检索结果-南通市图书馆

Smart prediction of liquefaction-induced lateral spreading

Journal of Rock Mechanics and Geotechnical Engineering 2024年第6期16卷 2310-2325页

作者： muhammad Nouman Amjad Raja Tarek Abdoun waleed El-Sekelly New York University(NYU)Abu Dhabi Abu Dhabi129188United Arab Emirates University of Management and Technology Lahore54372Pakistan Department of Civil and Environmental Eng. Rensselaer Polytechnic Institute(RPI)1108th StreetJEC 4049TroyNY12180USA Department of Structural Engineering Mansoura UniversityMansoura35516Egypt

The prediction of liquefaction-induced lateral spreading/displacement(Dh)is a challenging task for civil/geotechnical *** this study,a new approach is proposed to predict Dh using gene expression programming(GEP).Based on statistical reasoning,individual models were developed for two topographies:free-face and gently sloping *** with a comparison with conventional approaches for predicting the Dh,four additional regression-based soft computing models,*** process regression(GPR),relevance vector machine(RVM),sequential minimal optimization regression(SMOR),and M5-tree,were developed and compared with the GEP *** results indicate that the GEP models predict Dh with less bias,as evidenced by the root mean square error(RMSE)and mean absolute error(MAE)for training(i.e.1.092 and 0.815;and 0.643 and 0.526)and for testing(i.e.0.89 and 0.705;and 0.773 and 0.573)in free-face and gently sloping ground topographies,*** overall performance for the free-face topology was ranked as follows:GEP>RVM>M5-tree>GPR>SMOR,with a total score of 40,32,24,15,and 10,*** the gently sloping condition,the performance was ranked as follows:GEP>RVM>GPR>M5-tree>SMOR with a total score of 40,32,21,19,and 8,***,the results of the sensitivity analysis showed that for both free-face and gently sloping ground,the liquefiable layer thickness(T_(15))was the major parameter with percentage deterioration(%D)value of 99.15 and 90.72,respectively.

关键词： Lateral spreading Intelligent modeling Gene expression programming(GEP) Closed-form solution Feature importance

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

USpider-乌尔都语文本到SQL的数据集

USpider-乌尔都语文本到SQL的数据集

引用

作者： muhammad waleed Asif 中山大学

学位级别：硕士

在自然语言处理(NLP)领域中,文本到SQL转换上取得的显著进步,使得用自然语言与数据库交互成为可能。然而,它在低资源语言如乌尔都语上的表现不足。本研究提出USpider,一个乌尔都语文本到SQL转换数据集,旨在解决文本到SQL任务在乌尔都语... 详细信息

在自然语言处理(NLP)领域中,文本到SQL转换上取得的显著进步,使得用自然语言与数据库交互成为可能。然而,它在低资源语言如乌尔都语上的表现不足。本研究提出USpider,一个乌尔都语文本到SQL转换数据集,旨在解决文本到SQL任务在乌尔都语上的资源稀缺问题,为构建该领域在乌尔都语上的发展奠定基础。USpider包含9,693个乌尔都语自然语言问题及其对应的SQL查询,涉及133个不同领域的166个不同的数据库。数据集的创建采用严谨方法,结合机器翻译、人工改进和迭代审查,确保语言的准确性、连贯性和文化相关性。由此产生的高质量数据集展现了乌尔都语在数据库查询中的丰富性和复杂性。为了验证USpider的科研和使用价值,实验部分我们使用了大型语言模型(LLM),具体是GPT-3.5,应用DINSQL方法进行少样本学习。实验通过执行准确性和匹配准确性等指标进行评估,展示了模型在简单和中等难度查询上表现出色。对于简单查询,模型在不同测试批次中达到69%至72%的执行准确性和54%至58%的精确匹配准确性。对于中等难度查询,执行准确性和精确匹配准确性分别在59%至63%和42%至48%之间。这些发现证实了USpider在提高准确SQL查询方面的作用。然而,实验亦揭示了处理复杂查询和语言变化时的挑战。随着查询难度的增加,困难级别查询的执行准确性下降到40%-59%,非常困难级别的查询下降到38%-42%。精确匹配准确性在这些类别中分别在10%-34%和0%-23%之间。USpider数据集对乌尔都语社区将会具有重大意义,将能开启医疗保健、教育、金融和电子政务等领域数据库的自然语言接口。通过让乌尔都语使用者使用母语与技术互动,研究有助于缩小数字鸿沟,推动NLP的包容性。此外,本研究的发现将对更广泛的NLP领域,尤其是对低资源语言有重要启示。DINSQL方法成功应用于乌尔都语,,强调了为低资源语言专门构建数据集的重要性。USpider的创建方法将为其他语言中的类似挑战提供参考。未来的研究方向包括改进USpider以适应较弱的LLM,探索LLM的局限性,并适应Spider数据集的演变。随着Spider 2.0的预期发布,我将开发USpider 2.0,与它的查询复杂性和多样性的提高保持同步,同时利用LLM架构和训练技术的最新进展。总的来说,USpider为乌尔都语上的NLP研究作出了贡献,提供全面翻译的数据集,并证明了它在乌尔都语文本到SQL转换中的效用。实验结果展示了准确生成SQL查询的潜力,同时指出了需要改进的方面。这项研究为开发兼容性强和可用性高的数据库自然语言接口奠定了基础,赋能乌尔都语社区,推动低资源语言NLP领域的发展。

