检索结果-南通市图书馆

Manta Ray Foraging Optimization with Machine Learning Based Biomedical Data Classification

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

Computers, Materials & Continua 2022年第11期73卷 3275-3290页

作者： Amal Al-Rasheed Jaber S.Alzahrani Majdy M.Eltahir Abdullah Mohamed Anwer Mustafa Hilal Abdelwahed Motwakel Abu sarwar Zamani Mohamed I.Eldesouki Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversityMecca24382Saudi Arabia Department of Information Systems College of Science&Art at MahayilKing Khalid UniversityAbha62529Saudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The biomedical data classification process has received significant attention in recent times due to a massive increase in the generation of healthcare data from various *** developments of artificial intelligence(AI)and machine learning(ML)models assist in the effectual design of medical data classification ***,this article concentrates on the development of optimal Stacked Long Short Term Memory Sequence-toSequence Autoencoder(OSAE-LSTM)model for biomedical data *** presented OSAE-LSTM model intends to classify the biomedical data for the existence of ***,the OSAE-LSTM model involves min-max normalization based pre-processing to scale the data into uniform *** by,the SAE-LSTM model is utilized for the detection and classification of diseases in biomedical *** last,manta ray foraging optimization(MRFO)algorithm has been employed for hyperparameter optimization *** utilization of MRFO algorithm assists in optimal selection of hypermeters involved in the SAE-LSTM *** simulation analysis of the OSAE-LSTM model has been tested using a set of benchmark medical datasets and the results reported the improvements of the OSAELSTM model over the other approaches under several dimensions.

关键词： Biomedical data classification deep learning manta ray foraging optimization healthcare machine learning artificial intelligence

Improved Ant Lion Optimizer with Deep Learning Driven Arabic Hate Speech Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第9期46卷 3321-3338页

作者： Abdelwahed Motwakel Badriyya B.Al-onazi Jaber S.Alzahrani Sana Alazwari Mahmoud Othman Abu sarwar Zamani Ishfaq Yaseen Amgad Atta Abdelmageed Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Language Preparation Arabic Language Teaching InstitutePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaifP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt

Arabic is the world’s first language,categorized by its rich and complicated grammatical ***,the Arabic morphology can be perplexing because nearly 10,000 roots and 900 patterns were the basis for verbs and *** Arabic language consists of distinct variations utilized in a community and particular *** media sites are a medium for expressing opinions and social phenomena like racism,hatred,offensive language,and all kinds of verbal *** conduct does not impact particular nations,communities,or groups only,extending beyond such areas into people’s everyday *** study introduces an Improved Ant Lion Optimizer with Deep Learning Dirven Offensive and Hate Speech Detection(IALODL-OHSD)on Arabic *** presented IALODL-OHSD model mainly aims to detect and classify offensive/hate speech expressed on social *** the IALODL-OHSD model,a threestage process is performed,namely pre-processing,word embedding,and ***,data pre-processing is performed to transform the Arabic social media text into a useful *** addition,the word2vec word embedding process is utilized to produce word *** attentionbased cascaded long short-term memory(ACLSTM)model is utilized for the classification ***,the IALO algorithm is exploited as a hyperparameter optimizer to boost classifier *** illustrate a brief result analysis of the IALODL-OHSD model,a detailed set of simulations were *** extensive comparison study portrayed the enhanced performance of the IALODL-OHSD model over other approaches.

关键词： Hate speech offensive speech Arabic corpora natural language processing social networks

Utility of liver biopsy in predicting clinical outcomes after percutaneous angioplasty for hepatic venous obstruction in liver transplant patients

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Hepatology 2015年第14期7卷 1884-1893页

作者： Ammar sarwar Edward Ahn Ian Brennan Olga R Brook Salomao Faintuch Raza Malik Khalid Khwaja Muneeb Ahmed Divison of Vascular and Interventional Radiology Beth Israel Deaconess Medical Center/Harvard Medical School Division of Gastroenterology and Hepatology Beth Israel Deaconess Medical Center/Harvard Medical School Division of Transplant Surgery Beth Israel Deaconess Medical Center/Harvard Medical School

