首页 > 最新文献

Journal of Electronic Science and Technology最新文献

英文 中文
Dolphin vocal sound generation via deep WaveGAN 海豚的声音产生通过深波根
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100171
Lue Zhang , Hai-Ning Huang , Li Yin , Bao-Qi Li , Di Wu , Hao-Ran Liu , Xi-Feng Li , Yong-Le Xie

The marine biological sonar system evolved in the struggle of nature is far superior to the current artificial sonar. Therefore, the development of bionic underwater concealed detection is of great strategic significance to the military and economy. In this paper, a generative adversarial network (GAN) is trained based on the dolphin vocal sound dataset we constructed, which can achieve unsupervised generation of dolphin vocal sounds with global consistency. Through the analysis of the generated audio samples and the real audio samples in the time domain and the frequency domain, it can be proven that the generated audio samples are close to the real audio samples, which meets the requirements of bionic underwater concealed detection.

海洋生物声纳系统在与大自然的斗争中进化而来,远远优于目前的人工声纳。因此,发展仿生水下隐蔽探测技术对军事和经济都具有重要的战略意义。本文以构建的海豚声音数据集为基础,训练生成式对抗网络(GAN),实现无监督生成具有全局一致性的海豚声音。通过对生成的音频样本和真实音频样本在时域和频域的分析,可以证明生成的音频样本接近真实音频样本,满足仿生水下隐蔽检测的要求。
{"title":"Dolphin vocal sound generation via deep WaveGAN","authors":"Lue Zhang ,&nbsp;Hai-Ning Huang ,&nbsp;Li Yin ,&nbsp;Bao-Qi Li ,&nbsp;Di Wu ,&nbsp;Hao-Ran Liu ,&nbsp;Xi-Feng Li ,&nbsp;Yong-Le Xie","doi":"10.1016/j.jnlest.2022.100171","DOIUrl":"10.1016/j.jnlest.2022.100171","url":null,"abstract":"<div><p>The marine biological sonar system evolved in the struggle of nature is far superior to the current artificial sonar. Therefore, the development of bionic underwater concealed detection is of great strategic significance to the military and economy. In this paper, a generative adversarial network (GAN) is trained based on the dolphin vocal sound dataset we constructed, which can achieve unsupervised generation of dolphin vocal sounds with global consistency. Through the analysis of the generated audio samples and the real audio samples in the time domain and the frequency domain, it can be proven that the generated audio samples are close to the real audio samples, which meets the requirements of bionic underwater concealed detection.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000246/pdfft?md5=2570662ea1de4d606f71aca4e0d5a856&pid=1-s2.0-S1674862X22000246-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41457879","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: 5
Co-occurrence histogram based ensemble of classifiers for classification of cervical cancer cells 基于共现直方图的子宫颈癌症细胞分类分类器集成
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100170
Rajesh Yakkundimath , Varsha Jadhav , Basavaraj Anami , Naveen Malvade

To explore the potential of conventional image processing techniques in the classification of cervical cancer cells, in this work, a co-occurrence histogram method was employed for image feature extraction and an ensemble classifier was developed by combining the base classifiers, namely, the artificial neural network (ANN), random forest (RF), and support vector machine (SVM), for image classification. The segmented pap-smear cell image dataset was constructed by the k-means clustering technique and used to evaluate the performance of the ensemble classifier which was formed by the combination of the above considered base classifiers. The result was also compared with that achieved by the individual base classifiers as well as that trained with color, texture, and shape features. The maximum average classification accuracy of 93.44% was obtained when the ensemble classifier was applied and trained with co-occurrence histogram features, which indicates that the ensemble classifier trained with the co-occurrence histogram features is more suitable for the classification of cervical cancer cells.

