检索结果-南通市图书馆

Journal of Cyber Security 2023年第1期5卷 1-11页

作者： Bilal khan Muhammad Arshad sarwar shah khan Department of Computer Science City University of Science and Information TechnologyPeshawarPakistan Department of Computer Software Engineering University of Engineering and TechnologyMardanPakistan Department of Computer and Software Technology University of SwatSwatPakistan Department of Computer Science IQRA National UniversitySwatPakistan

The proliferation of maliciously coded documents as file transfers increase has led to a rise in sophisticated *** Document Format(PDF)files have emerged as a major attack vector for malware due to their adaptability and wide *** malware in PDF files is challenging due to its ability to include various harmful elements such as embedded scripts,exploits,and malicious *** paper presents a comparative analysis of machine learning(ML)techniques,including Naive Bayes(NB),K-Nearest Neighbor(KNN),Average One Dependency Estimator(A1DE),RandomForest(RF),and SupportVectorMachine(SVM)forPDFmalware *** study utilizes a dataset obtained from the Canadian Institute for Cyber-security and employs different testing criteria,namely percentage splitting and 10-fold *** performance of the techniques is evaluated using F1-score,precision,recall,and accuracy *** results indicate that KNNoutperforms other models,achieving an accuracy of 99.8599%using 10-fold *** findings highlight the effectiveness of ML models in accurately detecting PDF malware and provide insights for developing robust systems to protect against malicious activities.

关键词： Cyber-security PDF malware model training testing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

图像分类与融合研究基于机器学习技术

图像分类与融合研究基于机器学习技术

作者： sarwar shah khan 北京化工大学

学位级别：硕士

视觉对人类具有至关重要的意义,图像在人类生活中广泛分布。因此,图像处理被广泛应用于遥感,军事,医疗等领域。如今,人们很容易通过数字技术获取大量图像。图像处理需要能够解决更复杂的问题,适应人类视觉。机器学习技术是图像处理开发... 详细信息

视觉对人类具有至关重要的意义,图像在人类生活中广泛分布。因此,图像处理被广泛应用于遥感,军事,医疗等领域。如今,人们很容易通过数字技术获取大量图像。图像处理需要能够解决更复杂的问题,适应人类视觉。机器学习技术是图像处理开发的重要部分。因为数据集的发展,图像处理和机器学习引起了巨大的关注。基于机器学习的图像处理有很多优势,能够更好地理解复杂的图像。本文研究了三个方面问题:多光谱和全色图像的锐化、多焦点图像融合和高光谱图像分类。首先,图像锐化前进行图像增强,它是一个预处理的过程。图像增强包括同域增强和交叉域增强。同域增强方法（如拉普拉斯、边缘锐化）是在空间域增强多光谱和全色图像。交叉域增强方法是混合了拉普拉斯滤波器和离散傅里叶变换锐化。其次,使用抠图模型（MM）融合增强后的图像,获得高分辨率合成图像。定性和定量的实验结果表明本文方法在两个数据集上优于现有方法。多焦点图像是当视场超过成像系统景深时,导致图像模糊”。彩色多焦点图像融合是合并多张多焦点图像,获得清晰的合成图像。该方法分为两步。首先,通过具有离散傅立叶变换（DFT）和拉普拉斯滤波器（LF）技术增强了多焦点图像。其次,通过静止小波变换（SWT）对增强图像进行进一步处理,获得更多信息的融合图像。定性和定量方法实验结果表明,该方法的结果犹豫传统的SWT方法。。本文提出了基于最近正则化子空间（NRS）的高光谱图像（HSI）分类。因为NRS利用距离加权的Tikhonov正则化来确保类内相似样本的适当表示,NRS优于协同表示分类和基于稀疏表示的技术。然而,典型的NRS仅考虑欧几里德距离,这对于解决频谱绝对幅度中的灵敏度问题不是最佳的。提出了一种基于NRS-曼哈顿距离（MD）策略的HSI分类。MD控制了幅度变化并强化了频谱的形状。此外,MD度量使用HSI像素全维度的光谱带的全部信息,这使NRS-MD成为更有效的像素分类器。通过印度松树,博茨瓦纳,萨利纳斯和休斯敦高光谱数据的实验结果表明,NRS-MD优于现有方法。

