检索结果-南通市图书馆

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

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 Modeling in engineering & Sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho school of Computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and Software engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the school of Biomedical engineering of Southern Medical University(SMU-dataset),and The National Institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

A mechanical reinforced and antifreezing polyacrylate hydrogel electrolyte for high-performance zinc-ion batteries

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 341-350页

作者： Zili Zhang Ruolin Wang Hongfei Lu Di Zhang Yu Zhao Jing Xu Bin Sun Zhi-Min Dang Yang Jin school of Electrical and information engineering Zheng Zhou UniversityZhengzhou 450001China State Key Lab of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China

The operation of aqueous zinc-ion batteries in flexible energy storage field is plagued by the uncontrollable growth of Zn-dendrite and inevitable freeze of water below 0 ℃.Therefore,it is necessary to design a hydrogel electrolyte with good mechanical property and freezing resistance to uniform the Zn-deposition and resist flexibility loss at low *** find that the mechanical property(strength and toughness)of hydrogel electrolyte has a significant impact on the suppression of dendrite growth and the uniform deposition of zinc ***,a polyacrylate hydrogel is prepared in one step by ultraviolet(UV)curing method with Zn(CF_(3)SO_(3))_(2)salt and polyvinyl alcohol(PVA)addition to increase the antifreezing ability and mechanical *** adsorption of water molecules by 2-hydroxyethyl acrylate(HEA)and PVA reduces the freezing point of the hydrogel,which is beneficial for enhancing the electrochemical stability at low *** this basis,the Zn-symmetrical battery with hydrogel electrolyte has a long lifespan of 4710 h at 0.5 mA·cm^(-2)and 0.5 mAh·cm^(-2)at room ***,the hydrogel electrolyte exhibits an outstanding stability at low temperature of^(-2)0 ℃,the lifespan of symmetrical battery reaches to 4000 h at 0.5 mA·cm^(-2)and 0.5 mAh·cm^(-2).The assembled full cell with NaV3O8·1.5H_(2)O(NVO)cathode and hydrogel electrolyte possesses a high capacity retention ratio of 77%after 10,000 cycles at^(-2)0 ℃.The flexible cell can power light-emitting diode(LED)lamp under bending,warping and cutting without liquid leakage and an electronic watch at the operating temperature of^(-2)0 ℃.

关键词： zinc ion battery hydrogel electrolyte mechanical enhancement freezing resistance

Morphology engineering of ZnO micro/nanostructures under mild conditions for optoelectronic application

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 Minerals,Metallurgy and Materials 2025年第2期32卷 498-503页

作者： Liang Chu Haoyu Shen Hudie Wei Hongyu Chen Guoqiang Ma Wensheng Yan Institute of Carbon Neutrality and New Energy&school of Electronics and information Hangzhou Dianzi UniversityHangzhou 310018China school of Applied Physics and Materials Wuyi UniversityJiangmen 529020China

Zinc oxide(ZnO)serves as a crucial functional semiconductor with a wide direct bandgap of approximately 3.37 *** reaction is commonly used in the synthesis of ZnO micro/nanostructures,given its low cost,simplicity,and easy ***,ZnO morphology engineering has become desirable through the alteration of minor conditions in the reaction process,particularly at room *** this work,ZnO micro/nanostructures were synthesized in a solution by varying the amounts of the ammonia added at low temperatures(including room temperature).The formation of Zn^(2+)complexes by ammonia in the precursor regulated the reaction rate of the morphology engineering of ZnO,which resulted in various structures,such as nanoparticles,nanosheets,microflowers,and single ***,the obtained ZnO was used in the optoelectronic application of ultraviolet detectors.