为了探索传统图像处理技术在宫颈癌细胞分类中的潜力,本研究采用共现直方图方法进行图像特征提取,并将人工神经网络(ANN)、随机森林(RF)和支持向量机(SVM)等基础分类器相结合,开发了一种集成分类器进行图像分类。采用k-means聚类技术构建分割后的pap-smear细胞图像数据集,并利用该数据集评价由上述基分类器组合而成的集成分类器的性能。结果还与单个基本分类器以及使用颜色、纹理和形状特征训练的分类器所获得的结果进行了比较。采用共现直方图特征训练的集成分类器的最大平均分类准确率为93.44%,说明用共现直方图特征训练的集成分类器更适合于宫颈癌细胞的分类。
{"title":"Co-occurrence histogram based ensemble of classifiers for classification of cervical cancer cells","authors":"Rajesh Yakkundimath ,&nbsp;Varsha Jadhav ,&nbsp;Basavaraj Anami ,&nbsp;Naveen Malvade","doi":"10.1016/j.jnlest.2022.100170","DOIUrl":"10.1016/j.jnlest.2022.100170","url":null,"abstract":"<div><p>To explore the potential of conventional image processing techniques in the classification of cervical cancer cells, in this work, a co-occurrence histogram method was employed for image feature extraction and an ensemble classifier was developed by combining the base classifiers, namely, the artificial neural network (ANN), random forest (RF), and support vector machine (SVM), for image classification. The segmented pap-smear cell image dataset was constructed by the <em>k</em>-means clustering technique and used to evaluate the performance of the ensemble classifier which was formed by the combination of the above considered base classifiers. The result was also compared with that achieved by the individual base classifiers as well as that trained with color, texture, and shape features. The maximum average classification accuracy of 93.44% was obtained when the ensemble classifier was applied and trained with co-occurrence histogram features, which indicates that the ensemble classifier trained with the co-occurrence histogram features is more suitable for the classification of cervical cancer cells.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000234/pdfft?md5=a18c8261116b4410accd50218fea4186&pid=1-s2.0-S1674862X22000234-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47107997","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
Growth of Fe-doped and V-doped MoS2 and their magnetic-electrical effects fe掺杂和v掺杂MoS2的生长及其磁电效应
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100167
Rui Tao , Zhi-Hao Yang , Chao Tan , Xin Hao , Zun-Gui Ke , Lei Yang , Li-Ping Dai , Xin-Wu Deng , Ping-Jian Li , Ze-Gao Wang

Magnetism in two-dimensional (2D) materials has attracted much attention recently. However, intrinsic magnetic 2D materials are rare and mostly unstable in ambient. Although heteroatom doping can introduce magnetism, the basic property especially the electrical-magnetic coupling property has been rarely revealed. Herein, both iron (Fe)-doped and vanadium (V)-doped MoS2 films were grown by chemical vapor deposition. Through studying the structure and electrical property of Fe-doped and V-doped MoS2, it was found that both Fe and V doping would decrease the electron concentration, exhibiting a p-type doping effect. Significantly, V-doped MoS2 displays a p-type conduction behavior. Although the carrier mobility decreases after heteroatom doping, both Fe and V doping could endow MoS2 with magnetism, in which the transfer curves of both MoS2 transistors exhibit a strong magnetic-dependent behavior. It is found that the magnetic response of Fe-doped MoS2 can be tuned from ~0.2 ​nA/T to ~1.3 ​nA/T, with the tunability much larger than that of V-doped MoS2. At last, the magnetic mechanism is discussed with the local magnetic property performed by magnetic force microscopy. The typical morphology-independent magnetic signal demonstrates the formed magnetic domain structure in Fe-doped MoS2. This study opens new potential to design novel magnetic-electrical devices.

