检索结果-南通市图书馆

Deep Neural Network Based Spam Email Classification Using Attention Mechanisms

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 Intelligent Learning Systems and Applications 2023年第4期15卷 144-164页

作者： Md. Tofael Ahmed Mariam Akter Md. Saifur Rahman Maqsudur Rahman Pintu Chandra Paul Miss. Nargis Parvin almas Hossain Antar Department of Information and Communication Technology Comilla University Cumilla Bangladesh Department of Computer Science and Engineering Bangladesh Army International University of Science and Technology Cumilla Bangladesh

Spam emails pose a threat to individuals. The proliferation of spam emails daily has rendered traditional machine learning and deep learning methods for screening them ineffective and inefficient. In our research, we employ deep neural networks like RNN, LSTM, and GRU, incorporating attention mechanisms such as Bahdanua, scaled dot product (SDP), and Luong scaled dot product self-attention for spam email filtering. We evaluate our approach on various datasets, including Trec spam, Enron spam emails, SMS spam collections, and the Ling spam dataset, which constitutes a substantial custom dataset. All these datasets are publicly available. For the Enron dataset, we attain an accuracy of 99.97% using LSTM with SDP self-attention. Our custom dataset exhibits the highest accuracy of 99.01% when employing GRU with SDP self-attention. The SMS spam collection dataset yields a peak accuracy of 99.61% with LSTM and SDP attention. Using the GRU (Gated Recurrent Unit) alongside Luong and SDP (Structured Self-Attention) attention mechanisms, the peak accuracy of 99.89% in the Ling spam dataset. For the Trec spam dataset, the most accurate results are achieved using Luong attention LSTM, with an accuracy rate of 99.01%. Our performance analyses consistently indicate that employing the scaled dot product attention mechanism in conjunction with gated recurrent neural networks (GRU) delivers the most effective results. In summary, our research underscores the efficacy of employing advanced deep learning techniques and attention mechanisms for spam email filtering, with remarkable accuracy across multiple datasets. This approach presents a promising solution to the ever-growing problem of spam emails.

关键词： Spam Email Attention Mechanism Deep Neural Network Bahdanua Attention Scale Dot Product

Transformer Dissolved Gas Analysis Using Least Square Support Vector Machine and Bootstrap

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transformer Dissolved Gas Analysis Using Least Square Suppor...

Modeling of a Power Transformer Winding for Deformation Detection Based on Frequency Response Analysis

第二十六届中国控制会议

作者： Shintemirov almas Department of Electrical Engineering and Electronics The University of Liverpool

This paper presents a least square support vector machine（LS-SVM）approach to dissolved gas analysis（DGA）problems for power *** methods are employed to improve the diagnosis accuracy for DGA ***,bootstrap preprocessing is utilised to equalise the sample numbers for different fault ***,the preprocessed samples are inputted to a classier for fault *** comparison purposes,four classifiers are utilised,*** neural network（ANN）,K-nearest neighbour（KNN）,simple SVM and *** classification accuracy of LS-SVM is then compared with the ones of ANN,KNN and a simple *** results indicate that the LS-SVM approach can significantly improve the diagnosis accuracies for transformer fault classification.

关键词： Transformer Dissolved Gas Analysis Least Square Support Vector Machine Bootstrap

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Modeling of a Power Transformer Winding for Deformation Dete...

Multi-scale characterizations of colon polyps via computed tomographic colonography

第二十六届中国控制会议

作者： Shintemirov almas Department of Electrical Engineering and Electronics The University of Liverpool

The paper presents a mathematical model of disc-type power transformer winding for frequency response analysis（FRA）based on traveling wave and multiconductor transmission line *** disc of the model is described by traveling wave equations,which are connected to each other in a form of multiconductor transmission line *** model is applied to FRA simulation in order to study winding axial and radial deformation and its *** of the simulated winding deformation cases with the reference FRA traces is given and discussed to explore the potentials of the proposed model for winding fault detection.