关键词：机器学习全色锐化多光谱图像全色图像多焦点图像融合高光谱图像分

Sentiment Analysis Based on Performance of Linear Support Vector Machine and Multinomial Naïve Bayes Using Movie Reviews with Baseline Techniques

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Journal on Big Data 2023年第1期5卷 1-18页

作者： Mian Muhammad Danyal sarwar shah khan Muzammil khan Muhammad Bilal Ghaffar Bilal khan Muhammad Arshad Department of Computer Science City University of Science&TechnologyPeshawar25000Pakistan Department of Computer Science and Software Technology University of SwatSwat19200Pakistan Department of Computer Software Engineering University of Engineering&Technology MardanMardan23200Pakistan Department of Computer Science IQRA National UniversitySwat19200Pakistan

Movies are the better source of *** year,a great percentage of movies are *** comment on movies in the form of reviews after watching *** it is difficult to read all of the reviews for a movie,summarizing all of the reviews will help make this decision without wasting time in reading all of the *** mining also known as sentiment analysis is the process of extracting subjective information from textual *** mining involves identifying and extracting the opinions of individuals,which can be positive,neutral,or *** task of opinion mining also called sentiment analysis is performed to understand people’s emotions and attitudes in movie *** reviews are an important source of opinion data because they provide insight into the general public’s opinions about a particular *** summary of all reviews can give a general idea about the *** study compares baseline techniques,Logistic Regression,Random Forest Classifier,Decision Tree,K-Nearest Neighbor,Gradient Boosting Classifier,and Passive Aggressive Classifier with Linear Support Vector Machines and Multinomial Naïve Bayes on the IMDB Dataset of 50K reviews and Sentiment Polarity Dataset Version *** applying these classifiers,in pre-processing both datasets are cleaned,duplicate data is dropped and chat words are treated for better *** the IMDB Dataset of 50K reviews,Linear Support Vector Machines achieve the highest accuracy of 89.48%,and after hyperparameter tuning,the Passive Aggressive Classifier achieves the highest accuracy of 90.27%,while Multinomial Nave Bayes achieves the highest accuracy of 70.69%and 71.04%after hyperparameter tuning on the Sentiment Polarity Dataset Version *** study highlights the importance of sentiment analysis as a tool for understanding the emotions and attitudes in movie reviews and predicts the performance of a movie based on the average sentiment of all the reviews.

关键词： Opinion mining machine learning movie reviews IMDB Dataset of 50K reviews Sentiment Polarity Dataset Version 2.0

Water-Lubricated Ni-Based Composite(Ni-Al_2O_3,Ni-SiC and Ni-ZrO_2)Thin Film Coatings for Industrial Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2016年第1期29卷 8-16页

作者： Rizwan sarwar Bajwa Zulfiqar khan Vasilios Bakolas Wolfgang Braun Faculty of Science and Technology Sustainable Design Research CentreBournemouth University Talbot Campus Advanced Bearing Analysis Schaeffler Technologies GmbH& Co.KG

In this work, pure nickel and Ni-based nanocomposite coatings （Ni-AI2O3, Ni-SiC and Ni-ZrO2） were pro- duced on steel substrate by using pulse electrodeposition technique. The industrial performance tests were conducted to evaluate the wear resistance, corrosion resistance, adhesion strength and wettability behaviour of newly developed coat- ings. Rolling contact ball-on-disc tribometer was used to assess anti-wear behaviour of these coatings under water- lubricated contacts. The results showed that the wear- and corrosion resistance properties of nickel alumina and Ni-SiC composite coatings significantly improved than that of pure Ni and Ni-ZrO2 coatings. The adhesion and wettability results of Ni-A1203 composite showed better performance when compared to the rest of the coatings. The effects of incorporating nanoparticles on the surface microstructure, interface adhesion and distribution of the particles were also investigated. The coatings were characterized by using scanning electron microscopy, X-ray diffraction analysis and 3D white light inter- ferometry. The wear failure behaviour of these coatings was further examined by post-test surface observation under optical microscope.

