiaries by the Huntington-Hill method -- 2.7-11.0 entities, and by the Adapted Sainte-Lagu\"{e} method -- 1.7-9.7 entities. The Huntington-Hill method favors small beneficiaries up to 5.70 times stronger than the Adapted Sainte-Laguë one does. Also, the d’Hondt method favors beneficiaries (the large ones) much stronger than the Adapted Sainte-Laguë one does (the small ones) -- for very many cases the respective ratio exceeds 10 times.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122510431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
On Elimination of Erasing Rules from E0S Grammars E0S语法中擦除规则的消除
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.08
A. Meduna, Martin Havel
{"title":"On Elimination of Erasing Rules from E0S Grammars","authors":"A. Meduna, Martin Havel","doi":"10.56415/csjm.v30.08","DOIUrl":"https://doi.org/10.56415/csjm.v30.08","url":null,"abstract":"The present paper describes an alternative algorithm for the removal of erasing rules from E0S grammars. As opposed to the standard way of eliminating erasing rules in most E0S-like grammars, such as context-free grammars, this method requires no predetermination of symbols that derive the empty string. The proposed algorithm is formally verified. In the conclusion of the paper, the applicability of the algorithm to E0S grammars that work in a semi-parallel way is demonstrated. Furthermore, two open problems are formulated.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115297291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Comparative study on classification performance of Emphysema with transfer learning methods in deep convolutional neural networks 深度卷积神经网络中迁移学习与肺气肿分类性能的比较研究
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.15
Selçuk Yazar
{"title":"A Comparative study on classification performance of Emphysema with transfer learning methods in deep convolutional neural networks","authors":"Selçuk Yazar","doi":"10.56415/csjm.v30.15","DOIUrl":"https://doi.org/10.56415/csjm.v30.15","url":null,"abstract":"Today Emphysema, which takes place among the top five diseases, is encountered in the western world in terms of rehabilitation and healthcare costs. Diagnosis of this type of respiratory tract disease with the help of computers is gradually increasing its importance. In this study, we aimed to classify it with the transfer learning method by using single labeled emphysema diagnosed data which is obtained from three large data sets. We classified the images that are obtained from ChestX-ray14, CheXpert, and PadChest databases by 95% of Area Under the Curve (AUC) with the fully connected layer model and DenseNet-121 pre-trained neural network and 90% of Area Under the Curve (AUC) with Xception pre-trained neural network. We evaluated this proposed deep learning-based model as an effective and practical diagnostic tool for emphysema alone, using x-ray data. Notably, transfer learning is a very functional approach in terms of differentiation between normal and patient in similar diseases that have just emerged in the pandemic period that we live in.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116087670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Split logarithm problem and a candidate for a post-quantum signature scheme 分割对数问题及其后量子签名方案的候选方案
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.14
A. Moldovyan, N. A. Moldovyan
{"title":"Split logarithm problem and a candidate for a post-quantum signature scheme","authors":"A. Moldovyan, N. A. Moldovyan","doi":"10.56415/csjm.v30.14","DOIUrl":"https://doi.org/10.56415/csjm.v30.14","url":null,"abstract":"A new form of the hidden discrete logarithm problem, called split logarithm problem, is introduced as primitive of practical post-quantum digital signature schemes, which is characterized in using two non-permutable elements $A$ and $B$ of a finite non-commutative associative algebra, which are used to compute generators $Q=AB$ and $G=BQ$ of two finite cyclic groups of prime order $q$. The public key is calculated as a triple of vectors $(Y,Z,T)$: $Y=Q^x$, $Z=G^w$, and $T=Q^aB^{-1}G^b$, where $x$, $w$, $a$, and $b$ are random integers. Security of the signature scheme is defined by the computational difficulty of finding the pair of integers $(x,w)$, although, using a quantum computer, one can easily find the ratio $x/wbmod q$.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114214862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Vehicle Detection from Unmanned Aerial Images with Deep Mask R-CNN 基于深度掩模的无人机图像车辆检测
