检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Kang, Sukmin Lee, Seongtae Koo, Hyunwoo Chwa, Hoon Sung Lee, Jinkyu Dept. of Semiconductor and Display Engineering Sungkyunkwan University Korea Republic of Samsung Electronics Co. Ltd. Korea Republic of Dept. of Computer Science and Engineering Sungkyunkwan University Korea Republic of School of Electronic and Electrical Engineering Sungkyunkwan University Korea Republic of Dept. of Electrical Engineering and Computer Science Dgist Korea Republic of

ISBN: (纸本)9798400706011

As the application scope of DNNs executed on microcontroller units (MCUs) extends to time-critical systems, it becomes important to ensure timing guarantees for increasing demand of DNN inferences. To this end, this paper proposes RT-MDM, the first RealTime scheduling framework for Multiple DNN tasks executed on an MCU using external memory. Identifying execution-order dependencies among segmented DNN models and memory requirements for parallel execution subject to the dependencies, we propose (i) a segment-group-based memory management policy that achieves isolated memory usage within a segment group and sharded memory usage across different segment groups, and (ii) an intra-task scheduler specialized for the proposed policy. Implementing RT-MDM on an actual system and optimizing its parameters for DNN segmentation and segment-group mapping, we demonstrate the effectiveness of RT-MDM in accommodating more DNN tasks while providing their timing guarantees. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

State of the art: Security Testing of Machine Learning Development Systems 14

State of the art: Security Testing of Machine Learning Devel...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Das, Saikat Krishnamurthy, Bhargavi Das, Raktim Ranjan Shiva, Sajjan G Utah Valley University Dept. of Computer Science Orem United States Siddaganga Institute of Technology Dept. of Computer Science Karnataka Tumakuru India Stamford University Bangladesh Dept. of Computer Science Dhaka Bangladesh University of Memphis Dept. of Computer Science Memphis United States

ISBN: (纸本)9798350360134

In recent days, machine learning (ML) systems have become integral to nearly all mainstream applications. Understanding the underlying logic that contributes to the desired behavior in ML systems can be challenging. Humans play a crucial role in providing the necessary data samples for training ML models to ensure accurate predictions. The complexity of ML testing arises from various factors such as data dependency, dynamic model behavior, the absence of a test oracle, a vast input space, and the lack of a specific testing life cycle tailored for ML. Testing ML systems is not a straightforward process, as it not only involves verifying the code and their corresponding data but also is further complicated by the dynamic nature of these systems. A typical ML model undergoes seven stages, including eliciting business needs/requirements, gathering data, selecting a model, training the model, testing the model, deploying the model, and monitoring the model. Throughout the ML Development Life Cycle (MLDLC), each stage introduces various security risks. This paper explores the current state of the literature on security attacks and defense approaches concerning data, model, and prediction output of ML models. The paper also addresses potential security attacks at each stage of the MLDLC and the corresponding security measures to mitigate those attacks. © 2024 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection Using Deep Learning and Anomaly Detection Techniques

Cybersecurity Threat Detection Using Deep Learning and Anoma...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Rajendran, T. Mohamed Imtiaz, N. Jagadeesh, K. Sampathkumar, Balaji Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Nagarjuna College of Engineering and Technology Dept. of Information Science and Engineering Bangalore India Sri Venkateswaraa College of Technology Dept. of Computer Science and Engineering Chennai India Akshaya College of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359688

Through the use of combined deep learning and anomaly detection approaches, this research investigates the area of cybersecurity threat detection. The study proves the framework's extraordinary success in recognizing as well as mitigating diverse cyber dangers, including insider threats and zero-day attacks, through practical testing and case studies. The framework establishes itself as a proactive cybersecurity solution adaptive to the changing threat landscape due to its high accuracy of 95%, low amount of false positives 5%, and quick reaction times. The recommendations cover user training, scalability, regulatory compliance, including cross-disciplinary collaboration. Behavioral analysis, AI explainability, IoT security, and countering quantum computing concerns should be the main areas of future research. These revelations help the cybersecurity industry become more resilient and well-prepared. In this research investigation, experiments on threat detection were conducted using deep learning algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The findings of the study reveal that a detection accuracy of 93% was achieved by CNN, while a higher accuracy of 96% in threat detection was exhibited by RNN. © 2024 IEEE.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Modular LLC Resonant Converters with New Active Voltage Doublers Based Output Voltage Balancers for MVDC Distributed PV Systems

Modular LLC Resonant Converters with New Active Voltage Doub...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Kanathipan, Kajanan Abbasi, Mehdi Cheema, Muhammad Ali Masood Lam, John York University Dept. of Electrical Engineering and Computer Science Toronto Canada Northern Transformer Toronto Canada

