检索结果-南通市图书馆

Frontiers of Structural and Civil Engineering 2024年第10期18卷 1507-1523页

作者： Umer Sadiq KHAN Muhammad ISHFAQUE saif ur rehman KHAN Fang Xu Lerui CHEN Yi LEI School of Computer and Information Science Hubei Engineering UniversityXiaogan 432000China Institute for AI Industrial Technology Research Hubei Engineering UniversityXiaogan 432000China College of Water Conservancy and Hydropower Engineering Hohai UniversityNanjing 210098China School of Computer Science and Engineering Central South UniversityChangsha 410083China College of Aviation Zhongyuan University of TechnologyZhengzhou 451191China School of Civil Engineering Central South UniversityChangsha 410083China

Disaster-resilient dams require accurate crack detection,but machine learning methods cannot capture dam structural reaction temporal patterns and *** research uses deep learning,convolutional neural networks,and transfer learning to improve dam crack *** deep-learning models are trained on 192 crack *** research aims to provide up-to-date detecting techniques to solve dam crack *** finding shows that the EfficientNetB0 model performed better than others in classifying borehole concrete crack surface tiles and normal(undamaged)surface tiles with 91%*** study’s pre-trained designs help to identify and to determine the specific locations of cracks.

关键词： concrete dam borehole closed-circuit television deep learning models crack detection water resources management management

Malware Detection in Android IoT Systems Using Deep Learning

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 2023年第2期74卷 4399-4415页

作者： Muhammad Waqar Sabeeh Fareed Ajung Kim saif ur rehman Malik Muhammad Imran Muhammad Usman Yaseen Department of Computer Science COMSATS UniversityIslamabad45550Pakistan Department of Optical Engineering Sejong UniversitySeoul143747Korea Cybernetica AS Tallinn12618Estonia

The Android Operating System(AOS)has been evolving since its inception and it has become one of the most widely used operating system for the Internet of Things(IoT).Due to the high popularity and reliability ofAOS for IoT,it is a target of many cyber-attacks which can cause compromise of privacy,financial loss,data integrity,unauthorized access,denial of services and so *** Android-based IoT(AIoT)devices are extremely vulnerable to various malwares due to the open nature and high acceptance of Android in the ***,several detection preventive malwares are developed to conceal their malicious activities from analysis ***,conventional malware detection techniques could not be applied and innovative countermeasures against such anti-detection malwares are indispensable to secure the *** this paper,we proposed the novel deep learning-based real-time multiclass malware detection techniques for the AIoT using dynamic *** results show that the proposed technique outperforms existing malware detection techniques and achieves detection accuracy up to 99.87%.

关键词： Android cyber security deep learning internet of things malware detection

Interactive Evolutionary Multi-Objective Optimization Algorithm Using Cone Dominance

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 Harbin Institute of Technology(New Series) 2015年第6期22卷 76-84页

作者： Dalaijargal Purevsuren saif ur rehman Gang Cui Jianmin Bao Nwe Nwe Htay Win School of Computer Science and Technology Harbin Institute of Technology Key Lab of Broadband Wireless Communication and Sensor Network Technology (Jiangsu Provincial Engineering Research Center of Telecommunications and Network Technology) Ministry of Education

As the number of objectives increases,the performance of the Pareto dominance-based Evolutionary Multi-objective Optimization( EMO) algorithms such as NSGA-II,SPEA2 severely deteriorates due to the drastic increase in the Pareto-incomparable solutions. We propose a sorting method which classifies these incomparable solutions into several ordered classes by using the decision maker's( DM) preference *** is accomplished by designing an interactive evolutionary algorithm and constructing convex cones. This method allows the DMs to drive the search process toward a preferred region of the Pareto optimal front. The performance of the proposed algorithm is assessed for two,three,and four-objective knapsack problems. The results demonstrate the algorithm ' s ability to converge to the most preferred point. The evaluation and comparison of the results indicate that the proposed approach gives better solutions than that of NSGA-II. In addition,the approach is more efficient compared to NSGA-II in terms of the number of generations required to reach the preferred point.

