检索结果-内蒙古大学图书馆

Synergizing vision transformer with ensemble of deep learning model for accurate kidney stone detection using CT imaging

引用

Alexandria engineering Journal 2025年 127卷 357-373页

作者： Alzughaibi, Arwa Alanazi, Adwan A. Alshahrani, Mohammed Hilali Jaghdam, Ines Hassaballa, Abaker A. Applied college Taibah University Madinah Saudi Arabia Department of Computer Science and Information College of Computer Science and Engineering University of Hail Hail Saudi Arabia Department of Computer Sciences Applied College Najran University Najran66462 Saudi Arabia Department of Computer Science and Information Technology Applied College Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Mathematics Faculty of Science Northern Border University Arar73213 Saudi Arabia

The disease of Kidney stones is a risky disease for individuals all over the world. Many people with kidney stones in the early phase do not detect it as an illness, and it harms the organ gradually. Precise analysis of kidney illness is vital, as it is a major health concern that needs accurate detection for appropriate and effective treatment. CT scans are one of the most extensively accessible imaging models, and they are employed for effective diagnosis. Deep learning (DL) techniques are gradually identified as beneficial tools for analyzing illness in the medical field. However, present techniques employing deep networks often meet low accuracy and overfitting challenges, demanding further alteration for optimum performance. This study presents a Leveraging Flying Foxes Optimization with an Ensemble of Deep Learning for Accurate Kidney Stone Detection (LFFOEDL-AKSD) technique in CT scans. The presented LFFOEDL-AKSD technique mainly focuses on detecting kidney stones using CI imaging. At first, the presented LFFOEDL-AKSD technique applies the pre-processing phase, which involves image resizing for uniform CT scan dimensions and data augmentation through transformations like rotation and flipping to reduce overfitting, sobel filtering (SF) sharpens edges, and the data is separated into training, validation, and testing sets for model development. The presented LFFOEDL-AKSD technique employs the swin transformer (ST) model for the feature extraction method. Furthermore, the majority voting ensemble of three DL approaches, such as the graph convolutional network (GCN), temporal convolutional network (TCN), and three-dimensional convolutional autoencoder (3D-CAE) approaches, are employed to increase the precision and reliability of the kidney stone recognition. Finally, the presented LFFOEDL-AKSD technique implements the flying foxes optimization (FFO) approach for the hyperparameter tuning involved in the ensemble learning models. An extensive experiment is conduct

关键词： Flying foxes optimization Ensemble deep learning Kidney stone detection CI imaging Swin transformer

来源：评论

学校读者我要写书评

暂无评论

Mamba Meets Financial Markets: A Graph-Mamba Approach for Stock Price Prediction

Mamba Meets Financial Markets: A Graph-Mamba Approach for St...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Mehrabian, Ali Hoseinzade, Ehsan Mazloum, Mahdi Chen, Xiaohong Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada Department of Computer Science Simon Fraser University Burnaby Canada Department of Mathematics University of Pittsburgh Pittsburgh United States Department of Economics Yale University New Haven United States

ISBN: (纸本)9798350368741

Stock markets play an important role in the global economy, where accurate stock price predictions can lead to significant financial returns. While existing transformer-based models have outperformed long short-term memory (LSTM) networks and convolutional neural networks (CNNs) in financial time series prediction, their high computational complexity and memory requirements limit their practicality for real-time trading and long-sequence data processing. To address these challenges, in this paper, we propose SAMBA, an innovative framework for stock return prediction that builds on the Mamba architecture and integrates graph neural networks (GNNs). SAMBA achieves near-linear computational complexity by utilizing a bidirectional Mamba block to capture long-term dependencies in historical price data and employing adaptive graph convolution to model dependencies between daily stock features. Our experimental results demonstrate that SAMBA significantly outperforms state-of-the-art baseline models in prediction performance, maintaining low computational complexity. The code and datasets are available at ***/Ali-Meh619/SAMBA. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Topology Synthesis of Analog Integrated Circuits With Frequency Compensation