ISBN: (纸本)9798350376067

In this article, a new interconnecting modular full-bridge step-up LLC resonant converter for PV energy applications is proposed. The proposed converter module is capable of regulating power flow between modules through the use of pulse-width modulation (PWM) control on a new active voltage doubler based voltage balancer (VD), where an auxiliary switch is connected to the output VD. The input full bridge switches can be regulated with phase-shift control to achieve maximum power point tracking (MPPT) for all modules. Zero-voltage switching operation is realized on all module switches. This allows each of the converter modules to achieve a high efficiency while simultaneously achieving MPPT and balanced output voltage. The steady-state and dynamic performance of the designed system is validated on a four module 6kW, 8kV-output simulation and a scaled-down 500W, 700V-output two module laboratory prototype. © 2024 IEEE.

关键词： Resonant converters

来源：评论

学校读者我要写书评

暂无评论

Using IoT Enabled Predictive Maintenance to Enhance Business Operations: Benefits and Challenges 7

Using IoT Enabled Predictive Maintenance to Enhance Business...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Ansari, Seema Ansari, Adeel Institute of Business Management Dept. of Electrical Engineering Karachi Pakistan Shaheed Zulfiqar Ali Bhutto Institute of Science and Technology Dept. of Computer Science Karachi Pakistan

ISBN: (纸本)9798331534271

In today's changing world incorporating Internet of Things (IoT) technologies, into maintenance strategies is seen as a crucial innovation to improve business operations. This study delves into the use of driven maintenance systems and their notable impact on enhancing business efficiency cutting costs and ensuring operational dependability. By making use of real time data from sensors and devices these systems can predict equipment failures in advance reducing downtime and prolonging the lifespan of vital assets. The study provides a look at how maintenance strategies have evolved over time the technology behind powered predictive maintenance and how it revolutionizes business processes. The insights gathered from case studies and analysis of current executions reveals how business have transformed and achieved enhancement in operations. The paper also reflects challenges with their related solutions and suggested strategies to solve them. The findings show that implementing IoT for maintenance is not a technology hop but a necessity for companies struggling to stay in today's competitive market. In addition to this it investigates developments and possible innovations in this area emphasizing the evolvement and rising significance of IoT, in the upkeep of business industry. This research has explored into the competences of this technology highlighting its capability to reduce prices, improve efficiency, lift equipment reliability and upkeep making decision depending on data. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Entropy-weighted Voting Method for Diffusion-based Semantic Segmentation 14

Entropy-weighted Voting Method for Diffusion-based Semantic ...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Jeong, Seonggyun Heo, Yong Seok Ajou University Dept. of Electrical and Computer Engineering Suwon Korea Republic of Ajou University Dept. of Electrical and Computer Engineering Dept. of Artificial Intelligence Suwon Korea Republic of

ISBN: (纸本)9798350313277

Recently, semantic segmentation methods leveraging image generation models have garnered significant attention. In particular, approach based on Diffusion models (DDPM) that utilize mid-level activations from the diffusion network with a majority voting of distributions from several light multi-layer perceptron (MLP) have shown better performance compared to GAN-based approaches. However, utilizing a simple majority voting system is suboptimal. In this paper, we propose a novel voting method for DDPM-based semantic segmentation. Our method introduces a weighted sum of distributions, where the weights are determined by the entropy of the class prediction results obtained from each MLP model. We conduct experiments on various datasets, including LSUN-Bedroom, FFHQ-256, LSUN-Cat, and LSUN-Horse. The results demonstrate that our proposed method achieves better mean Intersection over Union (mIoU) scores compared to previous work. © 2023 IEEE.

关键词： diffusion entropy semantic segmentation voting

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Analysis for Normal and Canonical Internal Descriptions of A Notch Digital Filter

Sensitivity Analysis for Normal and Canonical Internal Descr...

引用

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2024

作者： Hinamoto, Yoichi Doi, Akimitsu Dept. of Electrical and Computer Engineering National Institute of Technology Kagawa College Takamatsu761-8058 Japan Dept. of Computer Science Hiroshima Institute of Technology Hiroshima731-5193 Japan

ISBN: (纸本)9798350353464

This paper analyzes coefficient sensitivity for the internal descriptions (state-space models) of a 2nd-order recursive notch digital filter. To this end, a 2nd-order recursive notch digital filter is realized by a normal-form or canonical-form internal description. The coefficient sensitivity for each internal description is then analyzed to derive the improved l2-sensitivity measure. Moreover, the coefficient sensitivity of the normal-form internal description is compared with that of the canonical-form counterpart by means of numerical experiments. The simulation results clarify that the normal-form internal description has low coefficient sensitivity as a whole comparing to the canonical-form counterpart. ©2024 IEEE.