关键词： morphology engineering low temperature ZnO nanosheets microflowers ultraviolet detector

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in engineering & Sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer Science and engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea school of Electrical and Computer engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia school of Automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

Controllable synthesis of biomimetic wood stem nanoporous high entropy oxides catalysts for oxygen evolution reaction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 107-117页

作者： Wei Wang Weiqi Wang Huihui Wang Xing Lu Jinwen Zhang Yunzhuo Lu school of Materials Science and engineering Dalian Jiaotong UniversityDalian 116028China school of Intelligence and Electronic engineering Dalian Neusoft University of InformationDalian 116023China Guangdong Key Laboratory of Materials and Equipment in Harsh Marine Environment Guangzhou Maritime UniversityGuangzhou 510725China

Bubbles generated during the oxygen evolution reaction(OER)in water splitting readily adhere to the electrode surface,thereby impeding contact between the electrolyte and the active sites,thereby increasing the ***,it is imperative to elucidate the bubble release behavior and engineer electrodes that facilitate faster bubble *** this study,inspired by the wood stem of the Norway spruce,we synthesized a gradient nanoporous high-entropy oxide(GNP-HEO)electrode with a controllable pore *** GNP-HEO,featuring a well-controlled gradient in pore size,is achieved through a straightforward strategy combining selective laser melting with selective phase *** unique gradient nanoporous structure not only facilitates bubble release but also diminishes the bubble shielding effect in OER,thereby enhancing electrocatalytic *** affect interaction of Al,Co,Cr,Fe,and Ni,coupled with the gradient nanoporous structure,yields exceptional OER performance,evidenced by an overpotential of 250 mV at a current density of 50 mA/cm^(2) and a Tafel slope of 38.0 mV/dec in 1 M *** functional theory calculations confirm that the GNPHEO adheres to the adsorbate evolution mechanism reaction pathway and exhibits significant *** work highlights a promising approach for the design and synthesis of high-performance OER electrocatalysts.

关键词： oxygen evolution reaction high-entropy oxides selective phase dis-solution selective laser melting gradient nanoporous

Progress of crystalline carbon nitride in synthesis,atomic structure characterization and photocatalysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 455-476页

作者： Yueyang Tan Zhongyan Zhang Yayun Pu Zongzhao Sun Limin Huang school of Materials Science and engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemistry Southern University of Science and TechnologyShenzhen 518055China school of Traffic and Environment Shenzhen Institute of Information TechnologyShenzhen 518172China College of Chemistry and Chemical engineering Linyi UniversityLinyi 276000China school of Optoelectronic engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China

Crystalline carbon nitride(CCN)has emerged as a highly promising semiconductor photocatalyst with unique properties,such as enhanced charge migration rate,reduced carrier recombination probability,narrow band gap and improved light-harvesting efficiency,which are suitable for a wide range of applications in solar-to-chemical conversion,energy storage,therapeutic and environmental pollution *** the past few years,there has been an increasing number of reviews on CCN ***,most of these reviews mainly focus on synthesis methods,modification and applications,with less emphasis on the relationship between structures and properties,as well as on indepth exploration of the crystalline *** electronic instability of CCN presents challenges for conventional characterization techniques to directly and thoroughly investigate the relationship between its intrinsic atom structure and photocatalytic *** mini-review not only highlights the progress in CCN-based photocatalysts,with a focus on molten-salt synthesis(including solid-salt-induced crystallization),but also emphasizes the atomic structure characterization by specifically introducing the differential phase contrast(DPC)scanning transmission electron microscopy(STEM)technique,which is essential for enhancing our understanding of the crystal structure and photocatalytic mechanisms of ***,the review outlines the photocatalytic performance and puts forward potential challenges on CCN *** review will provide a clearer understanding of the relationship in developing precise customization strategies for CCN materials and ultimately explain the regularity and specificity of the enhanced performance in targeted photocatalytic systems.

关键词： crystalline carbon nitride synthesis characterization photocatalysis

LoRa Sense:Sensing and Optimization of LoRa Link Behavior Using Path-Loss Models in Open-Cast Mines

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 Modeling in engineering & Sciences 2025年第1期142卷 425-466页

作者： Bhanu Pratap Reddy Bhavanam Prashanth Ragam school of Computer Science and engineering VIT-AP UniversityAmaravati52237India