近年来,二维材料中的磁性问题引起了人们的广泛关注。然而,本征磁性二维材料非常罕见,且大多在环境中不稳定。杂原子掺杂虽然可以引入磁性,但其基本性质特别是电-磁耦合性质却很少被揭示。本文采用化学气相沉积的方法制备了掺杂铁(Fe)和掺杂钒(V)的MoS2薄膜。通过对Fe掺杂和V掺杂MoS2的结构和电学性质的研究,发现Fe和V掺杂都会降低电子浓度,表现为p型掺杂效应。值得注意的是,v掺杂的MoS2表现出p型导电行为。虽然杂原子掺杂后载流子迁移率降低,但Fe和V的掺杂都能使MoS2具有磁性,其中两种MoS2晶体管的转移曲线都表现出较强的磁依赖行为。结果表明,铁掺杂MoS2的磁响应可以从~0.2 nA/T调谐到~1.3 nA/T,其可调性远高于v掺杂MoS2。最后,利用磁力显微镜对其局部磁性能进行了分析。铁掺杂二硫化钼形成的磁畴结构与典型的磁信号无关。这项研究为设计新型磁电器件开辟了新的潜力。
{"title":"Growth of Fe-doped and V-doped MoS2 and their magnetic-electrical effects","authors":"Rui Tao ,&nbsp;Zhi-Hao Yang ,&nbsp;Chao Tan ,&nbsp;Xin Hao ,&nbsp;Zun-Gui Ke ,&nbsp;Lei Yang ,&nbsp;Li-Ping Dai ,&nbsp;Xin-Wu Deng ,&nbsp;Ping-Jian Li ,&nbsp;Ze-Gao Wang","doi":"10.1016/j.jnlest.2022.100167","DOIUrl":"10.1016/j.jnlest.2022.100167","url":null,"abstract":"<div><p>Magnetism in two-dimensional (2D) materials has attracted much attention recently. However, intrinsic magnetic 2D materials are rare and mostly unstable in ambient. Although heteroatom doping can introduce magnetism, the basic property especially the electrical-magnetic coupling property has been rarely revealed. Herein, both iron (Fe)-doped and vanadium (V)-doped MoS<sub>2</sub> films were grown by chemical vapor deposition. Through studying the structure and electrical property of Fe-doped and V-doped MoS<sub>2</sub>, it was found that both Fe and V doping would decrease the electron concentration, exhibiting a p-type doping effect. Significantly, V-doped MoS<sub>2</sub> displays a p-type conduction behavior. Although the carrier mobility decreases after heteroatom doping, both Fe and V doping could endow MoS<sub>2</sub> with magnetism, in which the transfer curves of both MoS<sub>2</sub> transistors exhibit a strong magnetic-dependent behavior. It is found that the magnetic response of Fe-doped MoS<sub>2</sub> can be tuned from ~0.2 ​nA/T to ~1.3 ​nA/T, with the tunability much larger than that of V-doped MoS<sub>2</sub>. At last, the magnetic mechanism is discussed with the local magnetic property performed by magnetic force microscopy. The typical morphology-independent magnetic signal demonstrates the formed magnetic domain structure in Fe-doped MoS<sub>2</sub>. This study opens new potential to design novel magnetic-electrical devices.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000209/pdfft?md5=cb6a58f17581cf3943c882e763bcc8ef&pid=1-s2.0-S1674862X22000209-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43700977","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: 1
Feature layer fusion of linear features and empirical mode decomposition of human EMG signal 基于线性特征与经验模态分解的肌电信号特征层融合
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100169
Jun-Yao Wang , Yue-Hong Dai , Xia-Xi Si

To explore the influence of the fusion of different features on recognition, this paper took the electromyogram (EMG) signals of rectus femoris under different motions (walk, step, ramp, squat, and sitting) as signals, linear features (time-domain features (variance (VAR) and root mean square (RMS)), frequency-domain features (mean frequency (MF) and mean power frequency (MPF)), and nonlinear features (EMD) of the signals were extracted. Two feature fusion algorithms, the series splicing method and complex vector method, were designed, which were verified by a double hidden layer error back propagation (BP) neural network. Results show that with the increase of the types and complexity of feature fusions, the recognition rate of the EMG signal to actions is gradually improved. When the EMG signal is used in the series splicing method, the recognition rate of time-domain ​+ ​frequency-domain ​+ ​empirical mode decomposition (TD ​+ ​FD ​+ ​EMD) splicing is the highest, and the average recognition rate is 92.32%. And this value is raised to 96.1% by using the complex vector method, and the variance of the BP system is also reduced.