关键词： multi-objective optimization evolutionary optimization preference information pareto dominance cone dominance

Depositional Environment and Lithofacies Analyses of Eocene Lacustrine Shale in the Bohai Bay Basin:Insights from Mineralogy and Elemental Geochemistry

在线全文

学校读者我要写书评

暂无评论

Acta Geologica Sinica(English Edition) 2023年第2期97卷 589-609页

作者： Danish KHAN LIANG Chao QIU Longwei Kamran MIRZA WANG Yelei Muhammad KASHIF saif ur rehman WANG Yuzhe TENG Jianbin State Key Laboratory of Ore Deposit Geochemistry Institute of GeochemistryChinese Academy of SciencesGuiyang 550081China School of Geosciences China University of PetroleumQingdaoShandong 266580China Institute of Geology University of the PunjabLahore 54590Pakistan Department of Earth Sciences University of SargodhaSargodha 40100Pakistan Shengli Oil Field DongyingShandong 257015China

The effect of various depositional parameters including paleoclimate,paleosalinity and provenance,on the depositional mechanism of lacustrine shale is very important in reconstructing the depositional *** classification of shale lithofacies and the interpretation of shale depositional environment are key features used in shale oil and gas exploration and development *** lower 3rd member of the Eocene Shahejie Formation(Es_(3)^(x)shale)was selected for this study,as one of the main prospective intervals for shale oil exploration and development in the intracratonic Bohai Bay ***,it is composed of quartz(avg.9.6%),calcite(avg.58.5%),dolomite(avg.7%),pyrite(avg.3.3%)and clay minerals(avg.20%).An advanced methodology(thin-section petrography,total organic carbon and total organic sulfur contents analysis,X-ray diffraction(XRD),X-ray fluorescence(XRF),field-emission scanning electron microscopy(FE-SEM))was adopted to establish shale lithofacies and to interpret the depositional environment in the lacustrine *** different types of lithofacies were recognized,based on mineral composition,total organic carbon(TOC)content and sedimentary *** inorganic geochemical proxies(Rb/Sr,Ca/(Ca+Fe),Ti/Al,Al/Ca,Al/Ti,Zr/Rb)have been used to interpret and screen variations in depositional environmental parameters during the deposition of the Es_(3)^(x)*** experimental results indicate that the environment during the deposition of the Es_(3)^(x)shale was warm and humid with heightened salinities,moderate to limited detrital input,higher paleohydrodynamic settings and strong oxygen deficient(reducing)conditions.A comprehensive depositional model of the lacustrine shale was *** interpretations deduced from this research work are expected to not only expand the knowledge of shale lithofacies classification for lacustrine fine-grained rocks,but can also offer a theoretical foundation for lacustrine shale oil explorati

关键词： shale lithofacies shale mineralogy elemental geochemistry depositional environment Shahejie Formation Bohai Bay Basin

Aspect-Based Sentiment Analysis for Social Multimedia:A Hybrid Computational Framework

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第8期46卷 2415-2428页

作者： Muhammad Rizwan Rashid Rana saif ur rehman Asif Nawaz Tariq Ali Azhar Imran Abdulkareem Alzahrani Abdullah Almuhaimeed University Institute of Information Technology–PMAS Arid Agriculture University Rawalpindi46000Pakistan Department of Creative Technologies Air UniversityIslamabad44000Pakistan Computer Engineering and Science Department Faculty of Computer Science and Information TechnologyAl Baha UniversityAl Baha65799Saudi Arabia Digital Health Institute King Abdulaziz City for Science and TechnologyRiyadh11442Saudi Arabia