AIM: To determine utility of transplant liver biopsy in evaluating efficacy of percutaneous transluminal angioplasty(PTA) for hepatic venous obstruction(HVOO). METHODS: Adult liver transplant patients treated with PTA for HVOO(2003-2013) at a single institution were reviewed for pre/post-PTA imaging findings, manometry(gradient with right atrium), presence of HVOO on prePTA and post-PTA early and late biopsy(EB and LB, 60 d after PTA), and clinical outcome, defined as good(no clinical issues, non-HVOO-related death) or poor(surgical correction, recurrent HVOO, or HVOOrelated death). RESULTS: Fifteen patients meeting inclusion criteria underwent 21 PTA, 658 ± 1293 d after *** procedures with pre-PTA biopsy(n = 19), no difference was seen between pre-PTA gradient in 13/19 procedures with HVOO on biopsy and 6/19 procedures without HVOO(8 ± 2.4 mm Hg vs 6.8 ± 4.3 mm Hg; P = 0.35). Post-PTA, 10/21 livers had EB(29 ± 21 d) and 9/21 livers had LB(153 ± 81 d). On clinical follow-up(392 ± 773 d), HVOO on LB resulted in poor outcomes and absence of HVOO on LB resulted good outcomes. Patients with HVOO on EB(3/7 good, 4/7 poor) and no HVOO on EB(2/3 good, 1/3 poor) had mixed outcomes. CONCLUSION: Negative liver biopsy greater than 60 d after PTA accurately identifies patients with good clinical outcomes.

关键词： Hepatic venous outflow obstruction Livertransplantation Post-transplant biopsy Angioplasty

Chapman-Kolmogorov equations for global PPIs with Discriminant-EM

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Biomathematics 2014年第5期7卷 95-101页

作者： Md. sarwar Kamal Mohammad Ibrahim Khan Department of Computer Science and EngineeringChittagong University of Engineering and Technology Chittagong ~3~9 Bangladesh

Ongoing improvements in Computational Biology research have generated massive amounts of Protein-Protein Interactions （PPIs） dataset. In this regard, the availability of PPI data for several organisms provoke the discovery of computational methods for measurements, analysis, modeling, comparisons, clustering and alignments of biological data networks. Nevertheless, fixed network comparison is computationally stubborn and as a result several methods have been used instead. We illustrate a prohabilistic approach among proteins nodes that are part of various networks by using Chapman-Kolmogorov （CK） formula. We have compared CK formula with semi-Markov random method, SMETANA. We significantly noticed that CK outperforms the SMETANA in all respects such as efficiency, speed, space and complexity. We have modified the SMETANA source codes available in MATLAB in the light of CK formula. Discriminant-Expectation Maximization （D-EM） accesses the parameters of a protein network datasets and determines a linear transformation to simplify the assumption of probabilistic format of data distributions and find good features dynamically. Our implementation finds that D-EM has a satisfactory performance in protein network alignment applications.

关键词： SMETANA semi-Markov method Chapman-Kolmogorov formula D-EM.

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

Metaheuristics Enabled Clustering with Routing Scheme for Wireless Sensor Networks

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

Computers, Materials & Continua 2022年第12期73卷 5491-5507页

作者： Mashael M.Asiri Saud S.Alotaibi Dalia H.Elkamchouchi Amira Sayed A.Aziz Manar Ahmed Hamza Abdelwahed Motwakel Abu sarwar Zamani Ishfaq Yaseen Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Wireless Sensor Network(WSN)is a vital element in Internet of Things(IoT)as the former enables the collection of huge quantities of data in energy-constrained *** offers independent access to the target region and performs data collection in an effective *** energy constraints remain a challenging issue in WSN since it operates on in-built *** studies conducted earlier recommended that the energy spent on communication processmust be considerably reduced to improve the efficiency of *** organization and optimal selection of the routes are considered as NP hard optimization problems which can be resolved with the help of metaheuristic *** and routing are considered as effective approaches in enhancing the energy effectiveness and lifespan of *** this background,the current study develops an Improved Duck and Traveller Optimization(IDTO)-enabled cluster-based Multi-Hop Routing(IDTOMHR)technique for ***,IDTO algorithm is exploited for the selection of Cluster Head(CH)and construction of ***,Artificial Gorilla Troops Optimization(ATGO)technique is also used to derive an optimal set of routes to the *** clustering and routing approaches derive a fitness function with the inclusion of multiple input *** proposed IDTOMHR model was experimentally validated for its performance under different *** extensive experimental results confirmed the better performance of IDTOMHR model over other recent approaches.