为了探讨不同特征融合对识别的影响,本文以不同运动(步行、踏步、坡道、蹲坐)下的股直肌肌电图(EMG)信号为信号,提取信号的线性特征(时域特征(方差(VAR)和均方根(RMS))、频域特征(平均频率(MF)和平均工频(MPF))和非线性特征(EMD)。设计了序列拼接法和复向量法两种特征融合算法,并用双隐层误差反向传播(BP)神经网络进行了验证。结果表明,随着特征融合类型和复杂度的增加,肌电信号对动作的识别率逐渐提高。采用序列拼接方法对肌电信号进行拼接时,时域+频域+经验模态分解(TD + FD + EMD)拼接的识别率最高,平均识别率为92.32%。采用复向量法将该值提高到96.1%,同时也减小了BP系统的方差。
{"title":"Feature layer fusion of linear features and empirical mode decomposition of human EMG signal","authors":"Jun-Yao Wang ,&nbsp;Yue-Hong Dai ,&nbsp;Xia-Xi Si","doi":"10.1016/j.jnlest.2022.100169","DOIUrl":"10.1016/j.jnlest.2022.100169","url":null,"abstract":"<div><p>To explore the influence of the fusion of different features on recognition, this paper took the electromyogram (EMG) signals of rectus femoris under different motions (walk, step, ramp, squat, and sitting) as signals, linear features (time-domain features (variance (VAR) and root mean square (RMS)), frequency-domain features (mean frequency (MF) and mean power frequency (MPF)), and nonlinear features (<strong>EMD</strong>) of the signals were extracted. Two feature fusion algorithms, the series splicing method and complex vector method, were designed, which were verified by a double hidden layer error back propagation (BP) neural network. Results show that with the increase of the types and complexity of feature fusions, the recognition rate of the EMG signal to actions is gradually improved. When the EMG signal is used in the series splicing method, the recognition rate of time-domain ​+ ​frequency-domain ​+ ​empirical mode decomposition (<strong>TD</strong> ​+ ​<strong>FD</strong> ​+ ​<strong>EMD</strong>) splicing is the highest, and the average recognition rate is 92.32%. And this value is raised to 96.1% by using the complex vector method, and the variance of the BP system is also reduced.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000222/pdfft?md5=0e841e358d19a8069ba87cc3d767160f&pid=1-s2.0-S1674862X22000222-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46076651","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: 2
Simple ultrasonic-assisted clean graphene transfer 简单的超声波辅助清洁石墨烯转移
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100168
Zhuo-Cheng Zhang , Xiao-Qiu-Yan Zhang , Min Hu

Clean graphene transfer has received widespread research attention, where most methods are focused on cleaning the upper surface of graphene to improve the transfer technique. However, the residue formation on the bottom surface of graphene is also inevitable; therefore, cleaning the bottom surface is crucial. In this study, we proposed an improved graphene wet transfer method using an ultrasonic processing (UP) step for etching copper (Cu). Using this method, the bottom surface can be cleaned efficiently. The results of atomic force microscopy (AFM) and Raman spectroscopy mapping revealed that the graphene films transferred with UP had smoother and cleaner surfaces, less contamination, and higher quality than those transferred without UP.

清洁石墨烯转移已经受到了广泛的研究关注,大多数方法都集中在清洁石墨烯的上表面来改进转移技术。然而,石墨烯底表面的残留物形成也是不可避免的;因此,清洁底面是至关重要的。在这项研究中,我们提出了一种改进的石墨烯湿转移方法,使用超声波加工(UP)步骤蚀刻铜(Cu)。使用该方法,可以有效地清洗底面。原子力显微镜(AFM)和拉曼光谱成像的结果表明,与没有UP转移的石墨烯膜相比,UP转移的石墨烯膜表面更光滑,更清洁,污染更少,质量更高。
{"title":"Simple ultrasonic-assisted clean graphene transfer","authors":"Zhuo-Cheng Zhang ,&nbsp;Xiao-Qiu-Yan Zhang ,&nbsp;Min Hu","doi":"10.1016/j.jnlest.2022.100168","DOIUrl":"10.1016/j.jnlest.2022.100168","url":null,"abstract":"<div><p>Clean graphene transfer has received widespread research attention, where most methods are focused on cleaning the upper surface of graphene to improve the transfer technique. However, the residue formation on the bottom surface of graphene is also inevitable; therefore, cleaning the bottom surface is crucial. In this study, we proposed an improved graphene wet transfer method using an ultrasonic processing (UP) step for etching copper (Cu). Using this method, the bottom surface can be cleaned efficiently. The results of atomic force microscopy (AFM) and Raman spectroscopy mapping revealed that the graphene films transferred with UP had smoother and cleaner surfaces, less contamination, and higher quality than those transferred without UP.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000210/pdfft?md5=7d510e9d66142b20eb18d3f10a45e87f&pid=1-s2.0-S1674862X22000210-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41534905","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: 1
Framework for COVID-19 segmentation and classification based on deep learning of computed tomography lung images 基于计算机断层肺图像深度学习的COVID-19分割分类框架
Q1 Engineering Pub Date : 2022-09-01 DOI: 10.1016/j.jnlest.2022.100161
Wessam M. Salama , Moustafa H. Aly