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 832-844页

作者： Zhao, Zhenxin Liu, Jun Zhao, Wen-Sheng Zhang, Lihong Hangzhou Dianzi University Innovation Center for Electronic Design Automation Technology Zhejiang Hangzhou310018 China Memorial University of Newfoundland Faculty of Engineering and Applied Science Department of Electrical and Computer Engineering St. John'sNLA1C 5S7 Canada

Analog circuit topology synthesis suffers from weak synthesis capability and low-synthesis efficiency, which result in a bottleneck toward its practical industrial applications. This article presents a proximal-policy-optimization-based circuit topology synthesis framework, which features a superior convergence rate. To further promote its synthesis efficiency, we have improved a deterministic optimization method by incorporating a bias-aware scheme and group concept, which is applied as a filter to eliminate the undesirable topologies in the early evaluation stage. Moreover, a graph-based refinement scheme is proposed to perform deterministically on the generated circuit topologies, which can efficiently add frequency compensation circuits. Compared with the state-of-the-art approaches, our proposed method not only boosts the synthesis efficiency by at least 3 times but also enhances the synthesis capability with a deterministic compensation scheme, showcasing significant advancement of performance efficacy. © 2024 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Provable algorithms for multi-reference alignment over SO(2)

arXiv

引用

arXiv 2025年

作者： Drozatz, Gil Bendory, Tamir Sharon, Nir School of Electrical and Computer Engineering Tel Aviv University Israel Department of Applied Mathematics Tel Aviv University Israel

The multi-reference alignment (MRA) problem involves reconstructing a signal from multiple noisy observations, each transformed by a random group element. In this paper, we focus on the group SO(2) of in-plane rotations and propose two computationally efficient algorithms with theoretical guarantees for accurate signal recovery under a non-uniform distribution over the group. The first algorithm exploits the spectral properties of the second moment of the data, while the second utilizes the frequency matching principle. Both algorithms achieve the optimal estimation rate in high-noise regimes, marking a significant advancement in the development of computationally efficient and statistically optimal methods for estimation problems over groups. © 2025, CC BY-NC-ND.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Large Language Models for OCR Post-Processing in Persian: From ParsBERT to GPT 29

Comparative Analysis of Large Language Models for OCR Post-P...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Valizadeh, Fatemeh Ghasemian, Fahimeh Shabaninia, Elham Department of Computer Engineering Shahid Bahonar University of Kerman Kerman Iran Department of Applied Mathematics Graduate University of Advanced Technology Kerman Iran

ISBN: (纸本)9798331523114

Optical Character Recognition (OCR) refers to the automatic identification of text in images and its conversion into searchable and editable formats. Due to its extensive applications, OCR is considered a crucial and challenging topic in the field of computer vision. In Persian, the unique characteristics of the script often result in OCR outputs with significant errors, which can compromise readability and comprehension of the content, emphasizing the need for error correction, particularly in terms of spelling. This study investigates the performance of four large language models-ParsBERT, LLaMA, Mistral, and GPT-for enhancing OCR outputs. Additionally, an innovative approach that integrates ParsBERT with other models is introduced. These models were evaluated on three corpora of varying sizes and complexities using diverse evaluation metrics, including precision, accuracy, recall, and others. Our comparative analysis highlights the strengths and weaknesses of each model across different scenarios, providing deeper insights into their performance. Furthermore, the results demonstrate that the proposed hybrid approaches outperform standalone models across all corpora, significantly reducing error rates and improving key metrics such as precision, accuracy, and recall. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Contact-Rich Task Learning on an Articulated Soft Robot Arm Through Simulation 25th

Contact-Rich Task Learning on an Articulated Soft Robot Ar...

