检索结果-内蒙古大学图书馆

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Text Augmentation-Based Model for Emotion Recognition Using Transformers

引用

Computers, Materials & Continua 2023年第9期76卷 3523-3547页

作者： Fida Mohammad Mukhtaj Khan Safdar Nawaz Khan Marwat Naveed Jan Neelam Gohar Muhammad Bilal Amal Al-Rasheed Department of Computer Science The University of HaripurHaripur22620Pakistan Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and Technology PeshawarPeshawar25120Pakistan Department of Electronics Engineering Technology University of TechnologyNowshera24100Pakistan Department of Computer Science Shaheed Benazir BhuttoWomen UniversityPeshawar25000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally ***-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC ***,their limited ability to collect and acquire contextual information hinders their *** propose a Text Augmentation-based computational model for recognizing emotions using transformers(TA-MERT)to address *** proposed model uses the Multimodal Emotion Lines Dataset(MELD),which ensures a balanced representation for recognizing human *** used text augmentation techniques to producemore training data,improving the proposed model’s *** encoders train the deep neural network(DNN)model,especially Bidirectional Encoder(BE)representations that capture both forward and backward contextual *** integration improves the accuracy and robustness of the proposed ***,we present a method for balancing the training dataset by creating enhanced samples from the original *** balancing the dataset across all emotion categories,we can lessen the adverse effects of data imbalance on the accuracy of the proposed *** results on the MELD dataset show that TA-MERT outperforms earlier methods,achieving a weighted F1 score of 62.60%and an accuracy of 64.36%.Overall,the proposed TA-MERT model solves the GBN models’weaknesses in obtaining contextual data for ***-MERT model recognizes human emotions more accurately by employing text augmentation and transformer-based *** balanced dataset and the additional training samples also enhance its *** findings highlight the significance of transformer-based approaches for special emotion recognition in conversations.

关键词： Emotion recognition in conversation graph-based network text augmentation-basedmodel multimodal emotion lines dataset bidirectional encoder representation for transformer

来源：评论

学校读者我要写书评

暂无评论

Outage Analysis of Optimal UAV Cooperation with IRS via Energy Harvesting Enhancement Assisted Computational Offloading

引用

Computer Modeling in engineering & sciences 2024年第2期138卷 1885-1905页

作者： Baofeng Ji Ying Wang Weixing Wang Shahid Mumtaz Charalampos Tsimenidis School of Information Engineering Henan University of Science and TechnologyLuoyang471000China Research and Innovation Center of Intelligent System Longmen LaboratoryLuoyang471000China State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System(CEMEE) Luoyang471000China Sustainable Digital Communications and Energy Systems(DIGCOM)Group Nottingham Trent UniversityNottinghamUK

The utilization of mobile edge computing(MEC)for unmanned aerial vehicle(UAV)communication presents a viable solution for achieving high reliability and low latency *** study explores the potential of employing intelligent reflective surfaces(IRS)andUAVs as relay nodes to efficiently offload user computing tasks to theMEC server system ***,the user node accesses the primary user spectrum,while adhering to the constraint of satisfying the primary user peak interference ***,the UAV acquires energy without interrupting the primary user’s regular communication by employing two energy harvesting schemes,namely time switching(TS)and power splitting(PS).The selection of the optimal UAV is based on the maximization of the instantaneous signal-to-noise ***,the analytical expression for the outage probability of the system in Rayleigh channels is derived and *** study investigates the impact of various system parameters,including the number of UAVs,peak interference power,TS,and PS factors,on the system’s outage performance through *** proposed system is also compared to two conventional benchmark schemes:the optimal UAV link transmission and the IRS link *** simulation results validate the theoretical derivation and demonstrate the superiority of the proposed scheme over the benchmark schemes.