Corona Virus Disease 2019 (COVID-19) has affected millions of people worldwide and caused more than 6.3 million deaths (World Health Organization, June 2022). Increased attempts have been made to develop deep learning methods to diagnose COVID-19 based on computed tomography (CT) lung images. It is a challenge to reproduce and obtain the CT lung data, because it is not publicly available. This paper introduces a new generalized framework to segment and classify CT images and determine whether a patient is tested positive or negative for COVID-19 based on lung CT images. In this work, many different strategies are explored for the classification task. ResNet50 and VGG16 models are applied to classify CT lung images into COVID-19 positive or negative. Also, VGG16 and ReNet50 combined with U-Net, which is one of the most used architectures in deep learning for image segmentation, are employed to segment CT lung images before the classifying process to increase system performance. Moreover, the image size dependent normalization technique (ISDNT) and Wiener filter are utilized as the preprocessing techniques to enhance images and noise suppression. Additionally, transfer learning and data augmentation techniques are performed to solve the problem of COVID-19 CT lung images deficiency, therefore the over-fitting of deep models can be avoided. The proposed frameworks, which comprise of, end-to-end, VGG16, ResNet50, and U-Net with VGG16 or ResNet50, are applied on the dataset which is sourced from COVID-19 lung CT images in Kaggle. The classification results show that using the preprocessed CT lung images as the input for U-Net hybrid with ResNet50 achieves the best performance. The proposed classification model achieves 98.98% accuracy (ACC), 98.87% area under the ROC curve (AUC), 98.89% sensitivity (Se), 97.99% precision (Pr), 97.88% F1- score, and 1.8974-second computational time.

2019冠状病毒病(COVID-19)已影响全球数百万人,造成630多万人死亡(世界卫生组织,2022年6月)。人们越来越多地尝试开发基于计算机断层扫描(CT)肺部图像诊断COVID-19的深度学习方法。复制和获得CT肺数据是一个挑战,因为它不是公开的。本文介绍了一种新的广义框架来分割和分类CT图像,并根据肺部CT图像确定患者的COVID-19检测是阳性还是阴性。在这项工作中,探索了许多不同的分类任务策略。采用ResNet50和VGG16模型对CT肺部图像进行COVID-19阳性和阴性分类。并结合深度学习中最常用的图像分割架构之一的U-Net,利用VGG16和rennet50在分类前对CT肺部图像进行分割,提高系统性能。此外,利用图像大小相关归一化技术(ISDNT)和维纳滤波作为预处理技术来增强图像和抑制噪声。此外,通过迁移学习和数据增强技术解决了COVID-19 CT肺部图像不足的问题,避免了深度模型的过拟合。所提出的框架包括端到端、VGG16、ResNet50和带VGG16或ResNet50的U-Net框架,并应用于来自Kaggle的COVID-19肺部CT图像的数据集。分类结果表明,使用预处理后的CT肺图像作为U-Net混合ResNet50算法的输入,分类效果最好。该分类模型的准确率(ACC)为98.98%,ROC曲线下面积(AUC)为98.87%,灵敏度(Se)为98.89%,精度(Pr)为97.99%,F1-得分为97.88%,计算时间为1.8974 s。
{"title":"Framework for COVID-19 segmentation and classification based on deep learning of computed tomography lung images","authors":"Wessam M. Salama ,&nbsp;Moustafa H. Aly","doi":"10.1016/j.jnlest.2022.100161","DOIUrl":"10.1016/j.jnlest.2022.100161","url":null,"abstract":"<div><p>Corona Virus Disease 2019 (COVID-19) has affected millions of people worldwide and caused more than 6.3 million deaths (World Health Organization, June 2022). Increased attempts have been made to develop deep learning methods to diagnose COVID-19 based on computed tomography (CT) lung images. It is a challenge to reproduce and obtain the CT lung data, because it is not publicly available. This paper introduces a new generalized framework to segment and classify CT images and determine whether a patient is tested positive or negative for COVID-19 based on lung CT images. In this work, many different strategies are explored for the classification task. ResNet50 and VGG16 models are applied to classify CT lung images into COVID-19 positive or negative. Also, VGG16 and ReNet50 combined with U-Net, which is one of the most used architectures in deep learning for image segmentation, are employed to segment CT lung images before the classifying process to increase system performance. Moreover, the image size dependent normalization technique (ISDNT) and Wiener filter are utilized as the preprocessing techniques to enhance images and noise suppression. Additionally, transfer learning and data augmentation techniques are performed to solve the problem of COVID-19 CT lung images deficiency, therefore the over-fitting of deep models can be avoided. The proposed frameworks, which comprise of, end-to-end, VGG16, ResNet50, and U-Net with VGG16 or ResNet50, are applied on the dataset which is sourced from COVID-19 lung CT images in Kaggle. The classification results show that using the preprocessed CT lung images as the input for U-Net hybrid with ResNet50 achieves the best performance. The proposed classification model achieves 98.98% accuracy (ACC), 98.87% area under the ROC curve (AUC), 98.89% sensitivity (Se), 97.99% precision (Pr), 97.88% <em>F</em><sub>1</sub>- score, and 1.8974-second computational time.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000143/pdfft?md5=ab3b5702d4ce126d6b35c5ff609a0562&pid=1-s2.0-S1674862X22000143-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42961973","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: 12
Investigating the relevance of Arabic text classification datasets based on supervised learning 基于监督学习的阿拉伯语文本分类数据集的相关性研究
Q1 Engineering Pub Date : 2022-06-01 DOI: 10.1016/j.jnlest.2022.100160
Ahmad Hussein Ababneh