People utilize microblogs and other social media platforms to express their thoughts and feelings regarding current events,public products and the latest *** share their thoughts and feelings about various topics,including products,news,blogs,*** user reviews and tweets,sentiment analysis is used to discover opinions and *** polarity is a term used to describe how sentiment is ***,neutral and negative are all examples of *** area is still in its infancy and needs several critical *** and hidden emotions can detract from the accuracy of traditional *** methods only evaluate the polarity strength of the sentiment words when dividing them into positive and negative *** existing strategies are *** proposed model incorporates aspect extraction,association rule mining and the deep learning technique Bidirectional EncoderRepresentations from Transformers(BERT).Aspects are extracted using Part of Speech Tagger and association rulemining is used to associate aspects with opinion ***,classification was performed using *** proposed approach attained an average of 89.45%accuracy,88.45%precision and 85.98%recall on different datasets of products and *** results showed that the proposed technique achieved better than state-of-the-art sentiment analysis techniques.

关键词： Aspects deep learning lexicon sentiments reviews

Synergic Effect of Reworking for Imperfect Quality Items with the Integration of Multi-Period Delay-in-Payment and Partial Backordering in Global Supply Chains

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering 2021年第2期7卷 260-271页

作者： Waqas Ahmed Muhammad Moazzam Biswajit Sarkar saif ur rehman Department of Operations and Supply Chain NUST Business SchoolNational University of Sciences and TechnologyIslamabad 44000Pakistan Department of Industrial Engineering Yonsei UniversitySeoul 03722Republic of Korea Department of Management Science Lahore Garrison UniversityLahore 54660Pakistan

In intercontinental trade and economics goods are bought from a global *** occasion,the expected lot may include a fraction of defective *** imperfect items still have worth and can be sold to customers after *** is cost-effective and sustainable to rework such items in nearby repair workshops rather than return *** reworked items can be returned from the workshop to the buyer when shortages are equal to the quantity of imperfect *** the meantime,the supplier correspondingly deals a multi-period delay-in-payments strategy with *** entire profit has been maximized with paybacks for interim *** study aims to develop a synergic inventory model to get the most profit by making an allowance for reworking,multi-period delay-in-payments policy,and *** findings of the proposed model augment inventory management performance by monitoring cycle time as well as fraction of phase with optimistic inventory for a supply *** results demonstrate that profit is smaller if the permitted period given by supplier to buyer is equal to or greater than the cycle time,and profit is greater if the permitted period is smaller than the cycle *** algebraic method is engaged to make a closed system optimum *** mathematical experiment of this study is constructed to provide management insights and tangible practices.

关键词： Imperfect items Rework Shortages Multi-period delay-in-payments Non-derivative methodology

A Heuristics-Based Cost Model for Scientic Workow Scheduling in Clou

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第6期67卷 3265-3282页

作者： Ehab Nabiel Al-Khanak Sai Peck Lee saif ur rehman Khan Navid Behboodian Osamah Ibrahim Khalaf Alexander Verbraeck Hans van Lint Department of Transport and Planning Faculty of Civil Engineering and Geosciences(CiTG)Delft University of TechnologyDelftNetherlands Faculty of Computer Science and Information Technology University of MalayaKuala LumpurMalaysia Department of Computer Science COMSATS University Islamabad(CUI)IslamabadPakistan Faculty of Computing and Digital Technology HELP UniversityKuala LumpurMalaysia Al-Nahrain Nanorenewable Energy Research Centre Al-Nahrain UniversityBaghdadIraq Department Multi-Actor Systems Faculty of TechnologyPolicy and Management(TPM)Delft University of TechnologyDelftNetherlands