关键词：文本到SQL 语义解析少样本学习大型语言模型 USpider

来源：

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

Enhanced Fingerprinting Based Indoor Positioning Using Machine Learning

引用

Computers, Materials & Continua 2021年第11期69卷 1631-1652页

作者： muhammad waleed pasha Mir Yasir Umair Alina Mirza Faizan Rao Abdul Wakeel Safia Akram Fazli Subhan Wazir Zada Khan Department of Electrical Engineering National University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Engineering National University of Modern Languages(NUML)Islamabad44000Pakistan Faculty of Computing Capital University of Science and TechnologyIslamabad44000Pakistan

Due to the inability of the Global Positioning System(GPS)signals to penetrate through surfaces like roofs,walls,and other objects in indoor environments,numerous alternative methods for user positioning have been *** those,the Wi-Fi fingerprinting method has gained considerable interest in Indoor Positioning Systems(IPS)as the need for lineof-sight measurements is minimal,and it achieves better efficiency in even complex indoor *** and online are the two phases of the fingerprinting *** researchers have highlighted the problems in the offline phase as it deals with huge datasets and validation of Fingerprints without pre-processing of data becomes a *** learning is used for the model training in the offline phase while the locations are estimated in the online *** researchers have considered the concerns in the offline phase as it deals with huge datasets and validation of Fingerprints becomes an *** learning algorithms are a natural solution for winnowing through large datasets and determining the significant fragments of information for localization,creating precise models to predict an indoor *** training sets are a key for obtaining better results in machine learning ***,an existing WLAN fingerprinting-based multistory building location database has been used with 21049 samples including 19938 training and 1111 testing *** proposed model consists of mean and median filtering as pre-processing techniques applied to the database for enhancing the accuracy by mitigating the impact of environmental dispersion and investigated machine learning algorithms(kNN,WkNN,FSkNN,and SVM)for estimating the *** proposed SVM with median filtering algorithm gives a reduced mean positioning error of 0.7959 m and an improved efficiency of 92.84%as compared to all variants of the proposed method for 108703 m^(2) area.