Training and testing different models in the field of text classification mainly depend on the pre-classified text document datasets. Recently, seven datasets have emerged for Arabic text classification, including Single-Label Arabic News Articles Dataset (SANAD), Khaleej, Arabiya, Akhbarona, KALIMAT, Waten2004, and Khaleej2004. This study investigates which of these datasets can provide significant training and fair evaluation for text classification. In this investigation, well-known and accurate learning models are used, including naive Bayes, random forest, K-nearest neighbor, support vector machines, and logistic regression models. We present relevance and time measures of training the models with these datasets to enable Arabic language researchers to select the appropriate dataset to use based on a solid basis of comparison. The performances of the five learning models across the seven datasets are measured and compared with the performance of the same models trained on a well-known English language dataset. The analysis of the relevance and time scores shows that training the support vector machine model on Khaleej and Arabiya obtained the most significant results in the shortest amount of time, with the accuracy of 82%.

文本分类领域中不同模型的训练和测试主要依赖于预分类的文本文档数据集。最近,出现了七个用于阿拉伯语文本分类的数据集,包括单标签阿拉伯语新闻文章数据集(SANAD)、Khaleej、Arabiya、Akhbarona、KALIMAT、Waten2004和Khaleej2004。本研究探讨了哪些数据集可以为文本分类提供重要的训练和公平的评估。在这项研究中,使用了众所周知的和准确的学习模型,包括朴素贝叶斯,随机森林,k近邻,支持向量机和逻辑回归模型。我们提出了用这些数据集训练模型的相关性和时间度量,使阿拉伯语研究人员能够在坚实的比较基础上选择合适的数据集来使用。这五个学习模型在七个数据集上的表现被测量,并与在一个知名的英语语言数据集上训练的相同模型的表现进行比较。对相关性和时间分数的分析表明,在Khaleej和Arabiya上训练支持向量机模型在最短的时间内获得了最显著的结果,准确率达到82%。
{"title":"Investigating the relevance of Arabic text classification datasets based on supervised learning","authors":"Ahmad Hussein Ababneh","doi":"10.1016/j.jnlest.2022.100160","DOIUrl":"10.1016/j.jnlest.2022.100160","url":null,"abstract":"<div><p>Training and testing different models in the field of text classification mainly depend on the pre-classified text document datasets. Recently, seven datasets have emerged for Arabic text classification, including Single-Label Arabic News Articles Dataset (SANAD), Khaleej, Arabiya, Akhbarona, KALIMAT, Waten2004, and Khaleej2004. This study investigates which of these datasets can provide significant training and fair evaluation for text classification. In this investigation, well-known and accurate learning models are used, including naive Bayes, random forest, <em>K</em>-nearest neighbor, support vector machines, and logistic regression models. We present relevance and time measures of training the models with these datasets to enable Arabic language researchers to select the appropriate dataset to use based on a solid basis of comparison. The performances of the five learning models across the seven datasets are measured and compared with the performance of the same models trained on a well-known English language dataset. The analysis of the relevance and time scores shows that training the support vector machine model on Khaleej and Arabiya obtained the most significant results in the shortest amount of time, with the accuracy of 82%.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000131/pdfft?md5=f80d190efa3ad8651ea8b413ce044394&pid=1-s2.0-S1674862X22000131-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46018882","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: 2
Coherent optical frequency combs: From principles to applications 相干光频梳:从原理到应用
Q1 Engineering Pub Date : 2022-06-01 DOI: 10.1016/j.jnlest.2022.100157
Hao Zhang , Bing Chang , Zhaoyu Li , Yu-Pei Liang , Chen-Ye Qin , Chun Wang , Han-Ding Xia , Teng Tan , Bai-Cheng Yao