The Internet of Things(IoT)has orchestrated various domains in numerous applications,contributing significantly to the growth of the smart world,even in regions with low literacy rates,boosting socio-economic *** study provides valuable insights into optimizing wireless communication,paving the way for a more connected and productive future in the mining *** IoT revolution is advancing across industries,but harsh geometric environments,including open-pit mines,pose unique challenges for reliable *** advent of IoT in the mining industry has significantly improved communication for critical operations through the use of Radio Frequency(RF)protocols such as Bluetooth,Wi-Fi,GSM/GPRS,Narrow Band(NB)-IoT,SigFox,ZigBee,and Long Range Wireless Area Network(LoRaWAN).This study addresses the optimization of network implementations by comparing two leading free-spreading IoT-based RF protocols such as ZigBee and *** field tests are conducted in various opencast mines to investigate coverage potential and signal *** is tested in the Tadicherla open-cast coal mine in ***,LoRaWAN field tests are conducted at one of the associated cement companies(ACC)in the limestone mine in Bargarh,India,covering both Indoor-toOutdoor(I2O)and Outdoor-to-Outdoor(O2O)environments.A robust framework of path-loss models,referred to as Free space,Egli,Okumura-Hata,Cost231-Hata and Ericsson models,combined with key performance metrics,is employed to evaluate the patterns of signal *** field testing and careful data analysis revealed that the Egli model is the most consistent path-loss model for the ZigBee protocol in an I2O environment,with a coefficient of determination(R^(2))of 0.907,balanced error metrics such as Normalized Root Mean Square Error(NRMSE)of 0.030,Mean Square Error(MSE)of 4.950,Mean Absolute Percentage Error(MAPE)of 0.249 and Scatter Index(SI)of *** the O2O scenario,the Ericsson model

关键词： Internet of things long range wireless area network ZigBee mining environments path-loss models coefficient of determination mean square error

A New Online Dynamic Testing Method for Nonlinear Distortion of Broadcast Transmitter

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 Electronics 2020年第2期29卷 385-390页

作者： LI Shanshan ZHOU Jian WANG Xuan school of information and communication engineering Communication University of China

The traditional method for measuring the parameters of the transmitter is that the tester measures the parameters according to the test standard and records the test results manually in the case of non-work time. It has some shortcomings, such as low efficiency, inconvenient data storage and higher requirements for testers. In view of the shortcomings, an automatic online method of measuring harmonic distortion of transmitter is *** method calculates parameter values by collecting transmitter data in real time. It is based on the histogram algorithm. According to the cumulative distribution function, discrete distribution of transmitter input and output signal amplitude values are obtained, and then the least squares algorithm is applied to the nonlinear polynomial fitting of discrete values. The feasibility of the method is verified by experimental simulation, and the residual value and test accuracy of different test methods are given.

关键词： Histogram Least square Nonlinear fitting Gauss-Newton iteration Digital measurement

Zinc-based fiber-shaped rechargeable batteries:Insights into structures,electrodes,and electrolytes

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 278-293页

作者： Xuan Zhang Hongcheng Zhang Mengxiang Chen Jingqi Lu Evgeny Zhuravlev Jing Jiang Pin Liu Shengyang Dong Du Yuan Guoyin Zhu Lianbo Ma Yizhou Zhang Institute of Advanced Materials and Flexible Electronics(IAMFE) School of Chemistry and Materials ScienceNanjing University of Information Science and TechnologyNanjing 210044China school of Materials Science and engineering Anhui University of TechnologyMaanshan 243002China College of Materials Science and engineering Changsha University of Science and TechnologyChangsha 410004China

The rapid evolution of flexible wearable electronics has spurred a growing demand for energy storage devices,characterized by low-cost manufacturing processes,high safety standards,exceptional electrochemical performance and robust mechanical *** novel flexible devices,fiber-shaped batteries(FSBs)have emerged as prominent solutions exceptionally suited to future applications,owing to their unique one-dimensional(1D)architecture,remarkable flexibility,potential for miniaturization,adaptability to deformation and compatibility with the conventional textile *** the forefront research on fiber-shaped batteries,zincbased FSBs(ZFSBs)have garnered significant attentions,featured by the promising electrochemical properties of metallic *** enthusiasm is driven by the impressive capacity of Zn(820 mAh·g^(-1))and its low redox potential(Zn/Zn^(2+):-0.76 V *** hydrogen electrode).This review aims to consolidate recent achievements in the structural design,fabrication processes and electrode materials of flexible ***,we highlight three representative structural configurations:parallel type,twisted type and coaxial *** also place special emphasis on electrode modifications and electrolyte ***,we delve into the promising development opportunities and anticipate future challenges associated with ZFSBs,emphasizing their potential roles in powering the next generation of wearable electronics.

关键词： zinc-based batteries fiber-shape parallel type twisted type coaxial type