关键词： Indoor positioning system fingerprinting received signal strength indicator mean position error support vector machine

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Deep Learning Based Efficient Crowd Counting System

引用

Computers, Materials & Continua 2024年第6期79卷 4001-4020页

作者： waleed Khalid Al-Ghanem Emad Ul Haq Qazi muhammad Hamza Faheem Syed Shah Amanullah Quadri Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Centre of Excellence in Cybercrime and Digital Forensics Naif Arab University for Security SciencesRiyadh14812Saudi Arabia Center of Excellence for Information Assurance(COEIA) King Saud UniversityRiyadh12372Saudi Arabia

Estimation of crowd count is becoming crucial nowadays,as it can help in security surveillance,crowd monitoring,and management for different *** is challenging to determine the approximate crowd size from an image of the crowd’s *** in this research study,we proposed a multi-headed convolutional neural network architecture-based model for crowd counting,where we divided our proposed model into two main components:(i)the convolutional neural network,which extracts the feature across the whole image that is given to it as an input,and(ii)the multi-headed layers,which make it easier to evaluate density maps to estimate the number of people in the input image and determine their number in the *** employed the available public benchmark crowd-counting datasets UCF CC 50 and ShanghaiTech parts A and B for model training and testing to validate the model’s *** analyze the results,we used two metrics Mean Absolute Error(MAE)and Mean Square Error(MSE),and compared the results of the proposed systems with the state-of-art models of crowd *** results show the superiority of the proposed system.

关键词： Crowd counting EfficientNet multi-head attention convolutional neural network transfer learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Provoking Buying Behaviors Amid Crises:Unfolding the Underlying Mechanisms of Psychological Impairments

引用

International Journal of Mental Health Promotion 2024年第4期26卷 279-292页

作者： muhammad waleed Ayub Ghouri Guofeng Wang muhammad Ali Hussain Zhisheng Li Tachia Chin School of Management Zhejiang University of TechnologyHangzhou310023China School of Management and Economics University of Electronic Science and Technology of ChinaChengdu611731China Business School NingboTech UniversityNingbo315100China

Crises in the past have caused devastating,long-lasting impacts on the global *** after-effects always bring some dynamic and rigorous challenges for businesses and *** challenges have always been a point of discussion for *** recent COVID-19 pandemic emaciated the global economy,leaving everyone mired in uncertainty,fear,and psychological *** of the headwind features utilized by consumers during pandemic was panic buying(PB),which must be explored in various contexts for policymakers and *** address this gap,this study deployed a moderated mediation mechanism,integrating the health belief model(HBM)and competitive arousal theory(CAT)to excavate the notions underlying PB with the intrusion of evolved real-time psychological disorders:intolerance of uncertainty(IU)and cyberchondria(CYC).The study was conducted as a natural experiment in a South Asian developing economy using online *** found that health beliefs—perceived severity(PSV)and perceived susceptibility(PSC)—positively impact perceived arousal(PA),which causes PB,and that PA has a sturdy mediator ***,in the relationship between health beliefs and arousal,the different psychological disorders were found to have significant moderating roles The study findings can help mitigate risk uncertainties and panic situations and thus contribute to consumers’wellbeing.

关键词： Panic buying health belief model mental health competitive arousal theory intolerance of uncertainty cyberchondria

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Roasted fox nuts (Euryale Ferox L.) contain higher concentration of phenolics, flavonoids, minerals and antioxidants, and exhibit lower Glycemic Index (GI) in human subjects

引用

Food Production, Processing and Nutrition 2022年第1期4卷 1-12页

作者： Marrium Liaquat Imran pasha muhammad Ahsin Abdullah Salik National Institute of Food Science and Technology Faculty of FoodNutrition and Home SciencesUniversity of AgricultureFaisalabad38000Pakistan

Fox nut (Euryale ferox) is categorized among superior quality foods because of its highly nutritious profile. It also serves as a good protein source for vegetarian diets. However, it is not widely consumed, due to soggy texture and bland flavor as compared to other nuts. In this study, we used roasting and seasoning to enhance its consumer acceptance. Furthermore, we have also compared biochemical, nutritional and physical properties of the roasted and unroasted fox nuts;and their Glycemic Index (GI) in human subjects. Results showed that roasting significantly (P ≤ 0.05) improved the minerals content (from 0.58 to 0.66%), protein content (from 11.40 to 14.57%), total phenolics (from 346.02 to 470.62 mg GAE/100 g), flavonoids (from 4.15 to 4.43 mg CE/g), 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity (from 48.54 to 79.13% inhibition) and Ferric Reducing Antioxidant Power (from 662.46 to 957.14 μmol FeSO4/g). Consumer acceptance was evaluated with and without seasoning;both salt and spice seasoned roasted nuts had greater overall acceptability as compared to plain roasted and unroasted nuts. Fox nuts also reported low GI (37%) in human subjects (ethical approval #1772/01-06-2020). Thus, roasted fox nuts can be consumed as nutrient rich and low GI snack;not only as a component of healthy diet but can also be served to patients with metabolic disorders like obesity and diabetes.