关键词： Transformer winding frequency response analysis transfer function deformation detection

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Visual Computing for Industry,Biomedicine,and Art 2019年第1期2卷 245-256页

作者： Weiguo Cao Marc J.Pomeroy Yongfeng Gao Matthew A.Barish almas F.Abbasi Perry J.Pickhardt Zhengrong Liang The Department of Radiology Stony Brook UniversityStony BrookNY 11794USA The Departments of Radiology and Biomedical Engineering Stony Brook UniversityStony BrookNY 11794USA The Department of Radiology School of MedicineUniversity of WisconsinMadisonWI 53792USA

Texture features have played an essential role in the field of medical imaging for computer-aided *** gray-level co-occurrence matrix(GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these *** study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture *** this study,we first introduce a new parameter-stride,to explore the definition of *** we propose three multi-scaling GLCM models according to its three parameters,(1)learning model by multiple displacements,(2)learning model by multiple strides(LMS),and(3)learning model by multiple *** models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick *** further analyze the three parameters,we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign ***,the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning *** obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

关键词： Colon cancer Computed tomographic colonography Polyp characterization Texture feature

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

可穿戴式多巴胺和尿酸生物传感器的研究

可穿戴式多巴胺和尿酸生物传感器的研究

作者： Kiran almas 大连理工大学

学位级别：硕士

本论文制备了基于FeO纳米粒子功能化掺氮碳纳米管检测生物分子的可穿戴传感器。利用电化学方法检测生物小分子如多巴胺(DA)、尿酸(UA)等,主要采用脉冲伏安(DPV)法。制备了一种性能优异的氮掺杂碳纳米管通过丝网印刷预先排列的碳墨水辨... 详细信息

本论文制备了基于FeO纳米粒子功能化掺氮碳纳米管检测生物分子的可穿戴传感器。利用电化学方法检测生物小分子如多巴胺(DA)、尿酸(UA)等,主要采用脉冲伏安(DPV)法。制备了一种性能优异的氮掺杂碳纳米管通过丝网印刷预先排列的碳墨水辨别出底物中多巴胺(DA)和尿酸(UA),这种基于PET基底的丝网印刷碳墨水组装于可穿戴、灵活、耐用的传感器上。CNT和FeO纳米颗粒分别对DA和UA的氧化有较高的电催化性能,可通过阳极峰位置检测特定的生物分子。可穿戴传感器之间相互作用大,可靠性好,并且有较好的性能和线性响应检测,尤其利用手工打印的传感器应用于诸多商业领域,其中丝网印刷技术展示了其独特的检测方法来影响可穿戴传感器工艺。以材料的相互作用和性能为基础,对材料的电化学反应过程和传感性质是密不可分的。本论文主要是采用手工丝网印刷和碳素油墨传感器印刷传感器,利用FeO纳米粒子功能化掺氮碳纳米管作为工作电极,并装配传感器导线三电极,然后利用电化学工作站脉冲伏安法对多巴胺(DA)、尿酸(UA)等生物小分子进行检测,以分析检测底物的检测限和灵敏度。因此本工作重点关注于获得一个线性范围宽、灵敏度高,低检测下限的可穿戴传感器对于多巴胺和尿酸等检测。检测限随着温度的适当变化而变化。在计算检测限值时,最常用的是作为一个周期内,复合材料的传感性能在材料的检测和消耗中受到一定的影响和测量变化。不同的脉冲伏安曲线定义为对材料的检测性能,基于研究线性范围和检测限,得到一个基于FeO纳米粒子功能化掺氮碳纳米管具有优异的传感性能。基于PET基底的可穿戴式传感器检测中,通常关注的是材料制备及低成本。本研究领域涉及FeO纳米粒子功能化掺氮碳CNT用于传感器,及打印于PET基底表面,对碳纳米管材料进行表面掺杂并得到预期的工作和较好的性能。此工作围绕着改性碳墨水应用于传感器的描述和交出。本文制备了掺杂碳的方法FeO@CNT新方法,并将可穿戴传感器与设备结合在一起。在此研究中得到相关表征技术及良好的传感性能,是未来发展的重要研究方向。

关键词：生物传感器多巴胺尿酸碳纳米管

Comparative Water Efficiency Analysis of Sole and Multiple Cropping Systems under Tunnel Farming in Punjab-Pakistan

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 of Water Resource and Protection 2020年第6期12卷 455-471页

作者： Hina Fatima Lal K. almas Sehrish Haroon Department of Finance and Economics Mohammad Ali Jinnah University Karachi Pakistan Paul Engler College of Agriculture and Natural Sciences West Texas A & M University Canyon TX USA Department of Public Administration Fatima Jinnah Women University Rawalpindi Pakistan