A coherent optical frequency comb is a kind of broad-spectrum light sources delivering equidistant frequencies, and correspondingly its temporal waveform appears as a sequence of ultrashort pulses. Being the cornerstone technology of today's laser and time-frequency disciplines, it effectively links the optical frequency and the microwave frequency, and has promoted the development of diverse applications, such as precision spectroscopy, optical measurement, coherent optical communications, and optical clocks in the past two decades. In this review, we comprehensively introduce the development path, physical principle, generation/tuning methods, and advanced applications of optical frequency combs.

相干光频梳是一种传输等距频率的广谱光源,其时序波形表现为一系列超短脉冲。作为当今激光和时频学科的基石技术,它有效地连接了光频率和微波频率,并在过去二十年中推动了精密光谱、光学测量、相干光通信、光学时钟等多种应用的发展。本文全面介绍了光频梳的发展历程、物理原理、产生/调谐方法及其应用。
{"title":"Coherent optical frequency combs: From principles to applications","authors":"Hao Zhang ,&nbsp;Bing Chang ,&nbsp;Zhaoyu Li ,&nbsp;Yu-Pei Liang ,&nbsp;Chen-Ye Qin ,&nbsp;Chun Wang ,&nbsp;Han-Ding Xia ,&nbsp;Teng Tan ,&nbsp;Bai-Cheng Yao","doi":"10.1016/j.jnlest.2022.100157","DOIUrl":"10.1016/j.jnlest.2022.100157","url":null,"abstract":"<div><p>A coherent optical frequency comb is a kind of broad-spectrum light sources delivering equidistant frequencies, and correspondingly its temporal waveform appears as a sequence of ultrashort pulses. Being the cornerstone technology of today's laser and time-frequency disciplines, it effectively links the optical frequency and the microwave frequency, and has promoted the development of diverse applications, such as precision spectroscopy, optical measurement, coherent optical communications, and optical clocks in the past two decades. In this review, we comprehensively introduce the development path, physical principle, generation/tuning methods, and advanced applications of optical frequency combs.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000106/pdfft?md5=48ebbeb3a1b548cc278f9d90c1a87c3b&pid=1-s2.0-S1674862X22000106-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45580502","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: 5
Memristor-based genetic algorithm for image restoration 基于忆阻器的图像恢复遗传算法
Q1 Engineering Pub Date : 2022-06-01 DOI: 10.1016/j.jnlest.2022.100158
Yong-Bin Yu , Chen Zhou , Quan-Xin Deng , Yuan-Jing-Yang Zhong , Man Cheng , Zheng-Fei Kang

This paper explores a way of deploying the classical algorithm named genetic algorithm (GA) with the memristor. The memristor is a type of circuit device with both characteristics of storage and computing, which provides the similarity between electronic devices and biological components, such as neurons, and the structure of the memristor-based array is similar to that of chromosomes in genetics. Besides, it provides the similarity to the image gray-value matrix that can be applied to image restoration with GA. Thus, memristor-based GA is proposed and the experiment about image restoration using memristor-based GA is carried out in this paper. And parameters, such as the size of initial population and the number of iterations, are also set different values in the experiment, which demonstrates the feasibility of implementing GA with memristors.1

