检索结果-内蒙古大学图书馆

International Health Informatics Conference, IHIC 2023

作者： Sulaiman, Sadiya Thanka, M. Roshni Edwina, E. Bijolin Salam, Nader Department of Computer Science and Engineering Karunya Institute of Technology and Science Tamil Nadu Coimbatore India

ISBN: (纸本)9789819771899

Stroke, primarily categorized as ischemic and hemorrhagic, stands among the top global causes of mortality and can lead to severe neurological conditions if left untreated. The emergence of machine intelligence, especially advanced neural networks, has brought significant advancements in medical imaging, including the automated segmentation of stroke lesions. This automation aids radiologists and surgeons in more effective diagnosis and treatment planning. This review paper concentrates on deep learning methods used in segmenting ischemic and hemorrhagic stroke lesions, examining these models from an architectural standpoint. The paper begins with a discussion on the types of strokes. Subsequently, delve into a review of deep learning models, specifically emphasizing their application in ischemic and hemorrhagic stroke lesion segmentation. The performance, advantages, and limitations of these models are assessed and comparisons among them are presented. The paper concludes by spotlighting the current needs in this field and suggesting potential avenues for future research. The study aims to provide insights to both advancedresearchers and newcomers in the field, thereby fostering future advancements in stroke lesion segmentation using deep learning methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Transillumination

来源：评论

学校读者我要写书评

暂无评论

FLoomChecker: Repelling Free-riders in Federated Learning via Training Integrity Verification 30

FLoomChecker: Repelling Free-riders in Federated Learning vi...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Liang, Guanghao Chang, Shan Dai, Minghui Zhu, Hongzi Donghua University School of Computer Science and Technology Shanghai China Shanghai Jiaotong University Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798331515966

Federated learning is a mechanism that allows participating clients to train locally with their own data in order to receive rewards, thus avoiding the transfer of data to a central server and protecting users' privacy. However, some 'lazy' clients may adopt the strategy of fabricating false model local updates in an attempt to 'free-riding' without actually contributing real data or consuming local computational resources. To address this issue, we propose FLoomChecker, an integrity detection scheme for federated learning training models. The scheme combines the techniques of trusted execution environments and Bloom filters to efficiently identify clients that do not train honestly by committing and proving. We conducted experimental evaluations of FLoomChecker, examining three main aspects: query time, build time, and memory footprint in trusted execution environment (TEE). The experimental results demonstrate the effectiveness of our scheme, and its performance improves as the number of local training rounds increases. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Route Management for Secure Data Aggregation in Duty-Cycled Mobile Sink-Based WSNs

引用

SN computer science 2025年第3期6卷 1-15页

作者： Sran, Sukhwinder Singh Sidhu, Sukhpreet Kaur Kumar, Manoj Sood, Preeti Department of Computer Science & Engineering Punjabi University Punjab Patiala 147002 India Department of Mathematics Akal University Talwandi Sabo Punjab Bathinda 151302 India Department of Computer Engineering Yadavindra Department of Engineering Talwandi Sabo Punjab Bathinda 151302 India Research Scholar Department of Computer Engineering Yadavindra Department of Engineering Talwandi Sabo Punjab Bathinda 151302 India

Secure data aggregation and effective data transmission are necessary to enhance sensor network durability and performance. Secure data collection from the duty-cycled sensor nodes using a moving sink and evenly distributing the energy usage over the network is a promising solution. This work offers a dynamic path management technique to present a unique hybrid solution for energy efficiency and secure data aggregation. The goal is to minimize energy use and extend the network lifetime without compromising security. By utilizing sink mobility to dynamically optimize data collection paths, our proposed approach lowers the consumption of energy and enhances data integrity. The duty cycling mechanism is integrated to ensure the conservation of energy and optimal operation of sensor nodes extending network connectivity. The privacy, consistency of the aggregated data are guaranteed and the security of data transfer is reinforced by a lightweight encryption technique. It has been observed from the results that the proposed scheme decreases energy consumption, route construction cost, prolongs the lifespan of the network and transmits data in an encrypted form. For moving sink-based duty-cycled sensor networks, this article offers a thorough solution to the challenges related to secure data aggregation, dynamic routing, and energy efficiency. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adaptive routing Data aggregation DRMMS Mobile sink Network lifetime Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Denoising Historical Text Documents Using Generative Adversarial Networks 8th

Denoising Historical Text Documents Using Generative Adversa...