关键词： Electrodeposition Wear-resistant Corrosion-resistant Tribology Nanocoatings Water-lubrication

Organic and Inorganic Mercury in Biological Samples of Flouresecent Lamp Industries Workers and Health Risks

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Biomedical and Environmental Sciences 2020年第2期33卷 89-102页

作者： Nayab GUL Sardar khan Abbas khan Javed NAWAB Adnan sarwar Nida GUL Climate Change Centre The University of AgriculturePeshawar 25120Pakistan Department of Environmental Sciences University of PeshawarPeshawar 25120Pakistan Drug Control Administration Government of Khyber PakhtunkhwaHealth DepartmentPeshawar 25120Pakistan Department of Environmental Sciences Abdul Wali Khan University MardanPeshawar 25120Pakistan Pak International Medical College and Research Institute HayatabadPeshawar 25120Pakistan

Objective The present study aims to investigate the concentrations of Hg and its aspects methyl mercury(Me-Hg)and inorganic mercury(I-Hg)in the biological samples(BSs)of fluorescent lamp industries workers(FLIWs).Methodology Different BSs including red blood cells(RBCs),plasma,urine,hair and nails were collected from the workers exposed to Hg and unexposed persons were selected as control group to measure both the T-Hg concentration as well as its species in different biological samples through quantitative *** data was collected through questionnaire *** The mean concentrations of T-Hg(31.9μg/L),Me-Hg(27.7μg/L),and I-Hg(5.36μg/L)in RBCs were found significantly(P<0.001)higher among the workers(n=40)as compared to the control group(n=40).Similarly the mean Hg concentrations in plasma,urine,hair and nails were also significantly higher among the workers than the control *** statistical relation between Hg concentration and demographic characteristics observed that workers experience and fish consumption has increased the Hg concentration while age,weight and smoking found no significant effect on Hg concentration in the *** The study observed that the workers were highly exposed to high concentration of Hg and they are at a high health risk.

关键词： Mercury Health risk Fluorescent lamp industries Regression Demographic characteristics Biological samples

Liver-Tumor Detection Using CNN ResUNet

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第5期67卷 1899-1914页

作者： Muhammad Sohaib Aslam Muhammad Younas Muhammad Umar sarwar Muhammad Arif shah Atif khan MIrfan Uddin Shafiq Ahmad Muhammad Firdausi Mazen Zaindin Department of Computer Science Government College University FaisalabadFaisalabad38000Pakistan Department of IT and Computer Science Pak-Austria Fachhochschule Institute of Applied Sciences and TechnologyHaripur22620Pakistan Department of Computer Science Islamia College PeshawarPeshawarKPPakistan Institute of Computing Kohat University of Science and TechnologyKohatPakistan Department of Industrial Engineering College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia Department of Statistics and Operations Research College of ScienceKing Saud UniversityRiyadh11421Saudi Arabia

Liver tumor is the fifth most occurring type of tumor in men and the ninth most occurring type of tumor in women according to recent reports of Global cancer statistics *** are several imaging tests like Computed Tomography(CT),Magnetic Resonance Imaging(MRI),and ultrasound that can diagnose the liver tumor after taking the sample from the tissue of the *** tests are costly and *** paper proposed that image processing through deep learning Convolutional Neural Network(CNNs)ResUNet model that can be helpful for the early diagnose of tumor instead of conventional *** existing studies have mainly used the two Cascaded CNNs for liver segmentation and evaluation of Region Of Interest(ROI).This study uses ResUNet,an updated version of U-Net and ResNet Models that utilize the service of Residential *** apply over method on the 3D-IRCADb01 dataset that is based on CT slices of liver tumor affected *** results showed the True Value Accuracy around 99%and F1 score performance around 95%.This method will be helpful for early and accurate diagnose of the Liver tumor to save the lives of many patients in the field of Biotechnology.

