检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hasan, Md. Zahid Tamim, Abdullah Asadujjaman, D.M. Rahman, Md. Mahfujur Mollick, Md. Abu Ahnaf Dristi, Nosin Anjum Al-Noman, Abdullah Dept. of Computer Science & Engineering University of Rajshahi Bangladesh Dept. of Computer Science & Engineering Khulna University of Engineering & Technology Khulna Bangladesh Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Dept. of Computer Science & Engineering Varendra University Rajshahi Bangladesh

Brain tumors require an assessment to ensure timely diagnosis and effective patient treatment. Morphological factors such as size, location, texture, and variable appearance complicate tumor inspection. Medical imaging presents challenges, including noise and incomplete images. This research article presents a methodology for processing Magnetic Resonance Imaging (MRI) data, encompassing techniques for image classification and denoising. The effective use of MRI images allows medical professionals to detect brain disorders, including tumors. This research aims to categorize healthy brain tissue and brain tumors by analyzing the provided MRI data. Unlike alternative methods like Computed Tomography (CT), MRI technology offers a more detailed representation of internal anatomical components, making it a suitable option for studying data related to brain tumors. The MRI picture is first subjected to a denoising technique utilizing an Anisotropic diffusion filter. The dataset utilized for the model’s creation is a publicly accessible and validated Brain Tumour Classification (MRI) database, comprising 3,264 brain MRI scans. SMOTE was employed for data augmentation and dataset balancing. Convolutional Neural Networks(CNN) such as ResNet152V2, VGG, ViT, and EfficientNet were employed for the classification procedure. EfficientNet attained an accuracy of 98%, the highest *** Codes 68T07 © 2025, CC BY-NC-SA.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Diversity Seeking Techniques for Red-Teaming Large Language Models

Diversity Seeking Techniques for Red-Teaming Large Language ...

引用

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

作者： Lee, Seokhan Ku, Bonhwa Ko, Hanseok Dept. Computer Science and Engineering Korea University Seoul Korea Republic of Machine Learning Big Data Institute Korea University Seoul Korea Republic of Dept. Electrical and Computer Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798350368741

In this paper, we present new techniques for increasing the diversity of red-teaming prompts generated by automated machine learning-based methods, thereby enabling the discovery of more vulnerabilities in large language models. Using reinforcement learning to train models to output effective prompts for this task results in the models converging deterministically to a single output. Our first technique, which we term Defender, acts by blocking the reward signal for prompts that have already been discovered, thus making what was a stationary problem into a non-stationary problem that compels the reward maximizing algorithm to continually seek new prompts. Our second technique, Teamplay, trains two prompt generation models in tandem and adds the KL divergence between them to the reward in order to make them search in disparate regions of the space of prompts. Our techniques are shown experimentally to increase the effectiveness and diversity of prompts generated by existing reinforcement learning baselines. © 2025 IEEE.

关键词： AI safety large language models red-teaming reinforcement learning toxicity

来源：评论

学校读者我要写书评

暂无评论

High-Performance Image Restoration with SpectraNet: A Lightweight CNN Architecture

引用

Procedia computer science 2025年 258卷 2268-2277页

作者： Nitesh Patnaik Rishi Raj Piyush Kumar Singh Shreekara Mahapatra Debashis Pani Ravi Shankar Singh Dept. of Computer Science and Engineering Kalinga Institute Of Industrial Technology Bhubaneswar 751024 India Dept. of Computer Science Central University of South Bihar Bihar 824236 India Dept. of Computer Science and Engineering Indian Institute of Technology BHU Varanasi 221005 India

Deep learning-based image restoration faces significant challenges when deployed on resource-constrained platforms due to the computational demands and large number of parameters in existing models. The high computational load and extensive memory requirements make it difficult to implement these models on devices with limited processing power and storage capacity, such as mobile phones and embedded systems. Additionally, maintaining real-time performance while ensuring high-quality image restoration is a critical challenge, as traditional deep learning models often fail to meet the stringent latency and efficiency requirements of such platforms. This paper introduces a new, lightweight convolutional neural network (CNN) architecture tailored for efficient pixelation detection and restoration. Our approach combines a pre-trained MobileNetV2 with finetuning for pixelation detection, and SpectraNet, a architecture incorporating dept.-wise separable convolutions for image restoration. The proposed architecture was trained on the HQ-50k dataset, with 70% of the data used for training and 30% for testing. It achieved a Peak Signal-to-Noise Ratio (PSNR) of 17-23, outperforming 10 state-of-the-art architectures in both efficiency and image quality. This design addresses the dual problems of high computational load and extensive memory usage, prioritizing real-time performance and resource efficiency. The proposed architecture is ideal for deployment on mobile and embedded devices since it maintains high accuracy while significantly reducing the number of trainable parameters. Our findings advance the feasibility of deploying advanced image restoration techniques in real-world, resource-constrained environments.