Comput. Sci. J. Moldova Pub Date : 2022-07-01 DOI: 10.56415/csjm.v30.09
R. Yayla, Emir Albayrak, Uğur Yüzgeç
{"title":"Vehicle Detection from Unmanned Aerial Images with Deep Mask R-CNN","authors":"R. Yayla, Emir Albayrak, Uğur Yüzgeç","doi":"10.56415/csjm.v30.09","DOIUrl":"https://doi.org/10.56415/csjm.v30.09","url":null,"abstract":"In this paper, a classification approach which is applied to Mask Region-based Convolutional Neural Network as deeper is proposed for vehicle detection on the images from UAV instead of the familiar methods. The different types of unmanned aerial vehicles are widely used for a lot of areas such as agricultural spraying, advertisement shooting, fire extinguishing, transportation and surveillance, exploration, destruction for the military. In recent years, deep learning techniques are progressively developed for object detection. Segmentation algorithms based on CNN architecture are especially widely used for extracting meaningful parts of an image. Additionally, Mask R-CNN based on CNN architecture rapidly detects the object with high-accuracy on an image. This study shows that the high-accuracy results are obtained when the Mask R-CNN is applied as deeper in vehicle detection on the images taken by UAV.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121964204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Revisiting the Role of Classical Readability Formulae Parameters in Complex Word Identification (Part 2) 经典易读性公式参数在复杂词识别中的作用(下)
Comput. Sci. J. Moldova Pub Date : 2022-02-01 DOI: 10.56415/csjm.v30.03
G. Venugopal, Dhanya Pramod, Jatinderkumar R. Saini
{"title":"Revisiting the Role of Classical Readability Formulae Parameters in Complex Word Identification (Part 2)","authors":"G. Venugopal, Dhanya Pramod, Jatinderkumar R. Saini","doi":"10.56415/csjm.v30.03","DOIUrl":"https://doi.org/10.56415/csjm.v30.03","url":null,"abstract":"Accessibility of text is an attribute that deserves the attention of researchers and content creators. This study is an attempt to determine the lexical features that play a key role in identifying complex words in Hindi text. As the first step, we studied the parameters used in readability metrics in different languages and tested their importance on classifiers built on datasets created with the help of a user study. In part of the study, we reported the results of two different approaches used to label a word as complex. In this part, we compare the previous results with the results obtained from a third labeling approach. We found satisfactory evidence for certain parameters and also observed a new parameter that could be used while devising readability metrics for Hindi.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"1702 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127452187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
A hybrid deep learning and handcrafted feature approach for the prediction of protein structural class 一种用于预测蛋白质结构类的混合深度学习和手工特征方法
Comput. Sci. J. Moldova Pub Date : 2022-02-01 DOI: 10.56415/csjm.v30.06
Rached Yagoubi, A. Moussaoui, M. Yagoubi
{"title":"A hybrid deep learning and handcrafted feature approach for the prediction of protein structural class","authors":"Rached Yagoubi, A. Moussaoui, M. Yagoubi","doi":"10.56415/csjm.v30.06","DOIUrl":"https://doi.org/10.56415/csjm.v30.06","url":null,"abstract":"The knowledge of the protein structural class is one of the most important sources of information related to protein structure or that about function analysis and drug design. But researchers still face difficulties to predict the protein structural class when it is a question about low-similarity sequences. In this paper, we propose to make the prediction using a hybrid deep learning method and handcrafted features instead of shallow classifier. We input only nine features, mostly from predicted secondary structure information, to a feed-forward deep neural network. The latter will automatically explore and extend those features through many layers and discover the representations needed for classification. The obtained results, when applying the jackknife test on two low-similarity benchmark datasets (25PDB and FC699), proved to be very significant. After comparing our method to others, it has turned out that using deep learning methods affords satisfactory performance in the field of protein structural class prediction.","PeriodicalId":262087,"journal":{"name":"Comput. Sci. J. Moldova","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134394882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信