检索结果-南通市图书馆

Early-Stage Segmentation and Characterization of Brain Tumor

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第10期73卷 1001-1017页

作者： Syed Nauyan Rashid Muhammad Hanif Usman Habib Akhtar Khalil Omair Inam Hafeez Ur Rehman Department of Computer Science National University of Computer and Emerging Sciences IslamabadPeshawar CampusPakistan faculty of Computer Science and engineering Ghulam Ishaq Khan(GIK)Institute of Engineering Sciences and TechnologyTopiPakistan IFahja Pvt Limited PeshawarPakistan Department of Electrical and Computer engineering COMSATS University IslamabadPakistan

Gliomas are the most aggressive brain tumors caused by the abnormal growth of brain *** life expectancy of patients diagnosed with gliomas decreases *** gliomas are diagnosed in later stages,resulting in imminent *** average,patients do not survive 14 months after *** only way to minimize the impact of this inevitable disease is through early *** Magnetic Resonance Imaging(MRI)scans,because of their better tissue contrast,are most frequently used to assess the brain *** manual classification of MRI scans takes a reasonable amount of time to classify brain *** this,dealing with MRI scans manually is also cumbersome,thus affects the classification *** eradicate this problem,researchers have come up with automatic and semiautomatic methods that help in the automation of brain tumor classification ***,many techniques have been devised to address this issue,the existing methods still struggle to characterize the enhancing *** is because of low variance in enhancing region which give poor contrast in MRI *** this study,we propose a novel deep learning based method consisting of a series of steps,namely:data pre-processing,patch extraction,patch pre-processing,and a deep learning model with tuned hyper-parameters to classify all types of gliomas with a focus on enhancing *** trained model achieved better results for all glioma classes including the enhancing *** improved performance of our technique can be attributed to several ***,the non-local mean filter in the pre-processing step,improved the image detail while removing irrelevant ***,the architecture we employ can capture the non-linearity of all classes including the enhancing ***,the segmentation scores achieved on the Dice Similarity Coefficient(DSC)metric for normal,necrosis,edema,enhancing and non-enhancing tumor classes are 0.95,0.97,0.91,0.93,0.95;respectively.

关键词： Segmentation CNN characterization brain tumor MRI

Preparation and characterization of La_(0.9)Sr_(0.1)Ga_(0.8)Mg_(0.2)O_(3-δ) thin film deposited by radio frequency magnetic sputtering

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 Rare Earths 2013年第6期31卷 582-588页

作者：阳建君马文会于洁陈秀华邢洁李蕊 National engineering Laboratory for Vacuum Metallurgy faculty of Metallurgical and Energy engineering Kunming University of Science and Technology faculty of Environment Science and engineering Kunming University of Science and Technology faculty of Physical Science and Technology Yunnan University

La0.9Sr0.1Ga0.8Mg0.2O3–？（LSGM） electrolyte materials were synthesized by the solid state reaction method. The conductivity of LSGM materials was detected by four probe method, and it was 0.08 S/cm at 850 oC. Dense and uniform films of LSGM materials were deposited by the magnetic sputtering on substrates of Si and La0.7Sr0.3Cr0.5Mn0.5O3–？（LSCM）. The experimental results showed that the deposition rates dropped and the average grain sizes of the films enlarged with increase in the substrate temperatures. In the sputtering process, the LSGM film was deposited with preferred growth direction. After annealing, the preferred growth direction disappeared and the film surface became smoother and denser. Through observing the deposition process, deposition mechanism was proposed, which was consistent with a model of island growth.