关键词： Unmanned aerial vehicle(UAV) intelligent reflective surface(IRS) energy harvesting computational offloading outage probability

来源：评论

学校读者我要写书评

暂无评论

Chemical bond and dielectric response of Yb_(2)Si_(2)O_(7)ceramic with low dielectric constant at GHz and THz

引用

Journal of Advanced Ceramics 2025年第2期14卷 119-129页

作者： Yingxiang Li Zegui Hou Zixuan Fang Fei Wang Deyin Liang Zitao Shi Wei Liu Chuansheng He Bin Tang College of Information Engineering Shaoyang UniversityShaoyang 422000China School of Materials and Energy University of Electronic Science and Technology of ChinaChengdu 611731China School of Civil Engineering and Geomatics Southwest Petroleum UniversityChengdu 610500China State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of ChinaChengdu 611731China

The exploration of high-performance dielectric ceramics with dielectric constants lower than 10 is of great significance for the next generation of wireless *** this study,we reported the Yb_(2)Si_(2)O_(7)(YSO)dielectric ceramics synthesized using a facile solid-state reaction technique.X-ray diffraction(XRD)and transmission electron microscopy(TEM)characterization confirmed that YSO ceramics had a monoclinic *** a sintering temperature of 1500℃,the sintered sample reached a maximum relative density of 96%and demonstrated the best dielectric properties:dielectric constant(ε_(r))=7.57,Q×f=78,645 GHz(Q is quality factor,and f is the resonant frequency of 13.5 GHz),andtemperature coefficient of the resonant frequency(τ_(f))=−13.5 ppm/℃.Moreover,Raman analysis revealed that the Si–O bond dominated the lattice vibration,and the full width at half maximum(FWHM)of the strong peak at 922 cm^(−1)was inversely proportional to the Q×f *** to the Phillips–van Vechten–Levine(P–V–L)theory,the values of Q×f andτ_(f)are affected primarily by the Si–O bond,whileε_(r)is influenced mainly by the Yb–O *** ceramics demonstrated excellent dielectric properties in the terahertz band(ε_(r)=8.13,Q×f=112,758 GHz),making them promising candidates for future applications in the terahertz band.

关键词： Yb_(2)Si_(2)O_(7)(YSO) dielectric properties Phillips-van Vechten-Levine(P-V-L) terahertz

来源：评论

学校读者我要写书评

暂无评论

Buried interface bridging for inverted cesium-formamidinium triiodide perovskite solar cells with long operational stability

引用

science China Chemistry 2025年第1期68卷 163-173页

作者： Chenhui Zhang Chunjun Liang Fulin Sun Ting Zhu Xinghai Huang Yuzhu Guo Xinyu Guo Kunyang Ge Dan Li Fangtian You Zhiqun He Key Laboratory of Luminescence and Optical Information Ministry of EducationInstitute of Optoelectronic TechnologyBeijing Jiaotong UniversityBeijing 100044China Department of Physics School of Physical Science and EngineeringBeijing Jiaotong UniversityBeijing 100044China

In the field of perovskite solar cells(PSCs),the research on defects in the buried interface has been relatively limited due to its non-exposure;however,this interface significantly impacts the performance enhancement of inverted *** study employs phenylethylammonium chloride(PEACl)molecules as a buffer layer to modify the buried interface of p-i-n structured PSCs,aiming to enhance the uniformity of self-assembled monolayers(SAMs)and facilitate the uniform nucleation and growth of perovskite films on the ***,the introduction of the PEACl buffer layer effectively passivates defects at the bottom of the perovskite layer and notably enhances the crystal quality of the perovskite film by mitigating residual stress,thereby reducing nonradiative recombination *** these optimizations,the MA-free PSCs treated with PEACl achieve a power conversion efficiency(PCE)of 24.11%,with significant improvements in storage,thermal stability,and operational *** noteworthy is the device's performance in an unencapsulated state,whereas after 1,500 hours of continuous light operation stability testing,it retains 97%of its original *** study not only enriches the systematic understanding of the characteristics of the buried interface in PSCs but also contributes significantly to advancing the commercial production of perovskite photovoltaic technology.