引用

8th International Symposium on Intelligent Informatics, ISI 2023

作者： Preethi, P. Upadhya, Pradhyumna Likith, M.C. Meghana, N. Karande, Shruti Gunnan Ramkumar, Shreya Department of Computer Science and Engineering PES University Karnataka Bengaluru560085 India

ISBN: (纸本)9789819721467

The field of image-to-image translation, particularly in the context of denoising historical text documents, has witnessed significant advancements driven by the application of Generative Adversarial Networks (GANs). GANs have shown promise in various image restoration tasks, including unpaired image-to-image translation and denoising. This paper explores and contributes to the existing body of knowledge on denoising historical text documents using GANs, with a focus on addressing specific challenges such as stains, faded ink, background noise, and various types of artificial noise. The field of image-to-image translation, particularly in the context of denoising historical text documents, has witnessed significant advancements driven by the application of Generative Adversarial Networks (GANs). GANs have shown promise in various image restoration tasks, including unpaired image-to-image translation and denoising. This paper explores and contributes to the existing body of knowledge on denoising historical text documents using GANs, with a focus on addressing specific challenges such as stains, faded ink, background noise, and various types of artificial noise. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Penetration Testing Operating Systems: Exploiting Vulnerabilities

Penetration Testing Operating Systems: Exploiting Vulnerabil...

引用

2024 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2024

作者： Gardner, Evan Singh, Gurmeet Qu, Weihao Software Engineering Monmouth University Department of Computer Science United States

ISBN: (纸本)9798350349832

The safeguarding of critical data stored on devices such as phones, computers, and tablets against unauthorized access has emerged as a central concern in modern society. Along with the increasing reliance on these devices for both productivity and personal affairs, the protection of the vast collections of sensitive information becomes crucial. Information safety against unauthorized access is a critical area in cybersecurity which is addressed through the discipline of penetration testing. This practice involves security researchers simulating adversarial attacks to evaluate the defenses of various technological systems, including web applications, operating systems, and networks, with the goal of protecting sensitive data from malicious actors. This research specifically focuses on the study of penetration testing operating systems without requiring login credentials, employing techniques such as command combinations in languages like BASH within the terminal to gain access to administrative accounts. Our further studies explore the performance of emulating keystrokes when these command combinations are used in conjunction with penetration testing devices, such as a USB Rubber Ducky, focusing on optimizing speed and efficiency. This research uncovers significant security vulnerabilities that, if exploited, could result in severe consequences not only for individual devices but also for entire networks and critical infrastructures, including core businesses, healthcare systems, schools, and government agencies. By identifying and mitigating these vulnerabilities, we contribute to strengthening security protocols, such as implementing system administration enhancements that prevent unauthorized access to the root terminal. In this way, our work bolsters efforts to protect digital systems against evolving cyber threats, ensuring the safety and integrity of both individual and collective digital operations. © 2024 IEEE.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

Precise Lung Disease Classification Through Bagging Ensemble Method 7

Precise Lung Disease Classification Through Bagging Ensemble...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shimja, M. Kartheeban, K. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372816

Lung disease pose a significant global health challenge, with their prevalence and impact on public well-being necessitating advanced diagnostic methods for timely and accurate identification. As a vital organ for respiratory function, lungs are susceptible to an infinite number of conditions, ranging from infectious diseases like pneumonia and tuberculosis to chronic ailments such as chronic obstructive pulmonary disease (COPD) and lung cancer. The study proposes an innovative approach for accurate lung disease classification utilizing a Bagging ensemble technique (Bootstrap Aggregating). Three pre-trained models, namely Modified VGG-16, VGG-19, and MobileNet V2, are individually trained on a common computed tomography (CT) image dataset. The fine-tuned models predict class probabilities and the bagging ensemble technique amalgamates their predictions by calculating the average probability score. The input images are correctly classified into five distinct groups by the ensemble model such as Normal, Covid-19, Viral Pneumonia, Bacterial Pneumonia, and Tuberculosis with an impressive accuracy of 97.99%, aiming to alleviate individual model biases, enhance overall predictive accuracy and provide a stable architecture for the precise classification of various lung diseases. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

SCOUT+: Towards Practical Task-Driven Drivers' Gaze Prediction 35

SCOUT+: Towards Practical Task-Driven Drivers' Gaze Predicti...