本文探讨了一种将经典算法遗传算法(GA)部署到忆阻器中的方法。忆阻器是一种兼具存储和计算特性的电路器件,它提供了电子器件与生物元件(如神经元)之间的相似性,基于忆阻器的阵列结构与遗传学上的染色体结构相似。此外,它还提供了与图像灰度值矩阵的相似性,可以应用于遗传算法的图像恢复。为此,本文提出了基于忆阻器的遗传算法,并进行了基于忆阻器的遗传算法图像恢复实验。实验中还设置了初始种群大小、迭代次数等参数,验证了用忆阻器实现遗传算法的可行性
{"title":"Memristor-based genetic algorithm for image restoration","authors":"Yong-Bin Yu ,&nbsp;Chen Zhou ,&nbsp;Quan-Xin Deng ,&nbsp;Yuan-Jing-Yang Zhong ,&nbsp;Man Cheng ,&nbsp;Zheng-Fei Kang","doi":"10.1016/j.jnlest.2022.100158","DOIUrl":"10.1016/j.jnlest.2022.100158","url":null,"abstract":"<div><p>This paper explores a way of deploying the classical algorithm named genetic algorithm (GA) with the memristor. The memristor is a type of circuit device with both characteristics of storage and computing, which provides the similarity between electronic devices and biological components, such as neurons, and the structure of the memristor-based array is similar to that of chromosomes in genetics. Besides, it provides the similarity to the image gray-value matrix that can be applied to image restoration with GA. Thus, memristor-based GA is proposed and the experiment about image restoration using memristor-based GA is carried out in this paper. And parameters, such as the size of initial population and the number of iterations, are also set different values in the experiment, which demonstrates the feasibility of implementing GA with memristors.<sup>1</sup></p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X22000118/pdfft?md5=dd4580f3370fb603dc6a06343eb4c88c&pid=1-s2.0-S1674862X22000118-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48115729","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: 2
Salp swarm algorithm for solving optimal power flow problem with thyristor-controlled series capacitor 求解晶闸管串联电容最优潮流问题的Salp群算法
Q1 Engineering Pub Date : 2022-06-01 DOI: 10.1016/j.jnlest.2022.100156
Balasubbareddy Mallala , Divyanshi Dwivedi

In this paper, a salp swarm algorithm (SSA) is proposed for solving the optimal power flow (OPF) problem of a power system with the incorporation of the thyristor-controlled series capacitor (TCSC). The proposed methodology is implemented for determining the optimal setting of control variables for the OPF problem, which includes the real power of generators buses, voltages of generator buses, reactive power injected by shunt compensators, and tap changing transformer ratios. The performance of the proposed approach is validated and tested on the standard IEEE-30 bus system and single-objective functions, including transmission line losses. The severity factor has been minimized and the result obtained is compared with the existing algorithms. Simulation results achieved with the proposed SSA approach demonstrate that it results in an effective and better solution for the OPF problem.

本文提出了一种求解含晶闸管控制串联电容的电力系统最优潮流问题的salp群算法(SSA)。提出的方法用于确定OPF问题的控制变量的最佳设置,其中包括发电机母线的实际功率、发电机母线的电压、并联补偿器注入的无功功率和分接改变变压器比率。在标准IEEE-30总线系统和单目标函数(包括传输线损耗)上验证和测试了所提出方法的性能。将严重性因子最小化,并与现有算法进行了比较。仿真结果表明,该方法能较好地解决OPF问题。
{"title":"Salp swarm algorithm for solving optimal power flow problem with thyristor-controlled series capacitor","authors":"Balasubbareddy Mallala ,&nbsp;Divyanshi Dwivedi","doi":"10.1016/j.jnlest.2022.100156","DOIUrl":"10.1016/j.jnlest.2022.100156","url":null,"abstract":"<div><p>In this paper, a salp swarm algorithm (SSA) is proposed for solving the optimal power flow (OPF) problem of a power system with the incorporation of the thyristor-controlled series capacitor (TCSC). The proposed methodology is implemented for determining the optimal setting of control variables for the OPF problem, which includes the real power of generators buses, voltages of generator buses, reactive power injected by shunt compensators, and tap changing transformer ratios. The performance of the proposed approach is validated and tested on the standard IEEE-30 bus system and single-objective functions, including transmission line losses. The severity factor has been minimized and the result obtained is compared with the existing algorithms. Simulation results achieved with the proposed SSA approach demonstrate that it results in an effective and better solution for the OPF problem.</p></div>","PeriodicalId":53467,"journal":{"name":"Journal of Electronic Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674862X2200009X/pdfft?md5=42b8b1fc87caf36049d92172082470af&pid=1-s2.0-S1674862X2200009X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43846596","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: 5
期刊
Journal of Electronic Science and Technology
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