关键词： dept.-wise Separable Convolutions Embedded Devices Image Restoration Lightweight Real-Time Performance Resource-Constrained Platforms Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Quantum Resistance Blockchain Algorithm using QHF and Novel Consensus Mechanism

Quantum Resistance Blockchain Algorithm using QHF and Novel ...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Paul, Soumyadip Mazumdar, Mausumi Maitra Chakraborty, Sarit Government College of Engineering & Ceramic Technology Dept. of Information Technology Kolkata700010 India Government College of Engineering and Leather Technology Department of Computer Science and Engineering Kolkata700106 India

ISBN: (纸本)9798331529833

The emergence of quantum computing poses a significant threat to the security of traditional blockchain systems, which rely heavily on classical cryptographic algorithms. To safeguard the integrity and reliability of blockchain technology in the upcoming era, this work proposes a novel quantum-resistant blockchain architecture. This approach integrates a robust consensus mechanism, with advanced quantum cryptographic primitives, including quantum digital signatures based on a Quantum Hash Function (QHF). Incorporating a quantum hash function enhances the blockchain resistance, providing an additional layer of security against quantum attacks. By combining these elements, our method creates a blockchain system fortified against the potential vulnerabilities introduced by quantum computers. The proposed solution leverages the power of QHFs to safeguard transaction integrity, while the consensus mechanism ensures the reliability and decentralization of the network. This paper also delves into the theoretical underpinnings of quantum blockchains, exploring their design, feasibility, and potential applications, emphasizing their promising future, particularly in areas such as decentralized identity authentication. Finally, it contributes to the development of a secure and resilient blockchain ecosystem capable of thriving in the coming era. © 2025 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Object Detection in Underwater Environments

Deep Learning Techniques for Object Detection in Underwater ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Praveen, R.V.S. Maindola, Meenakshi Anandhi, R.J. Thandra, Nagarjuna Bansal, Saloni Sharma, Vishal LTIMindtree Limited Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India New Horizon College of Engineering Department of Information Science Engineering Bangalore India MLR Institute of Technology Dept. Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India

ISBN: (纸本)9798331512965

The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. Applications like marine research, environmental monitoring, and autonomous underwater vehicles (AUVs) are restricted in their effectiveness by traditional image processing techniques, which often struggle with these complexities. Recent years have seen the rise of deep learning techniques as a potent weapon in the fight against these obstacles. In order to accurately detect objects underwater, this paper investigates the use of deep learning models, specifically convolutional neural networks (CNNs). We explore cutting-edge models and methods like attention mechanisms, transfer learning, and hybrid deep learning architectures to improve detection performance in challenging underwater environments. Furthermore, we utilize data augmentation techniques and synthetic dataset generation to tackle the critical issue of limited labeled underwater datasets. From a detection accuracy and robustness perspective, the experimental results show that our suggested deep learning method is light years ahead of the competition. Marine exploration, autonomous underwater vehicle navigation, and underwater surveillance systems can all benefit from this study's new insights into how to better detect objects in real time while submerged. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real Time Modeling and Control Algorithm of a Grid-Connected Battery Energy Storage System

Real Time Modeling and Control Algorithm of a Grid-Connected...

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Karimi, Sepehr Nazaralizadeh, Solmaz Srivastava, Anurag Salem, Aboubakr Famouri, Parviz West Virginia University Lane Department of Computer Science and Electrical Engineering Morgantown United States WVU-IT Electrical and Computer Engineering Dept. Beckley United States PCS Eaton PittsburghPA United States

ISBN: (纸本)9798331541125

This work develops real time model and associate control for a grid-tied battery energy storage system (BESS), based on the real industrial system specifications, 362kW/1499kWh lithium-ion BESS. An active and reactive power controller based on the dq reference frame is designed for the grid-tied inverter. To ensure system performance, an LCL filter with passive damping is also developed and analyzed. The system is tested using the Controller Hardware-in-the-Loop (CHIL) platform: Typhoon. The results demonstrate the controller's effective reference tracking across varying load conditions, with the filter design achieving a 3.3% output current THD, emphasizing the inverter's optimized performance. © 2025 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Predicting Glucose Levels via Disentangled Patterns with Triplet Network

Predicting Glucose Levels via Disentangled Patterns with Tri...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Lee, Janghee Jin, Heung-Yong Buu, Seok-Jun Seattle Pacific University Dept. of Biochemistry Seattle United States Jeonbuk National University Dept. of Endocrinology and metabolism Jeonju-si Korea Republic of Gyeongsang National University Dept. of Computer Science and Engineering Jinju-si Korea Republic of

ISBN: (纸本)9798331510756

Increasing prevalence of diabetes has driven adoption of wearable technologies for glucose management, with continuous glucose monitoring (CGM) being important for diabetes patients. However, extracting meaningful patterns from CGM data to enhance glucose level predictions remains a challenge. To address this issue, this study proposes a deep learning method of Triplet Network to disentangle CGM pattern based on specific trends and employs a deep learning-based regressor to predict glucose levels. Especially, the disentanglement method was used to enhance the classification process of the specific glucose trends visible in CGM data. This allows CGM regressor to differentiate basic glucose data into meaningful representations, as the disentanglement contributes to the network to focus on clustering salient figures. We used the Glucobench dataset, a collection of real-world CGM data from 5 diverse cohorts, including 5 to 208 participants. Despite the inherent variability in glucose recordings, our model demonstrated robust trend capture and prediction accuracy. We explored multiple window sizes and dense layer configurations, incorporating a 1D convolutional layer to enhance performance. The model achieved its best accuracy with an RMSE of 6.046 mg/dL and outperformed other machine learning models, with an average RMSE of 10.802 mg/dL across all datasets. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ENHANCING E-HEALTH CYBERSECURITY AND RESILIENCE: SHIFTING FROM MONOLITHIC TO MICROSERVICES ARCHITECTURE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2025年第1期87卷 21-34页