关键词： Liver tumor diagnose ResUNet CNNs segmentation

Development of Molecular Marker Linked with Cercospora Leaf Spot (CLS) Disease Resistance in Vigna radiata, Cloning, and Expression for Evaluating Antifungal Activity against Cercospora canescens

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2023年第4期92卷 1289-1300页

作者： Maria Babar Siddra Ijaz Imran Ul Haq Muhammad sarwar khan Centre of Agricultural Biochemistry and Biotechnology(CABB) University of Agriculture FaisalabadFaisalabad38040Pakistan Department of Plant Pathology University of Agriculture FaisalabadFaisalabad38040Pakistan

We developed a molecular marker for MAS of mungbean resistant varieties against CLS from the consensus sequence(MB-CLsRG)of identified RGAs(MB-ClsRCaG1 and MB-ClsRCaG2).The MB-CLsRG sequence-specific primer pair was used to screen Cercospora leaf spot(CLS)resistant varieties of mungbean in genomic analysis that showed congruency with phenotypic *** of molecular marker linkage with CLS resistance was performed using rtPCR in transcriptomic *** sequenced PCR products showed 100%homology with MB-CLsRG sequence and putative disease resistance proteins that confirmed the linkage of molecular marker with CLS resistance in *** antifungal potential of MB-CLsRG gene encoding protein was *** MB-CLsRG gene sequence was cloned in the *** expression vector for recombinant protein *** recombinant protein was then investigated for its in vitro antifungal potential against Cercospora *** in vitro investigation showed strong antifungal activity of recombinant protein as it restricted the growth of fungal mycelial *** results validated the linkage of developed marker with CLS-resistant mungbean varieties;therefore,it can be used to screen resistant varieties from a large population in ***,the recombinant protein of the MB-CLsRG gene sequence revealed antifungal potential,which proved the gene sequence could be suitable to use in transgenic plants technology to develop fungal-resistant transgenic crops.

关键词： Molecular marker mungbean MAS recombinant protein antifungal potential

The occurrence of vanadium in nature:its biogeochemical cycling and relationship with organic matter—a case study of the Early Cambrian black rocks of the Niutitang Formation,western Hunan,China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Geochimica 2021年第6期40卷 973-997页

作者： Rizwan sarwar Awan Chenglin Liu Shangfeng Yang Yuping Wu Qibiao Zang Ashar khan Guoxiong Li College of Geosciences China University of PetroleumBeijing 102249China State Key Laboratory of Petroleum Resource and Prospecting China University of PetroleumBeijing 102249China Water and Power Development Authority Lahore Pakistan

Vanadium in the black rocks has economic and environmental *** sediments,it is broadly disseminated as a multivalent metal element mainly sensitive to redox *** in petroleum,it is considered an abundant *** is an essential tool to determine the relationship of the Earth with extra-terrestrial *** the Yangtze region,the black rocks of the Early Cambrian Niutitang Formation are highly enriched in the concentration of V,Co,Ni and *** sediments are comprised of a high total organic carbon content,and the average concentration of vanadium is over 240 *** we discuss the mechanisms and conditions that were responsible for the accumulation of vanadium in these black sediments in the Yangtze *** oxygenated ocean water is favorable for the dissolved vanadate species Ⅴ(Ⅴ).Therefore,in oxic ocean-water,it can be reduced by organic matters or by H_(2)S to vanadyl ions Ⅴ(Ⅳ),which can facilely be adsorbed to the tiny particles and finally deposit into the sediments with the settling of the *** presence of V_(2)O_(3) in the Niutitang Formation indicates the isomorphism state of vanadium existence in the clay *** and pyrite are the most favorable mineral for vanadium ***,it is suggested the quartz of non-biogenic origin might be unfavorable for vanadium *** is mainly derived from the diagenetic transformation of its precursor(porphyrin pigments and chlorophyll)from the *** the Early Cambrian period,the massive transgression in the sea level created a favorable environment for organisms to ***,the hydrothermal activities brought massive nutrient supply in the form of vanadium and other metal elements from the deep *** creatures consumed the vanadium-rich nutrients,which became a part of their bodies in the form of hard and soft *** on,when these organisms died and were submerged in the *** the diagenetic actions,this v