Scientic Workow Applications(SWFAs)can deliver collaborative tools useful to researchers in executing large and complex scientic ***,Scientic Workow Scheduling(SWFS)accelerates the computational procedures between the available computational resources and the dependent workow jobs based on the researchers’***,cost optimization is one of the SWFS challenges in handling massive and complicated tasks and requires determining an approximate(near-optimal)solution within polynomial computational *** by this,current work proposes a novel SWFS cost optimization model effective in solving this *** proposed model contains three main stages:(i)scientic workow application,(ii)targeted computational environment,and(iii)cost optimization *** model has been used to optimize completion time(makespan)and overall computational cost of SWFS in cloud computing for all considered scenarios in this research *** will ultimately reduce the cost for service *** the same time,reducing the cost has a positive impact on the protability of service providers towards utilizing all computational resources to achieve a competitive advantage over other cloud service *** evaluate the effectiveness of this proposed model,an empirical comparison was conducted by employing three core types of heuristic approaches,including Single-based(i.e.,Genetic Algorithm(GA),Particle Swarm Optimization(PSO),and Invasive Weed Optimization(IWO)),Hybrid-based(i.e.,Hybrid-based Heuristics Algorithms(HIWO)),and Hyper-based(i.e.,Dynamic Hyper-Heuristic Algorithm(DHHA)).Additionally,a simulation-based implementation was used for SIPHT SWFA by considering three different sizes of *** proposed model provides an efcient platform to optimally schedule workow tasks by handing data-intensiveness and computational-intensiveness of *** results reveal that the proposed cost optimization model attained an optimal Job completio

关键词： Scientic workow scheduling empirical comparison cost optimization model heuristic approach cloud computing

基于零次学习的半监督BERTopic模型研究——以移动电子商务应用程序中的用户投诉为例

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于零次学习的半监督BERTopic模型研究——以移动电子商务应用程...

作者： HAFIZ saif ur rehman 西南财经大学

学位级别：硕士

电子商务是一个在世界各地被广泛利用的平台。到2023年,全世界的电子商务收入额将达到4.11万亿美元。这项研究旨在确定用户在使用移动电子商务应用程序时面临的共同问题。为了实现这一目标,通过使用Similar Web和Google Play Store统计... 详细信息

电子商务是一个在世界各地被广泛利用的平台。到2023年,全世界的电子商务收入额将达到4.11万亿美元。这项研究旨在确定用户在使用移动电子商务应用程序时面临的共同问题。为了实现这一目标,通过使用Similar Web和Google Play Store统计等工具刮取11个电子商务B2B和B2C应用程序,收集了857616条用户反馈数据。所选的应用来自Google Play Store,Alibaba、Aliexpress、Amazon、e Bay、Etsy、Wish、SHEIN、Shopee、Flipkart、Fetch Rewards和DHgate,来自全球不同地区。然后对收集到的给出一星和二星评价的用户数据进行分析和可视化,以确定用户投诉的模式和趋势。研究方法涉及五个步骤,包括数据收集、语言检测、翻译、标签管理,以及使用半监督的BERTopic主题建模与零点学习进行分类。这种方法确定了用户在使用这些移动电子商务应用时面临的3个宏观类别和38个微观类别的问题。研究发现,用户面临的最常见的宏观类问题与"APP Functional Issues"有关,占总投诉量的56%。这类问题包括崩溃、缓慢的加载时间和使用应用程序时的错误。第二大类问题是"Customer Service Issues",占用户投诉的37.68%。这类问题包括对糟糕的客户服务、延迟回应和无助的支持的投诉。第三类也是最后一类问题是"Scam and Frauds Issues",占评论的8.70%,包含对这些电子商务应用的欺诈活动的投诉。在所有研究的应用程序中发现的微观类问题显示,用户的主要关注点是"bad user interface",其投诉数量最高。这个类别包括关于混乱的导航、糟糕的布局和难以找到物品的投诉。微观类的其他突出问题包括"customer service"和"update issues"。通过对用户评论进行彻底的主题分析,研究人员提供了克服这些问题的建议。这些建议旨在改善整体用户体验,提高客户满意度,确保高比例的忠诚客户,吸引新客户,并最终提高销售额。总的来说,这项研究的结果强调了在开发和改进电子商务应用程序时考虑用户反馈和关注的重要性。通过实施本研究提供的建议,电子商务公司可以改善用户体验,提高客户忠诚度,最终导致这个行业的发展。然而,需要注意的是,本研究有一些局限性,必须考虑对其有效性的威胁。尽管如此,本研究的结果对移动电子商务应用的用户所面临的问题提供了宝贵的见解。