作者： Contașel, Cristian Rughiniș, Răzvan Trancă, Dumitru Cristian Țurcanu, Dinu Dept. of Computer Science and Engineering National University of Science and Technology POLITEHNICA Bucharest Romania Dep. of Software Engineering and Automatics Technical University of Moldova Chișinău Moldova

This study provides an innovative architectural model for e-Health systems that aims to improve cyber resilience while maintaining high availability under fluctuating traffic loads. We examined typical cybersecurity incidents in the field of e-Health, their correlations with architectural defects, and frequent design patterns in currently operational systems. A testing approach based on our research finds those weaknesses and proposes viable fixes. In this paper, a comprehensive support strategy for transitioning from conventional monolithic architectures to microservices is presented. This change makes use of cloud computing's vertical and horizontal scalability to maximize resource utilization while ensuring system reliability. We also discuss deployment ideas for the new microservices, focusing on operational resilience and cybersecurity in e-Health environments. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Game Theory-based Reverse Vickrey Auction for Dynamic Pricing in Edge Computing 3

A Game Theory-based Reverse Vickrey Auction for Dynamic Pric...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Rasane, Atharva Tapale, Manisha Dept. Computer Science and Engineering KLE Technological University’s Dr. M. S. Sheshgiri College Belagavi India

ISBN: (纸本)9798331527549

Low-latency communication is critical for effectively functioning Internet of Things (IoT) systems, including applications in healthcare monitoring, industrial automation, and smart cities. However, the vast number of IoT Devices often overwhelms cloud providers, necessitating the adoption of edge computing to reduce latency and distribute computational load. This paper introduces a novel dynamic pricing mechanism for edge computing based on a reverse Vickrey auction, leveraging game theory to balance competitive pricing with profitability for Edge Servers. We develop utility functions for both IoT Devices and Edge Servers, optimizing the markup to maximize edge server utility while adhering to the budget constraints of IoT Devices. Simulations were conducted with 10 Edge Servers and 50 IoT Devices over 2,000 time units. Results show that the proposed mechanism significantly reduces wait times, with most tasks completed within 10-time units. Moreover, dynamic pricing increases Edge Server profits by up to 10 times in some instances compared to fixed markup approaches. Notably, one server’s total profit rose from 7,702 to 76,130 and another from 57,965 to 94,298, underscoring the enhanced profitability and utilization. These findings confirm that our reverse Vickrey auction strategy effectively balances low-latency demand with sustainable operational revenue for Edge Servers, offering a robust and scalable solution for edge-centric IoT environments. © 2025 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

WQuatNet: Wide range quaternion-based head pose estimation

引用

Journal of King Saud University - computer and Information sciences 2025年第3期37卷 1-14页

作者： Algabri, Redhwan Shin, Hyunsoo Abdu, Ahmed Bae, Ji-Hun Lee, Sungon Dept. of Computer Science & Engineering College of AI Convergence Sejong University Seoul 05006 South Korea Research Institute of Engineering and Technology Hanyang University Ansan 15588 South Korea School of Software Northwestern Polytechnical University Xi’an 710072 China Department of Robotics Hanyang University Ansan 15588 South Korea

Head pose estimation (HPE) is a critical task for numerous applications ranging from human-computer interaction, healthcare, and robotics, to surveillance. Most existing methods employ Euler angles as a representation, which often face challenges such as a gimbal lock, especially in full-range rotation scenarios or rotation matrices that require nine parameters. This study introduces WQuatNet, a novel deep learning-based model that leverages the quaternion representation, which uses only four parameters, to avoid this challenge. WQuatNet was designed based on a landmark-free HPE method to predict head poses across the full-range angles of 360∘ from images. Landmark-free methods bypass the need for explicit detection of facial landmarks;instead, they leverage the entire image to estimate the head orientation. The model incorporates a RepVGG-D2se backbone for robust feature extraction and introduces two loss functions tailored for quaternion predictions. Our experimental results on multiple HPE datasets covering both narrow- and full-range angles demonstrate that WQuatNet outperforms the state-of-the-art (SOTA) approaches in terms of accuracy. The performance of the proposed HPE was evaluated using the CMU, AGORA, BIWI, AFLW2000, and 300W-LP datasets. We also perform ablation studies and error analyses to validate the significance of each component of the model. © The Author(s) 2025.

关键词： Deep neural network Full range of rotation Head pose estimation Quaternion

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：