引用

35th IEEE Intelligent Vehicles Symposium, IV 2024

作者： Kotseruba, Iuliia Tsotsos, John K. York University Department Of Electrical Engineering And Computer Science Toronto Canada

ISBN: (纸本)9798350348811

Accurate prediction of drivers' gaze is an important component of vision-based driver monitoring and assistive systems. Of particular interest are safety-critical episodes, such as performing maneuvers or crossing intersections. In such scenarios, drivers' gaze distribution changes significantly and becomes difficult to predict, especially if the task and context information is represented implicitly, as is common in many state-of-the-art models. However, explicit modeling of top-down factors affecting drivers' attention often requires additional information and annotations that may not be readily *** this paper, we address the challenge of effective modeling of task and context with common sources of data for use in practical systems. To this end, we introduce SCOUT+, a task-and context-aware model for drivers' gaze prediction, which leverages route and map information inferred from commonly available GPS data. We evaluate our model on two datasets, DR(eye)VE and BDD-A, and demonstrate that using maps improves results compared to bottom-up models and reaches performance comparable to the top-down model SCOUT which relies on privileged ground truth information. Code is available at https://***/ykotseruba/SCOUT. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Neural Program Synthesis in High Level Code Generation 15

Unveiling the Power of Neural Program Synthesis in High Leve...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sai, Gurram Kumar Harshith, Koganti Sri Sai Varma, Kucharlapati Akash Yashwanth Kiran, G. Swaminathan, J. Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350370249

In this research, we delve into a transformative exploration of the realm of code generation, unveiling three fundamental modules that constitute the backbone of our study: the Text-to-Code Generation Model, Code Autocompletion Model, and the formidable Neural Program Synthesis Model. At the forefront of our investigation, we underscore the paramount importance of Neural Program Synthesis - a dynamic force adept at crafting custom programs from input-output examples. Our exploration delves into the intricate landscape of natural language-to-code generation, offering profound insights and invaluable contributions to the field. The ability to automatically generate code from natural language instructions holds immense significance in streamlining software development processes, reducing manual effort, and enhancing productivity. Furthermore, this research addresses a pressing need within the software engineering community for efficient methods of code generation, particularly in domains where human-program interaction is prevalent. Through rigorous experimentation and meticulous analysis, we shed light on methodologies and promising avenues for future research in this burgeoning domain, paving the way for advancements in automated software development and programming assistance tools. © 2024 IEEE.

关键词： Input output programs

来源：评论

学校读者我要写书评

暂无评论

FLARE: Federated Learning And Resilient Encryption for Firewalls 7

FLARE: Federated Learning And Resilient Encryption for Firew...

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Senthilkumar, Lohith Rengarajan, Aaditya Psg College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331527822

Traditional firewalls rely on static rule-based mechanisms, where rules are manually defined and often written in specialized languages. While effective to a degree, these rules are inherently limited and can be easily bypassed by new and evolving types of malware, leading to significant security vulnerabilities. To address these challenges, we propose FLARE: Federated Learning And Resilient Encryption, a novel machine learning-based firewall solution. FLARE dynamically analyzes past network connections to predict and determine the appropriate actions for incoming traffic, thereby adapting to emerging threats in *** the sensitive nature of firewall data, which often contains confidential information, the training of machine learning models poses significant privacy risks. FLARE mitigates these risks by incorporating federated learning, allowing the model to learn from decentralized data sources without requiring raw data to be shared. To further enhance privacy, we introduce an encryption layer that ensures the central model learns from encrypted weights, preventing exposure of sensitive information known to the local model. This combined approach not only improves the resilience of firewalls but also safeguards the confidentiality of the data used in training, offering a robust solution for modern cybersecurity challenges. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Design of high output DC/DC boost circuit without boost transformer 8

Design of high output DC/DC boost circuit without boost tran...

引用

8th International Conference on Communication and Information Systems, ICCIS 2024

作者： Hong, Qin Zhou, Liang Jia, Zhongning Liu, Chun Liu, Jianbo Software Engineering Institute of Guangzhou Department of Computer Science Guangzhou China

ISBN: (纸本)9798331531171

The development of IOT smart devices has necessitated increasingly stringent requirements for DC power sources in terms of output voltage, size, and cost. For instance, Avalanche Photodiodes (APDs), utilized as photodetectors, require a significantly high reverse bias voltage during the detection of feeble optical signals to achieve optimal gain and high signal-to-noise ratio, thereby ensuring exceptional sensitivity. To address the diverse demands of various smart devices for DC power, a high-output DC/DC boost circuit without a step-up transformer has been innovatively designed. This circuit is comprised of four fundamental components: an oscillator circuit, a comparator circuit, a voltage multiplier circuit, and a constant-current and voltage-stabilizing circuit. The paper conducts a comprehensive theoretical analysis of the circuit's topology, parameter selection, and operational process, which is further validated through Multisim simulation. Additionally, a PCB circuit was designed, fabricated, and underwent rigorous practical testing. The test results conclusively demonstrate that the designed boost circuit proficiently provides APDs with the appropriate bias voltage, eliminating the need for boost transformer. It boasts high output voltage, a simplistic structure, small size, and low cost, enabling it to seamlessly share the same input power source with the APD detection circuit and be integrated into the same PCB layout. © 2024 IEEE.

关键词： avalanche photodiode boost circuit direct current stabilized power supply oscillator voltage multiplier circuit

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：