Water scarcity is the growing concern of present times, requiring its efficient utilization deemed as necessity. Rapidly growing population has significantly exerted pressure on its demand, in Pakistan. In order to fulfill it, all factors of production are required to be used in the possibly most efficient way. Good quality and quantity of water are the growing concerns of producers in Pakistan and around the globe. The efficient water utilization is crucial to optimize the farm returns under the selected sole and multiple cropping systems. This study considered the water efficiency analysis of multiple and sole cropping systems, with the aim of finding out cropping patterns more efficient in terms of water utilization in Pakistan. In order to estimate the water efficiency analysis, the Data Envelopment Analysis (DEA) is run to find out the water efficient cropping systems among sole and multiple cropping systems. The Tobit analysis is also used to find out the factors affecting the water efficiency of selected farms in the study area. The results of the study report an inefficient water usage in terms of irrigation, the inefficient use of water instigates the wastage of one of the most important as well as scarce farm inputs especially water, in case of multiple cropping system. Around 51% and 13% of water inefficiency are present under multiple and sole cropping systems, respectively. Basin irrigation is the method for irrigation, used by the farmers of the study area approximating to be 95% - 97%. It is one of the most conventional and least efficient methods of irrigation. Only 2.67 and 4.67 percent of farms were using the Furrow irrigation method, which is way more efficient and steady as compared to Basin irrigation method, respectively. It appears as a requirement that the most efficient methods regarding water application in Pakistan should be recognized. Lack of management in wate

关键词： Water Efficiency Irrigated Agriculture Sole and Multiple Cropping Tun-nel Farming Punjab-Pakistan Data Envelopment Analysis (DEA) Tobit Analysis

Influence of catalytic systems on process of model object hydrogenation

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 Coal Science & Technology 2014年第1期1卷 88-92页

作者： Murzabek Ispolovich Baikenov Gulzhan Gausilevna Baikenova Bolat Shaimenovich Sarsembayev Alma Baimagambetova Tateeva almas Tusipkhan Aisha Zharasovna Matayeva Karaganda State University Karaganda 100028Kazakhstan

On the basis of b-FeOOH,Fe(OA)_(3),Fe_(3)O_(4) iron and spherical catalysts NiO/SiO_(2),Fe_(2)O_(3)/SiO_(2) derived from slag waste coals of heating electrical stations,the hydrogenation of model polycyclic hydrocarbon at presence of nanodimensioned catalysts antracene was *** the example of conversion of anthracene,it was shown that upon release of hydrogenation of the product yield and degradation of polycyclic hydrocarbons in the hydrogenation,the mentioned catalyst systems appeared to be in the following order:nanoparticles b-FeOOH,Fe(OA)_(3) and Fe_(3)O_(4)[spherical catalysts NiO/SiO_(2),Fe_(2)O_(3)/SiO_(2)[commercial cobalt-molybdenum *** results showed that the catalysts studied are promising catalysts for the hydrogenation of polycyclic hydrocarbons and may be used for direct coal liquefaction.

关键词： Antracene Multi-ring hydrocarbons Nanocatalysts Spherical catalysts Hydrogenation

对图书发行专业过去与现在的粗浅理解——两代人的心宿

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

蒙古学研究（蒙文版） 2023年第3期 19-22,123页

作者：吉·阿拉玛斯不详

The article presents a comprehensive portrayal of the"Publishing and Distribution Major,"serving as a testament to the aspirations of two *** delves into the initial establishment of the major,examines its current teaching situation,and celebrates the outstanding achievements of its ***,it pays a heartfelt tribute to the remarkable historical accomplishments of the alma mater over the span of 70 years.

关键词： accomplishment Major outstanding

Assessment of Wastewater Quality of Drains for Irrigation

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 Environmental Protection 2013年第9期4卷 937-945页

作者： almas Hamid Mahrukh Zeb Asim Mehmood Sana Akhtar Samia Saif Department of Environmental Sciences Kinnaird College for Women Lahore Pakistan Global Environmental Laboratories La- hore Pakistan

Rapid industrialization and overpopulation have stimulated increase in waste water both domestic and industrial. Due to lack of inefficient sewerage system and absence of treatment plants, the wastewater is discharged into drainage systems causing environmental and health implications. At various points, the wastewater of these drains is used for irrigation purposes. This study characterizes the effluent of major drains of Lahore city and assesses its suitability for irrigation. Wastewater samples were collected from drains in winter and spring seasons and analyzed for various parameters of special concern to irrigation. TSS, oil and grease, BOD, COD, chloride, TDS, sodium, SAR, bicarbonate ions, EC, iron, Copper and Nickel were found to be varied in concentration in different drains when compared with NEQS (National Environment Quality Standards) and FAO guidelines for irrigation in both seasons. Regular monitoring and proper treatment of wastewater before discharging into the drains can reduce the pollution in these drains.

关键词： Industrialization Wastewater Quality Drains Irrigation Winter and Spring Season FAO Guidelines