引用

25th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2024

作者： Elstner, Laurenz Kyrkjebø, Erik Stoelen, Martin F. Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Førde Norway Fieldwork Robotics Ltd. Cambridge United Kingdom

ISBN: (纸本)9783031720611

Traditional rigid robots face limitations in exploration during learning processes in dynamic and unknown environments where contact and impacts are common. Soft robots that leverage compliant materials, for example as part of variable stiffness actuators (VSAs), offer promising avenues for enhanced adaptability and safety. Deep Reinforcement Learning (RL), while proven to be a powerful tool, requires a lot of training data that is time-consuming to gather. This paper introduces a novel approach to simulating robots driven by antagonistic VSAs, as well as full-task learning with a soft robot arm in three environments with different contact types: path following (no contact), door opening (kinematic constraint), and surface wiping (continuous contact). We show that the tendon-driven robot can learn all three tasks, even if learning in a very low-level actuation space. The stretchable tendons enables it to perform relatively well on the contact-rich tasks. Further, using the proposed variable stiffness controller the robot is able to develop a stable behaviour in terms of forces applied to the environment. The results are promising for extending the approach to the physical robot. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Tendons

来源：评论

学校读者我要写书评

暂无评论

Modeling of III-N heterostructures for GaN light-emitting diodes based on effective bond-orbital model 29

Modeling of III-N heterostructures for GaN light-emitting di...

引用

Light-Emitting Devices, Materials, and Applications XXIX 2025

作者： Hsiao, Fu-Chen Chang, Yia-Chung Wierer, Jonathan Kish, Fred Department of Electrical and Computer Engineering North Carolina State University RaleighNC27606 United States Research Center for Applied Sciences Academia Sinica Taipei11529 Taiwan

ISBN: (纸本)9781510685208

Spontaneous emission and Auger non-radiative recombination rates are critical factors influencing the performance of light-emitting diodes (LEDs). This study introduces a computational framework for evaluating both direct and phonon-assisted Auger recombination in III-Nitride (III-N) bulk materials and single quantum well (QW), leveraging the effective-bond orbital model (EBOM). The EBOM-derived band structure for Wurtzite III-N demonstrates excellent agreement with density functional theory calculations using the meta-generalized gradient approximation, affirming its efficiency and suitability for heterostructure systems due to its tight-binding-like orbital basis. Simulations reveal that the zone-center approximation for initial states is inadequate for accurate Brillouin zone integration in phonon-assisted Auger recombination calculations. The computational approach presented here can be generalized to study various indirect Auger recombination processes in heterostructures, including quantum wires and quantum dots. Incorporating refined electron-phonon matrix elements from advanced first-principles methods could further enhance result accuracy. Additionally, the calculated spontaneous emission rate in single InGaN/GaN QW is presented to provide a comprehensive perspective on GaN-based LEDs. The exciton states and corresponding enhancement factors are integrated into the spontaneous emission spectra, enabling accurate characterization of the dependence of LED spontaneous emission coefficients on carrier injection density. While this study focuses on calculating the Auger recombination rate, a comprehensive LED model based on EBOM, incorporating the present computational scheme, will be detailed in a forthcoming publication. © 2025 SPIE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

A Shallow Water Model: Analytical and Numerical Study for Simulating the Coastline Evolution 4th

A Shallow Water Model: Analytical and Numerical Study for ...

引用

4th International Conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

作者： Scarcella, Maria Antonietta Carini, Manuela Zampoli, Vittorio Department of Environmental Engineering DIAm University of Calabria via Pietro Bucci CS Rende87036 Italy Department of Information and Electrical Engineering and Applied Mathematics DIEM University of Salerno via Giovanni Paolo II SA Fisciano84084 Italy

ISBN: (纸本)9783031812439

In a broader research context, we aim to explore and improve existing mathematical models able to predict and simulate the evolution of the coastline in time, taking into account the variation of seabed topography and morphology, as well as resistance conditions, time intervals between storm surges, seasonal variations and viscosity, all factors that greatly influence coastal dynamics. With this target, relying on a numerical approach, in the present contribution we implement our investigation considering waves analytically modeled through the Saint Venant’s equations. We exploit the COMSOL Multiphysics simulation platform, which allows to handle engineering problems governed by PDEs, highlighting if and how seabed topography, friction term and dispersion coefficient influence the elevation of the water column in space and time which, in turn, has an impact on the coastal erosion. Two particular topographies are taken into account, designed to simulate seabeds with common features actually existing. A number of graphical results are provided and commented, accompanying the conclusions with a brief note on potential future advancements and applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Coastal engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing energy management and power quality in grid-connected photovoltaic systems through ESS and STATCOM integration