关键词： Euryale ferox seeds Fox nuts Roasting Nutritious snack and low glycemic index foods

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Probing nutritional and functional properties of salted noodles supplemented with ripen Banana peel powder

引用

Food Production, Processing and Nutrition 2022年第1期4卷 249-258页

作者： Imran pasha Abdul Basit muhammad Ahsin Farah Ahmad National Institute of Food Science and Technology Faculty of Food Nutrition and Home SciencesUniversity of AgricultureFaisalabad38000Pakistan

Banana peel is appreciated for higher dietary fiber, phenolics, flavonoid contents, and minerals (particularly iron, calcium, and potassium), despite being a waste product. After drying, it can be processed into powder/flour to be combined with wheat flour (WF) for development of value-added products. In this study, we substituted WF with banana peel powder (BPP) at supplementation rates of 5, 10, and 15%, and evaluated their suitability to develop salted noodles. The results showed that the composite flour with 15% BPP had significantly higher protein, ash, and crude fiber content as compared to control. Higher antioxidant capacity was observed in composite flour noodles: total phenolics content (TPC), total flavonoid content (TFC), ferric reducing power (FRAP) and DPPH reducing power were increased up to 278, 260, 143 and 13 percent respectively in the noodles containing 15% BPP as compared to control (100% WF). On the other hand, values for viscosity decreased up to 22% with addition of BPP in WF. Furthermore, water absorption capacity and cooking losses were increased up to 15 and 13 percent respectively with 15% BPP incorporation in WF. Results for sensory evaluation demonstrated that noodles with 10% BPP scored highest for sensory profile.

关键词： Banana peel Noodles Bioactive compounds Pasting properties Waste utilization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Time Pattern-Based Intelligent Cache Optimization Policy on Korea Advanced Research Network

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3743-3759页

作者： waleed Akbar Afaq muhammad Wang-Cheol Song Department of Computer Engineering Jeju National UniversityJeju-si63243Korea

Data is growing quickly due to a significant increase in social media ***,billions of people use an enormous amount of data to access the *** backbone network experiences a substantial load as a result of an increase in *** in the same region or company frequently ask for similar material,especially on social media *** subsequent request for the same content can be satisfied from the edge if stored in proximity to the *** that require relatively low latency can use Content Delivery Network(CDN)technology to meet their *** edge and the data center con-stitute the CDN *** fulfill requests from the edge and minimize the impact on the network,the requested content can be buffered closer to the user *** content should be kept on the edge is the primary *** cache policy has been optimized using various conventional and unconventional methods,but they have yet to include the timestamp beside a video *** 24-h content request pattern was obtained from publicly available *** popularity of a video is influenced by the time of day,as shown by a time-based video *** present a cache optimization method based on a time-based pat-tern of *** problem is described as a cache hit ratio maximization pro-blem emphasizing a relevance score and machine learning model accuracy.A model predicts the video to be cached in the next time stamp,and the relevance score identifies the video to be removed from the ***,we gather the logs and generate the content requests using an extracted video request *** logs are pre-processed to create a dataset divided into three-time slots per day.A Long short-term memory(LSTM)model is trained on this dataset to forecast the video at the next time *** proposed optimized caching policy is evaluated on our CDN architecture deployed on the Korean Advanced Research Network(KOREN)*** finding

关键词： Multimedia content delivery request pattern recognition real-time machine learning deep learning optimization caching edge computing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Empirical Analysis of Software Success Rate Forecasting During Requirement Engineering Processes