关键词： Wireless sensor network clustering routing metaheuristics energy efficiency lifetime

Comparison of Different Dosage of Dexamethasone as Pre-medication in NSCLC Patients with First Line Docetaxel-Platinum-Based Chemotherapy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Comparison of Different Dosage of Dexamethasone as Pre-medic...

作者： Faisal sarwar Abbasi 大连医科大学

学位级别：硕士

背景:随着肿瘤患病率的不断增加以及肿瘤治疗伴随的强烈不良反应,如何能使肿瘤治疗变得更有效且更安全就变得非常重要。本研究的目的在于对比作为以多西他赛为基础化疗的标准剂量地塞米松及改良低剂量地塞米松预处理,研究改良后的低剂... 详细信息

背景:随着肿瘤患病率的不断增加以及肿瘤治疗伴随的强烈不良反应,如何能使肿瘤治疗变得更有效且更安全就变得非常重要。本研究的目的在于对比作为以多西他赛为基础化疗的标准剂量地塞米松及改良低剂量地塞米松预处理,研究改良后的低剂量地塞米松是否具有与标准剂量地塞米松一样的疗效。方法:本研究选取了 2014年6月至2016年6月就诊大连医科大学附属第一医院肿瘤科的38名非小细胞肺癌患者,将患者分为两组,一组接受标准剂量地塞米松预处理:地塞米松4mg,一天两次口服,连用三天。第二组接受改良后的地塞米松预处理:前一天口服地塞米松7.5mg,次日给予5或10mg地塞米松配伍100ml生理盐水静脉点滴。结果:研究结果表明,地塞米松预处理剂量变化与肿瘤反应、骨髓抑制(血小板减少、中性粒细胞减少)和消化道毒性显著相关。t检验分析结果显示,骨髓抑制(尤其血小板减少症)的发生率在第一组明显增加,此外,无进展生存期的中位平均值为4.26±0.47个月(*P<0.05),危险比为0.87。这表明,给予改良计量地塞米松预处理的患者预后更好。结论:本研究表明对于非小细胞肺癌患者进行以多西他赛为基础的化疗我们认为改良后的低剂量地塞米松预处理更为优选,因为其安全性高且不良反应少。但是,如何确保肿瘤患者的健康以及减少治疗毒性仍然需要更多的研究和学习。

关键词：地塞米松多西他赛非小细胞肺癌术前用药

Optimal Deep Learning Enabled Communication System for Unmanned Aerial Vehicles

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

Computer Systems Science & Engineering 2023年第4期45卷 955-969页

作者： Anwer Mustafa Hilal Jaber S.Alzahrani Dalia H.Elkamchouchi Majdy M.Eltahir Ahmed S.Almasoud Abdelwahed Motwakel Abu sarwar Zamani Ishfaq Yaseen Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Information Systems College of Science&Art at MahayilKing Khalid UniversityMuhayel Aseer62529Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrince Sultan UniversitySaudi Arabia

Recently,unmanned aerial vehicles(UAV)or drones are widely employed for several application areas such as surveillance,disaster management,*** UAVs are limited to energy,efficient coordination between them becomes essential to optimally utilize the resources and effective communication among them and base station(BS).Therefore,clustering can be employed as an effective way of accomplishing smart communication systems among multiple *** this aspect,this paper presents a group teaching optimization algorithm with deep learning enabled smart communication system(GTOADL-SCS)technique for UAV *** proposed GTOADL-SCS model encompasses a two stage process namely clustering and *** the initial stage,the GTOADL-SCS model includes a GTOA based clustering scheme to elect cluster heads(CHs)and organize ***,the GTOADL-SCS model develops a fitness function containing three input parameters as residual energy of UAVs,average neighoring distance,and UAV *** classification process,the GTOADLSCS model applies pre-trained densely connected network(DenseNet201)feature extractor with gated recurrent unit(GRU)*** ensuring the enhanced performance of the GTOADL-SCS model,a widespread simulation analysis is performed and the comparative study reported the significant outcomes over the existing approaches with maximum packet delivery ratio(PDR)of 92.60%.

关键词： Unmanned aerial vehicles energy efficiency smart communication system deep learning

Comparative Analysis of Machine Learning Models for PDF Malware Detection:Evaluating Different Training and Testing Criteria

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

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