关键词： Vanadium Organic matter Chlorophyll Porphyrin Anthropogenic Isomerization

Enhanced Accuracy for Motor Imagery Detection Using Deep Learning for BCI

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第9期68卷 3825-3840页

作者： Ayesha sarwar Kashif Javed Muhammad Jawad khan Saddaf Rubab Oh-Young Song Usman Tariq National University of Sciences and Technology(NUST) Islamabad44000Pakistan Department of Software Sejong UniversitySeoulGwangjin-guKorea College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

Brain-Computer Interface(BCI)is a system that provides a link between the brain of humans and the hardware *** recorded brain data is converted directly to the machine that can be used to control external *** are four major components of the BCI system:acquiring signals,preprocessing of acquired signals,features extraction,and *** traditional machine learning algorithms,the accuracy is insignificant and not up to the mark for the classification of multi-class motor imagery *** major reason for this is,features are selected manually,and we are not able to get those features that give higher accuracy *** this study,motor imagery(MI)signals have been classified using different deep learning *** have explored two different methods:Artificial Neural Network(ANN)and Long Short-Term Memory(LSTM).We test the classification accuracy on two datasets:BCI competition III-dataset IIIa and BCI competition IV-dataset *** outcome proved that deep learning algorithms provide greater accuracy results than traditional machine learning *** the deep learning classifiers,LSTM outperforms the ANN and gives higher classification accuracy of 96.2%.

关键词： Brain-computer interface motor imagery artificial neural network long-short term memory classification

3D Head Pose Estimation through Facial Features and Deep Convolutional Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第2期66卷 1757-1770页

作者： Khalil khan Jehad Ali Kashif Ahmad Asma Gul Ghulam sarwar Sahib khan Qui Thanh Hoai Ta Tae-Sun Chung Muhammad Attique Department of Computer Science and Software Engineering Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur-KPKPakistan Department of Computer Engineering and Department of AI Convergence Network Ajou UniversitySuwon16499South Korea Hamad Bin Khalifa University DohaQatar Department of Statistics Shaheed Benazir Bhutto Women UniversityPeshawarPakistan Department of Software Engineering University of Azad Jammu and KashmirPakistan Department of Electronics and Telecommunications Politecnico di TorinoTorino10129Italy Institute of Research and Development Duy Tan UniversityDanang550000Vietnam Department of Computer Engineering Ajou UniversitySuwon16499Korea Department of Software Sejong UniversitySeoul05006South Korea

Face image analysis is one among several important cues in computer *** the last five decades,methods for face analysis have received immense attention due to large scale applications in various face analysis *** parsing strongly benefits various human face image analysis tasks inducing face pose *** this paper we propose a 3D head pose estimation framework developed through a prior end to end deep face parsing *** have developed an end to end face parts segmentation framework through deep convolutional neural networks(DCNNs).For training a deep face parts parsing model,we label face images for seven different classes,including eyes,brows,nose,hair,mouth,skin,and *** extract features from gray scale images by using *** train a classifier using the extracted *** use the probabilistic classification method to produce gray scale images in the form of probability maps for each dense semantic *** use a next stage of DCNNs and extract features from grayscale images created as probability maps during the segmentation *** assess the performance of our newly proposed model on four standard head pose datasets,including Pointing’04,Annotated Facial Landmarks in the Wild(AFLW),Boston University(BU),and ICT-3DHP,obtaining superior results as compared to previous results.

关键词： Face image analysis face parsing face pose estimation