关键词： solid state reaction magnetic sputtering annealing island growth rare earths

Characteristic evaluation on spray-deposited WFTO thin films as a function of W doping ratio

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2014年第4期33卷 433-441页

作者： G.Turgut E.F.Keskenler S.Aydin D.Tatar E.Sonmez S.Dogan B.Duzgun Department of Physics Education Kazim Karabekir Education FacultyAtatürk University Department of Nanotechnology Faculty of EngineeringRecep Tayyip Erdogan University Department of Electrical and Electronics engineering Faculty of Engineering and ArchitectureBalikesir University

Abstract In this work, F and F ＋ W simultaneously doped SnO2 highly transparent conducting thin films were depos- ited on glass substrates at （500 4± 5） ℃ temperature by the spray pyrolysis method. Microstructural, morphological, electrical and optical properties of FrO films were investi- gated as a function of tungsten （W） doping, in the range from 0 to 5 at%. X-ray diffraction patterns show that the films exhibit a tetragonal cassiterite structure and （200） preferen- tial orientation of FTO film, and the relative strength of these peaks changes with altering the W doping ratio. The pre- ferred growth of （211） changed to （200） plane with 2 at% W doping level and 3 at% W-doped film had （200） orientation and with further doping, this changed to （110） orientation. The scanning electron microscopy and atomic force microscopy images of the films indicate that the films are made up of dense small particles of a pyramidal shape and have a smooth surface. It was observed that the surface morphology of the films did not change much when the W element was inserted to the FrO structure. It was found that the sheet resistance values of the films varied with W doping ratio, and 2 at% W-doped FTO thin film exhibited the lowest values of sheet resistance （1.12Ω）. Also, the highest figure of merit, infrared reflectivity and optical band gap values werecalculated for 2 at% W-doped FTO film as 50.9× 10-2 Ω-1, 98.82 % and 4.13 eV, respectively. These results make the films an effective candidate for usage in many optoelectronic applications and photo-thermal conversion of solar energy.

关键词： WFTO FrO Spray pyrolysis Thin films Lattices

Higher Order OAM Mode Generation Using Wearable Antenna for 5G NR Bands

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & engineering 2023年第10期47卷 537-551页

作者： Shehab Khan Noor Arif Mawardi Ismail Mohd Najib Mohd Yasin Mohamed Nasrun Osman Thennarasan Sabapathy Shakhirul Mat Salleh Ping Jack Soh Ali Hanafiah Rambe Nurulazlina Ramli Advanced Communication engineering(ACE) Centre of ExcellenceFaculty of Electronic Engineering&TechnologyUniversiti Malaysia PerlisKangarPerlisMalaysia faculty of engineering Technology(FTK) Department of Electronic Engineering TechnologyUniversiti Malaysia Perlis(UniMAP)Unicity Alam Campus02100Padang BesarPerlisMalaysia Centre for Wireless Communications(CWC) University of Oulu90570OuluFinland Department of Electrical engineering Universitas Sumatera UtaraMedan20155Indonesia Centre for Advanced Electrical and Electronic System(CAEES)faculty of engineering Built Environment and Information TechnologySEGi University SelangorMalaysia

This paper presents a flexible and wearable textile array antenna designed to generate Orbital Angular Momentum(OAM)waves with Mode+2 at 3.5 GHz(3.4 to 3.6 GHz)of the sub-6 GHz fifth-generation(5G)New Radio(NR)*** proposed antenna is based on a uniform circular array of eight microstrip patch antennas on a felt textile *** contrast to previous works involving the use of rigid substrates to generate OAM waves,this work explored the use of flexible substrates to generate OAM waves for the first *** than that,the proposed antenna was simulated,analyzed,fabricated,and tested to confirm the generation of OAMMode+*** the same design,OAM Mode−2 can be generated readily simply by mirror imaging the feed *** that the proposed antenna operated at the desired frequency of 3.5 GHz with an overall bandwidth of 400 MHz in free ***,mode purity analysis is carried out to verify the generation of OAM Mode+2,and the purity obtained was 41.78%at free space flat ***,the effect of antenna bending on the purity of the generated OAM mode is also ***,the influence of textile properties on OAM modes is examined to assist future researchers in choosing suitable fabrics to design flexible OAM-based *** a comprehensive analysis considering different factors related to wearable applications,this paper demonstrates the feasibility of generating OAMwaves using textile ***,as per the obtained Specific Absorption Rate(SAR),it is found that the proposed antenna is safe to be *** findings of this work have a significant implication for body-centric communications.