引用

International Journal of Advanced Manufacturing Technology 2025年 1-16页

作者： Velukutty, Kannan Nithin Kariyankattil Sundararajan, Deepa Krishnappa, Muthuraman Ramaiah Angappan, Senthil Kumar Premalatha, Munuswamy Sivaraju, Selligoundanur Subramaniyam Usha, Subramaniam SCMS School of Engineering and Technology Kerala Karukutty India Department of Physics Government College of Engineering Tamilnadu Salem India Sri Ramakrishna Engineering College Tamil Nadu Vattamalaipalayam N.G.G.O Colony Post Coimbatore641 022 India Computer Science and Engineering School of Engineering Dayananda Sagar University Bangalore India Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Tamil Nadu Chennai India Department of Electrical and Electronics Engineering RVS College of Engineering and Technology Kannampalayam Tamil Nadu Coimbatore India Department of Electrical and Electronics Engineering Kongu Engineering College Tamilnadu Perundurai India

This paper presents a hybrid system that integrates a photovoltaic (PV) array, an energy storage system (ESS), and a Static Synchronous Compensator (STATCOM), utilizing a Quasi-Z Source Inverter (qZSI) to improve the efficiency of grid-connected power systems. The qZSI facilitates both voltage boosting and inversion in a single stage, enabling efficient power conversion from the PV array and ESS while minimizing component count. The STATCOM plays a crucial role in dynamic reactive power control and voltage regulation, while the ESS provides rapid charge and discharge capabilities, ensuring grid stability during voltage fluctuations and varying load demands. To enhance ESS battery safety, an energy management strategy is proposed, which regulates power flow to prevent overcharging and over-discharging, thereby extending its life and optimizing performance. The system operates in three distinct modes: PV mode for real power generation, PV-STATCOM mode for reactive power control and power factor correction, and ESS-STATCOM mode for emergency grid support. This integrated approach enhances power quality, improves grid flexibility, and supports the sustainable integration of renewable energy. MATLAB simulations confirm the system’s capability to maintain power quality and stabilize the grid across various operational scenarios, highlighting its efficiency and cost-effectiveness for modern power grids. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Degradation of Organic LEDs Characterized with Algebraic Decay Relaxation Function 15

Degradation of Organic LEDs Characterized with Algebraic Dec...

引用

Advances in Display Technologies XV 2025

作者： Aygen, Can Richards, Michael Yazdaanpanah, Ramin Kulkarni, Sachin Tanriover, Ibrahim Onsager, Claire Lin, BoYen Lee, Jiun-Haw Aydin, Koray Grayson, Matthew A. Department of Electrical & Computer Engineering Northwestern University EvanstonIL United States Department of Opto-Electronic Engineering National Dong Hwa University Hualien Taiwan Graduate Institute of Photonics and Optoelectronics Department of Electrical Engineering National Taiwan University Taipei Taiwan Program in Applied Physics Northwestern University EvanstonIL United States

ISBN: (纸本)9781510685246

Lifetime studies of organic light emitting diodes are necessary to both understand and mitigate causes of degradation. Here, electroluminescence (EL) studies of green organic light-emitting diode (OLED) pixels are measured continuously using three different dc currents over a period of one week, and their slow EL degradation is accurately fit to an analytical expression with only two fit parameters. The slower-than-exponential EL decay is fit to an empirical unified heavy-tail function that can interpolate between power-law algebraic decays (AD) and stretched-exponential decays (SE). Whereas SE and AD are largely indistinguishable down to 50% of the initial luminance, here we report degradation down to 10% of the initial luminance which most closely fits an AD function with remarkable precision over the entire duration of the experiment. All relaxations share the same characteristic exponent β = 0.53 in the power law decay, whereas the characteristic time-scale τ for degradation decreases with a power-law exponent B = 1.9 as the current increases. The high degree of accuracy in the fit allows asymptotic predictions at time scales that are orders of magnitude longer than the duration of the data collection. The voltage across the OLED is simultaneously monitored under constant-current degradation and reveals an early-onset time scale where the voltage reaches a minimum before degradation runoff. © 2025 SPIE.

关键词： Organic light emitting diodes (OLED)

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：