引用

Computers, Materials & Continua 2023年第1期74卷 783-799页

作者： muhammad Hasnain Imran Ghani Seung Ryul Jeong muhammad Fermi pasha Sardar Usman Anjum Abbas Lahore Leads University Lahore42000Pakistan Computer and Information Sciences Virginia Military InstituteLexingtonVA24450USA Graduate School of Business IT Kookmin UniversitySeoul136Korea School of Information Technology Monash UniversityBandar Sunway47500Malaysia Department of Computer Science and Software Engineering Grand Asian University Sialkot51040Pakistan Government Sarwar Shaheed Associate College Gujjar KhanRawalpindi46000Pakistan

Forecasting on success or failure of software has become an interesting and,in fact,an essential task in the software development *** order to explore the latest data on successes and failures,this research focused on certain questions such as is early phase of the software development life cycle better than later phases in predicting software success and avoiding high rework?What human factors contribute to success or failure of a software?What software practices are used by the industry practitioners to achieve high quality of software in their day-to-day work?In order to conduct this empirical analysis a total of 104 practitioners were recruited to determine how human factors,misinterpretation,and miscommunication of requirements and decision-making processes play their roles in software success *** discussed a potential relationship between forecasting of software success or failure and the development *** noticed that experienced participants had more confidence in their practices and responded to the questionnaire in this empirical study,and they were more likely to rate software success forecasting linking to the development *** analysis also shows that cognitive bias is the central human factor that negatively affects forecasting of software success *** results of this empirical study also validated that requirements’misinterpretation and miscommunication were themain causes behind software systems’*** has been seen that reliable,relevant,and trustworthy sources of information help in decision-making to predict software systems’success in the software *** empirical study highlights a need for other software practitioners to avoid such bias while working on software *** investigation can be performed to identify the other human factors that may impact software systems’success.

关键词： Cognitive bias misinterpretation of requirements miscommunication software success and failure prediction decision making

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Intelligence Computational Approach for the Fractional 4D Chaotic Financial Model

引用

Computers, Materials & Continua 2023年第2期74卷 2711-2724页

作者： Wajaree Weera Thongchai Botmart Charuwat Chantawat Zulqurnain Sabir waleed Adel muhammad Asif Zahoor Raja muhammad Kristiawan Department of Mathematics Faculty of ScienceKhon Kaen UniversityKhon Kaen40002Thailand Department of Mathematics and Statistics Hazara UniversityMansehraPakistan Department of Mathematical Sciences United Arab Emirates UniversityP.O.Box 15551Al AinUAE Department of Mathematics and Engineering Physics Faculty of EngineeringMansoura UniversityEgypt UniversitéFrançaise D’Egypte Ismailia Desert RoadEl-ShoroukCairoEgypt Future Technology Research Center National Yunlin University of Science and Technology123 University RoadSection 3DouliouYunlin 64002Taiwan Science of Education Universitas BengkuluBengkulu CityIndonesia

The main purpose of the study is to present a numerical approach to investigate the numerical performances of the fractional 4-D chaotic financial system using a stochastic *** stochastic procedures mainly depend on the combination of the artificial neural network(ANNs)along with the Levenberg-Marquardt Backpropagation(LMB)i.e.,ANNs-LMB *** fractional-order term is defined in the Caputo sense and three cases are solved using the proposed technique for different values of the fractional orderα.The values of the fractional order derivatives to solve the fractional 4-D chaotic financial system are used between 0 and *** data proportion is applied as 73%,15%,and 12%for training,testing,and certification to solve the chaotic fractional *** acquired results are verified through the comparison of the reference solution,which indicates the proposed technique is efficient and *** 4-D chaotic model is numerically solved by using the ANNs-LMB technique to reduce the mean square error(MSE).To authenticate the exactness,and consistency of the technique,the obtained performances are plotted in the figures of correlation measures,error histograms,and *** these figures,it can be witnessed that the provided technique is effective for solving such models to give some new insight into the physical behavior of the model.

关键词： Financial model chaotic Levenberg-Marquardt Backpropagation fractional order artificial neural networks reference dataset

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：