关键词： Wearable antenna OAM vortex waves 5G textile antenna microstrip patch antenna specific absorption rate(SAR)

Optimizing Deep Neural Networks for Face Recognition to Increase Training Speed and Improve Model Accuracy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第12期38卷 315-332页

作者： Mostafa Diba Hossein Khosravi faculty of Electrical engineering Shahrood University of TechnologyShahroodSemnanP.O.Box ***Iran

Convolutional neural networks continually evolve to enhance accuracy in addressing various problems,leading to an increase in computational cost and model *** paper introduces a novel approach for pruning face recognition models based on convolutional neural *** proposed method identifies and removes inefficient filters based on the information volume in feature *** each layer,some feature maps lack useful information,and there exists a correlation between certain feature *** associated with these two types of feature maps impose additional computational costs on the *** eliminating filters related to these categories of feature maps,the reduction of both computational cost and model size can be *** approach employs a combination of correlation analysis and the summation of matrix elements within each feature map to detect and eliminate inefficient *** method was applied to two face recognition models utilizing the VGG16 and ResNet50V2 backbone *** the proposed approach,the number of filters removed in each layer varies,and the removal process is independent of the adjacent *** convolutional layers of both backbone models were initialized with pre-trained weights from *** training,the CASIA-WebFace dataset was utilized,and the Labeled Faces in the Wild(LFW)dataset was employed for benchmarking *** the VGG16-based face recognition model,a 0.74%accuracy improvement was achieved while reducing the number of convolution parameters by 26.85%and decreasing Floating-point operations per second(FLOPs)by 47.96%.For the face recognition model based on the ResNet50V2 architecture,the ArcFace method was *** removal of inactive filters in this model led to a slight decrease in accuracy by 0.11%.However,it resulted in enhanced training speed,a reduction of 59.38%in convolution parameters,and a 57.29%decrease in FLOPs.

关键词： Face recognition network pruning FLOPs reduction deep learning ArcFace

Policy on water Loss Control in 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

Journal of Geoscience and Environment Protection 2018年第3期6卷 100-107页

作者： Xinyue Liu Shihu Shu National engineering Research Center of Urban water resource Shanghai China

The Chinese government has raised great attention on water resources and environment over the past several years. In dealing with the issues of water pollution, water management, and the imbalance of water resources, China’s state council released “water Pollution Prevention and Control Action Plan” in 2015. This policy has become a guideline to promote water sustainability in the long run. Since then, a number of regulatory policies were released to increase the focus on water conservation. Among those actions, water loss control associated with distribution systems is regarded as a key solution to improve water supply efficiency. This paper provided a comprehensive introduction to the framework of water loss control policy in China.

关键词： water Distribution Networks water Loss Control water Ten Plan water Loss Rate Non-Revenue water Rate

Fuzzy logic controller implementation on a microbial electrolysis cell for biohydrogen production and storage

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical engineering 2021年第12期34卷 149-159页

作者： Gabriel Khew Mun Hong Mohd Azlan Hussain Ahmad Khairi Abdul Wahab Department of Chemical engineering Faculty of EngineeringUniversiti Malaya50603 Kuala LumpurMalaysia Department of Biomedical engineering Faculty of EngineeringUniversiti Malaya50603 Kuala LumpurMalaysia Centre for Separation Science and Technology(CSST) Faculty of EngineeringUniversiti Malaya50603 Kuala LumpurMalaysia

This work presents the implementation of fuzzy logic control(FLC) on a microbial electrolysis cell(MEC).Hydrogen has been touted as a potential alternative source of energy to the depleting fossil fuels. MEC is one of the most extensively studied method of hydrogen production. The utilization of biowaste as its substrate by MEC promotes the waste to energy initiative. The hydrogen production within the MEC system, which involves microbial interaction contributes to the system's nonlinearity. Taking into account of the high complexity of MEC system, a precise process control system is required to ensure a wellcontrolled biohydrogen production flow rate and storage application inside a tank. Proportionalderivative-integral(PID) controller has been one of the pioneer control loop mechanism. However, it lacks the capability to adapt properly in the presence of disturbance. An advanced process control mechanism such as the FLC has proven to be a better solution to be implemented on a nonlinear system due to its similarity in human-natured thinking. The performance of the FLC has been evaluated based on its implementation on the MEC system through various control schemes progressively. Similar evaluations include the performance of Proportional-Integral(PI) and PID controller for comparison purposes. The tracking capability of FLC is also accessed against another advanced controller that is the model predictive controller(MPC). One of the key findings in this work is that the FLC resulted in a desirable hydrogen output via MEC over the PI and PID controller in terms of shorter settling time and lesser overshoot.