关键词： Notch filters

来源：评论

学校读者我要写书评

暂无评论

The SNS based E mentoring and Development of Computational Thinking for Undergraduate Students in an Online Course

引用

Educational Technology and Society 2023年第2期26卷 147-164页

作者： Jang, Yeonju Choi, Seongyune Kim, Seonghun Kim, Hyeoncheol Dept. of Computer Science and Engineering The Graduate School of Korea University South Korea Dept. of Education Gachon University South Korea Dept. of Computer Science and Engineering Korea University South Korea

Given the importance of digital technology in daily life, computational thinking (CT) has become a necessary skill for everyone, not just for computer scientists. For CT development, students need to receive appropriate social learning support. However, instructors find it difficult to provide such support to many students in online courses. This study aimed to examine the effectiveness of e-mentoring via social network services (SNS) in developing students’ CT during large-scale online courses. A total of 327 undergraduate students volunteered to participate in this study, which included 16 weeks of lectures aimed at developing CT. The effects of SNS-based e-mentoring on CT development, the influences of each e-mentoring activity on CT development, and gender differences were analyzed using data on participants’ CT assistance scores and their utilization of e-mentoring activities. The findings indicated that SNS-based e-mentoring was effective in developing the CT of undergraduate students’ engagement in a large-scale online course. The most influential e-mentoring activities for students’ CT development were informational and technical support in a group and informational support in a private environment. Female students benefited more from SNS-based e-mentoring than male students, and they also engaged in more types of e-mentoring activities than male students. Participation in SNS-based e-mentoring was found to lower the gap in CT between students with and without prior learning experience. Our study findings can be used by educational institutions and instructors when designing courses for students’ CT development in large-scale online courses or when developing strategies to close the gender gap in CT ability. © 2023,Educational Technology and Society. All Rights Reserved.

关键词： Computational thinking Computational thinking and prior learning experience e-Mentoring Gender difference Social Network Service (SNS)

来源：评论

学校读者我要写书评

暂无评论

Benchmark Study on YOLOv8 Variants in Localized Multiclass Fault Detection in PCBs 6

Benchmark Study on YOLOv8 Variants in Localized Multiclass F...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Najib, Taeef Muntasir, Fahim Wasi, Wasif Al Wazed Sidetrek Dhaka Bangladesh Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350385779

Detecting surface faults on PCBs is critical for ensuring device dependability and performance. Manual PCB inspection methods like X-ray imaging struggle to ensure quality control due to limitations in speed and defect characterization. However, advanced automated technologies, such as object detection models like YOLOv8, have emerged as a more efficient solution. This study focuses on evaluating the performance of different YOLOv8 variants in identifying and classifying various defects on PCBs. A benchmark of how each modification of the model performs detection and the factors behind were investigated here. It was determined that, YOLOv8 is sensitive to the amount of data it is being trained on, as the larger models tend to overlearn on smaller datasets. YOLOv8-m had the best performance, 97.1% precision, concerning the time taken and epoch count, over others. Large YOLOv8 variants, such as YOLOv8x, are also computationally expensive. The models were trained for 200 epochs with a patience value set at 50. Both increasing the number of data points and the resources will improve the performance and facilitate the overall training procedures. A significant gap in automated electronics production is addressed by this study: precise PCB fault localization for higher reliability of the product. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Greek Conversational Agent for Hematologic Malignancies: Usability and User Experience Assessment

A Greek Conversational Agent for Hematologic Malignancies: U...

引用

34th Medical Informatics Europe Conference, MIE 2024

作者： Chatzimina, Maria E. Papadaki, Helen A. Pontikoglou, Charalampos Tsiknakis, Manolis Dept. of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece Institute of Computer Science FORTH Heraklion Greece Dept. of Hematology School of Medicine University of Crete Heraklion Greece

ISBN: (纸本)9781643685335

Enabling patients to actively document their health information significantly improves understanding of how therapies work, disease progression, and overall life quality affects for those living with chronic disorders such as hematologic malignancies. Advancements in artificial intelligence, particularly in areas such as natural language processing and speech recognition, have resulted in the development of interactive tools tailored for healthcare. This paper introduces an innovative conversational agent tailored to the Greek language. The design and deployment of this tool, which incorporates sentiment analysis, aims at gathering detailed family histories and symptom data from individuals diagnosed with hematologic malignancies. Furthermore, we discuss the preliminary findings from a feasibility study assessing the tool's effectiveness. Initial feedback on the user experience suggests a positive reception towards the agent's usability, highlighting its potential to enhance patient engagement in a clinical setting. © 2024 The Authors.

关键词： Chatbots

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：