关键词： defect-induced recombination buried interfaces inverted perovskite solar cells crystallization lattice mismatch

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of UAV-based mixed underwater PLC-RF systems

引用

Digital Communications and Networks 2024年第5期10卷 1332-1340页

作者： Shenghai Chen Liang Yang Xianfu Lei College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua UniversityHuaihua418000China School of Information Science and Technology Southwest Jiaotong UniversityChengdu610031China

In this study,we analyzed the performance of an Unmanned Aerial Vehicle(UAV)-based mixed Underwater Power Line Communication-Radio Frequency(UPLC-RF)*** this network,a buoy located at the sea is used as a relay to transmit signals from the underwater signal source to the UAV through the PLC *** assume that the UPLC channel obeys a log-normal distribution and that the RF link follows the Rician *** this model,we obtained the closed-form expressions for the Outage Probability(OP),Average Bit-error-rate(ABER),and Average Channel Capacity(ACC).In addition,the asymptotic analysis of the OP and ABER was performed,and an upper bound for the average capacity was ***,the analytical results were verified by Monte Carlo simulation thereby demonstrating the effect of impulse noise and the altitude of the UAV on network performance.

关键词： ABER Average bit-error-rate ACC Average channel capacity OP Outage probability UAV Unmanned aerial vehicle UPLC Underwater power line communication

来源：评论

学校读者我要写书评

暂无评论

Unintentional emissions of polychlorinated naphthalenes in China:Sources,composition,and historical trends

引用

Journal of Environmental sciences 2025年第2期148卷 221-229页

作者： Ye Huang Lin Huang Ying Li Nazupar Sidikjan Yunshan Zhang Yan Chen Yangmin Chen Ye Li Wei Du Long Chen YanWu Shanshan Zhang Jing Yang Wenjun Meng Guofeng Shen Min Liu Shu Tao Key Laboratory of Geographic Information Science of the Ministry of Education School of Geographic SciencesEast China Normal UniversityShanghai 200241China Yunnan Provincial Key Laboratory of Soil Carbon Sequestration and Pollution Control Faculty of Environmental Science&EngineeringKunming University of Science&TechnologyKunming 650500China Laboratory of Earth Surface Processes College of Urban and Environmental SciencePeking UniversityBeijing 100871China

Polychlorinated naphthalenes(PCNs)are detrimental to human health and the *** the commercial production of PCNs banned,unintentional releases have emerged as a significant environmental ***,relevant information is still *** this study,provincial emissions for eight PCNs homologues from 37 sources in the Chinese mainland during the period of 1960-2019 were estimated based on a source-specific and time-varying emission factor *** results showed that the total PCNs emissions in 2019 reached 757.0 kg with Hebei ranked at the top among all the provinces and iron&steel industry as the biggest ***-chlorinated PCNs comprised 90%of emissions by mass,while highly chlorinated PCNs dominated in terms of toxicity,highlighting divergent priorities for mitigating emissions and safeguarding human *** emissions showed an overall upward trend from 1960 to 2019 driven by emission increase from iron&steel industry in terms of source,and from North China and East China in terms of geographic ***-capita emissions followed an inverted U-shaped environmental Kuznets curvewhile emission intensities decreased with increasing per-capita Gross Domestic Product(GDP)following a nearly linear pattern when log-transformed.