关键词： Fuzzy logic control Process control Nonlinear Microbial electrolysis cell Renewable energy Hydrogen

Control mechanism of a cable truss system for stability of roadways within thick coal seams

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 2017年第5期24卷 1098-1110页

作者：严红何富连李林玥冯锐敏邢鹏飞 Key Laboratory of Deep Coal resource Mining Ministry of Education of China (School of Mines China University of Mining & Technology) faculty of resources and Safety engineering China University of Mining and Technology (Beijing) Guizhou Xinlian Blasting engineering Group Co. Ltd. Department of Mining and Mineral resources engineering Southern Illinois University

Cable truss systems have been widely applied in roadways with complicated conditions, such as the large cross-sections of deep wells, and high tectonic stress. However, they are rarely applied to roadways with extremely thick coal seams because the control mechanism of the system for the deformation of the roof and the separation between coal rock segments is not completely understood. By using the relationship between the support system and the roof strata, a mechanical model was established to calculate the deformation of the roof in a thick coal seam with bedding separation under different support conditions: with an anchor truss support and without support. On this basis, the research was used to deduce a method for computing the minimum pre-tightening forces in the anchor truss, the maximum amounts of subsidence and separation with, and without, anchor truss support under the roof, and the maximum subsidence and the decreasing amounts of the separation before and after adopting the anchor truss. Additionally, mechanical relationships between the minimum pre-tightening force and the anchoring force in the anchor were analyzed. By taking a typical roadway with thick coal roof as an example, the theoretical results mentioned above were applied in the analysis and testing of a roof supporting project in a roadway field to verify the accuracy of the theory: favorable experimental results were achieved. In addition, the relationships among other parameters were analyzed, including the minimum pre-tightening forces applied by the anchor truss, the angle of inclination of the anchor cable, and the array pitch. Meanwhile, the changing characteristics of the amounts of roof separation and subsidence with key parameters of the support system(such as array pitch, pre-tightening force, and inclination angle) were also analyzed. The research results revealed the acting mechanism of the anchor truss in control of roadway stability with a thick coal seam, providing a theoretic

关键词： cable truss system thick coal seam roof separation pre-tightening force

Finite element modeling assumptions impact on seismic response demands of MRF-buildings

在线全文

学校读者我要写书评

暂无评论

Earthquake engineering and engineering Vibration 2018年第4期17卷 821-834页

作者： Shehata E Abdel Raheem Ahmed K Abdel Zaher Ahmed MA Taha Civil engineering Department Engineering College Taibah University Civil engineering Department Faculty of Engineering Assiut University

Recent seismic events have raised concerns over the safety and vulnerability of reinforced concrete moment resisting frame ＂RC-MRF＂ buildings. The seismic response of such buildings is greatly dependent on the computational tools used and the inherent assumptions in the modelling process. Thus, it is essential to investigate the sensitivity of the response demands to the corresponding modelling assumption. Many parameters and assumptions are justified to generate effective structural finite element（FE） models of buildings to simulate lateral behaviour and evaluate seismic design demands. As such, the present study focuses on the development of reliable FE models with various levels of refinement. The effects of the FE modelling assumptions on the seismic response demands on the design of buildings are investigated. the predictive ability of a FE model is tied to the accuracy of numerical analysis; a numerical analysis is performed for a series of symmetric buildings in active seismic zones. The results of the seismic response demands are presented in a comparative format to confirm drift and strength limits requirements. A proposed model is formulated based on a simplified modeling approach, where the most refined model is used to calibrate the simplified model.

关键词： RC-MRF buildings design codes provisions seismic design finite element modeling modeling assumptions response demands