关键词：电子商务应用评论零样本文本分类自然语言推理 BERTopic建模

RePizer：a framework for prioritization of software requirements

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

Frontiers of Information Technology & Electronic Engineering 2016年第8期17卷 750-765页

作者： saif ur rehman KHAN Sai Peck LEE Mohammad DABBAGH Muhammad TAHIR Muzafar KHAN Muhammad ARIF Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur 50603 Malaysia Faculty of Computing and Information Technology University of Jeddah Jeddah 21589 Saudi Arabia College of Computer and Information Sciences (Muzahmiyah Branch) King Saud University Riyadh 11362 Saudi Arabia Department of Computer Science University of Gujrat Gujrat 50700 Pakistan

The standard software development life cycle heavily depends on requirements elicited from stakeholders. Based on those requirements, software development is planned and managed from its inception phase to closure. Due to time and resource constraints, it is imperative to identify the high-priority requirements that need to be considered first during the software development process. Moreover, existing prioritization frameworks lack a store of historical data useful for selecting the most suitable prioritization technique of any similar project domain. In this paper, we propose a framework for prioritization of software requirements, called Re Pizer, to be used in conjunction with a selected prioritization technique to rank software requirements based on defined criteria such as implementation cost. ReP izer assists requirements engineers in a decision-making process by retrieving historical data from a requirements repository. Re Pizer also provides a panoramic view of the entire project to ensure the judicious use of software development resources. We compared the performance of Re Pizer in terms of expected accuracy and ease of use while separately adopting two different prioritization techniques, planning game（PG） and analytical hierarchy process（AHP）. The results showed that Re Pizer performed better when used in conjunction with the PG technique.

关键词： Software requirements Requirements prioritization techniques Prioritization framework Planning game Analytical hierarchy process

Sedimentology of Marl and Marly Limestone Sequence of Upper Cretaceous Kawagarh Formation from Northern Kalachitta Range, Attock Hazara Fold and Thrust Belt, Pakistan

在线全文

学校读者我要写书评

暂无评论

Open Journal of Geology 2019年第1期9卷 1-14页

作者： saif ur rehman Khalid Mehmood Muhammad Fahad Ullah Naveed Ahsan Faisal rehman Tariq Mahmood Mahboob Ahmed Department of Earth Sciences University of Sargodha Sargodha Pakistan Institute of Geology University of the Punjab Lahore Pakistan Oil and Gas Development Corporation Limited Islamabad Pakistan

Upper Cretaceous Kawagarh Formation is well exposed in the Attock Hazara Fold and Thrust Belt (AHFTB) and shows significant lateral and vertical variations in lithology. The present work deals with the sedimentological studies of marl and marly limestone sequence of Kawagarh Formation exposed at the Bagh Neelab, Ghariala north and Sojhanda villages in Northern Kalachitta Range. Detailed petrographic studies of marly limestone and hard marl substrate show that planktons and oysters are the main skeletal constituents of studied samples and clay and detrital quartz mainly composed the non skeletal fraction. X-Ray diffraction analyses of selected marl samples confirm the petrographic data. On the basis of skeletal and non skeletal content, two microfacies—marl microfacies and Planktonic microfacies are constructed. The faunal content, their paleoecology and detrital content of microfacies suggest that marl and marly limestone sequence of Kawagarh Formation was deposited over the mid and outer ramp settings.

关键词： Attock Hazara Fold & Thrust Belt Fauna Kalachitta Range Microfacies Ramp