关键词： PCNs Emission inventory Emission factor Composition profile Emission intensity Chinese mainland

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness in Multi-Agent Actor-Critic with Double Actors 38

Enhancing Robustness in Multi-Agent Actor-Critic with Double...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Han, Xue Cui, Peng Zhang, Ya Southeast University School of Automation Nanjing210096 China Science and Technology on Information Systems Engineering Laboratory Nanjing210007 China

ISBN: (纸本)9798350303636

In recent years, multi-agent reinforcement learning (MARL) has shown a strong ability to solve complex system tasks. How to solve the overfitting problem of MARL algorithm and how to improve the robustness of MARL algorithm are important issues that need to be considered when the algorithm is turned to practical application. In this paper, we discuss the application potential of two-actor networks in MARL algorithms. First, we design double actors based on MADDPG algorithm, to improve the robustness of learning strategies, which is called DA-MADDPG algorithm. In the DA-MADDPG, the central-decentralized mismatch caused by two actor networks updating with the same Q value is further discussed. A gradient updating optimization method for DA-MADDPG by KL divergence and clipped function is proposed respectively. Experimental results in MPE environment show that DA-MADDPG and DA-MADDPG bycclipped function can achieve better results than MADDPG algorithm. © 2023 IEEE.

关键词： clipped function double actors KL divergence Multi-Agent Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Single-atom Ni-N_(4) for enhanced electrochemical sensing

引用

Nano Research 2024年第8期17卷 7658-7664页

作者： Zhuhui Qin Bo Tang Guiru Zhang Chongqing Zhu Kun Jiang Bowei Zhang Fu-Zhen Xuan Shanghai Key Laboratory of Intelligent Sensing and Detection Technology East China University of Science and TechnologyShanghai 200237China Key Laboratory of Pressure Systems and Safety of Ministry of Education East China University of Science and TechnologyShanghai 200237China School of Mechanical and Power Engineering East China University of Science and TechnologyShanghai 200237China Key Laboratory of Theoretical and Computational Photochemistry Ministry of EducationCollege of ChemistryBeijing Normal UniversityBeijing 100875China Interdisciplinary Research Center School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China

Single-atom catalysts(SACs)attract widespread attention in heterogeneous catalysis due to their maximum atomic utilization efficiency and unique physical and chemical ***,their applications in chemical sensing keep huge potential but remain ***,a Ni-N_(4)-C SAC was synthesized for the trace detection of dopamine(DA)and uric acid(UA).The Ni-N_(4)-C SAC exhibited superior sensing performance compared to the Ni *** detection range for DA and UA were 0.05–75μM and 5–90μM with detection limits of 0.027 and 0.82μM,*** functional theory(DFT)computations indicate that Ni-N_(4)-C has a lower reaction barrier during electrochemical process,indicating that the atomic Ni sites possess higher intrinsic activity than Ni ***,DA and UA show strong potential dependency on the Ni-N_(4)-C catalyst,indicating its applicability for their concurrent *** work extends the application of SACs in chemical sensing.

关键词： single-atom catalysts chemical sensing dopamine uric acid

来源：评论

学校读者我要写书评

暂无评论

Path Inference Based on Voronoi Graph 1

引用

36th International Conference on Industrial, engineering and Other Applications of Applied Intelligent systems, IEA/AIE 2023

作者： Xu, Xin Science and Technology on Information System Engineering Laboratory Nanjing210023 China

ISBN: (数字)9783031368226

ISBN: (纸本)9783031368219

Traditional path planning approach is generally focused on finding a single one shortest path given the temporal or spatial constraints. However, the strategy of single-one optimal path is unable to adapt to various situations in real applications. For example, in the scenarios of vehicle patrolling and search &rescue, the comprehensiveness of coverage is much more important. Rather than finding a single one optimal shortest path as the traditional path planning does, our path inference approach aims at inferring all the possible paths which satisfy the specified temporal and spatial constraints. Path inference is able to provide more valuable insights for internet routing, migration pattern study, urban construction and adversary profiling. In this work, we propose a novel path inference algorithm based on Voronoi graph. We model the 2D geospatial topology with Voronoi cells according to the spatial constraint, represent the adjacency relationships of Voronoi cells with an adjacency matrix and infer all the possible paths in the derived Voronoi graph satisfying the user-specified temporal and spatial constraints. Experimental results indicate that our path inference algorithm based on Voronoi graph is able to perform more delicately and efficiently than the traditional path planning approach in term of both space partition and path inference. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：