检索结果-内蒙古大学图书馆

2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022

作者： Wang, Sying-Jyan Shih, Yen-Chang Li, Katherine Shu-Min Lin, Chen-Yeh Chong, Song-Kong National Chung Hsing University Dept. Computer Science Engineering Taichung Taiwan National Sun Yat-sen University Dept. Computer Science Engineering Kaohsiung Taiwan Cybersecurity Technology Institute Institute for Information Industry Taipei Taiwan

ISBN: (纸本)9781665409216

The IEEE Std. 1687 (IJTAG) provides a more efficient and flexible mechanism to access embedded instruments in complex system-on-chips (SoC). Embedded instruments are mainly used for testing, debugging, diagnosing, and post-silicon validation. In this paper, we propose a comprehensive protection method against data flow attacks in IJTAG networks. The network structure is arranged according to the access times of each instrument in to optimize the test efficiency and prevent third-party intellectual property attacks. Furthermore, we provide a method to group instruments to reduce hardware overhead and maintain the security. Experimental results show that the proposed methods achieve minimal overall access time (OAT) and segment insertion bit programming overhead. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Towards Content Dissemination in Subway Mobility: Re-Evaluating the Performance of Power and Interest Aware PeopleRank

Towards Content Dissemination in Subway Mobility: Re-Evaluat...

引用

IEEE International Conference on Wireless and Mobile Computing, Networking And Communications (WiMob)

作者： Sara Elsingergy Soumaia Al Ayyat Sherif G. Aly Computer Science and Engineering Dept. The American University in Cairo Cairo Egypt

ISBN: (数字)9798350387445

ISBN: (纸本)9798350387452

In this paper, we explore the performance of an opportunistic network forwarding algorithm, namely Power and Interest Aware PeopleRank (PIPeR) in a subway mobility environment. PIPeR is known to perform well according to known metrics in delivering data taking into consideration both the interest in the disseminated data, along with power conservation. The algorithm was only tested however using pedestrian mobility models. Subway mobility is a candidate for many other useful cases for opportunistic content dissemination such as that of armed conflicts where civilian populations live in subway environments for safety without fixed network infrastructure. In this work, we implement and evaluate the PIPeR algorithm in a subway model using the AnyLogic simulator. Our results show a significant increase in the f-measure by 61% and decrease in the delay by 41% in comparison to the pedestrian mobility environment. In addition to that, we pinpoint some areas of interest where content dissemination happens vigorously yet at the expense of some increase in cost and power consumption, which we subsequently alleviate by using a particular hibernation model that decreases the power consumption by 43 % at the expense of only 6% reduction in delivery ratio.

关键词： Measurement Wireless communication Power demand Costs Pedestrians Mobility models Hybrid power systems Delays Safety Public transportation

来源：评论

学校读者我要写书评

暂无评论

Privacy preserving data mining techniques using a denoising Auto Encoder (DAE) for medical images

SSRN

引用

SSRN 2024年

作者： Kalshetty, Jagadevi N. Pareek, Piyush Kumar Dept. of Computer Science and Engineering Nitte Meenakshi Institute of Technology India

The p proposed article a new reversible privacy-preserving data hiding approach for medical imaging. Our method uses a Denoising Autoencoder (DAE) to successfully incorporate sensitive information inside medical images, ensuring data integrity and reversible. This method concentrates on patient privacy while keeping medical images useful for diagnostic purposes. Our method uses a Denoising Autoencoder (DAE) to successfully incorporate sensitive information inside medical images, ensuring data integrity and reversible. This method concentrates on patient privacy while keeping medical images useful for diagnostic purposes. © 2024, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Design and Implement Driveway Door Access Control by Using VLC and RFID Technology 12

Design and Implement Driveway Door Access Control by Using V...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Hung, Chi-Huang Fanjiang, Yong-Yi Li, Cheng-Yen Chiu, Sheng-Wei Hung, Tzu-Chieh Chiang, Meng-Huan Fu Jen Catholic University Lee-Ming Institute of Technology Graduate Institute of Applied Science and Engineering Dept. of Information Technology New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering Dept. of Computer Science and Information Engineering New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering New Taipei City Taiwan Lee-Ming Institute of Technology Dept. of Vehicle Engineering New Taipei City Taiwan Kang Chiao International School Dept. of International High School New Taipei City Taiwan

ISBN: (纸本)9798350340181

In recent years, the application of radiofrequency identification technology in smart access control systems has become a trend. Users only need to take out the RFID electronic key and approach the sensor of the gate to open the gate through signal induction. For housewives who always have a lot of bags and bags in their hands, there is no need to free up one hand to find the key to open the door and avoid being in a hurry. However, it is relatively inconvenient for drivers. Instead, it is much more convenient to use wireless controllers or license plate recognition. This study proposes a system that combines RFID with optical communication technology and vehicle headlights to open the garage door with a light code. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Rough Set Based Recipe Clustering Approach

Rough Set Based Recipe Clustering Approach

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： Priyanka Das Chandrani Mukherjee Samiksha Gupta Sayan Roy Khushi Shah Shreya Singh Dept. of Computer Application and Science Institute of Engineering & Management Kolkata India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Online cooking instructions including ingredient lists and cooking methods are now widely available due to the proliferation of recipe sharing websites. Finding novel and complex patterns in such vast, ambiguous categorical data sets is a crucial task. Conventional clustering analysis algorithms frequently fail to address the uncertainty surrounding the exact value of features found in these categorical data sets. Thus to aid in decision-making, rough set based clustering is frequently used. This study aims to identify the optimal clustering feature from the recipe data that will result in the grouping of related food products by applying the rough purity notion. The recipe data has been regarded as a categorical valued information system in this instance, and information theoretic attribute purity is taken into account using the rough purity technique.

关键词： Uncertainty Communication systems Decision making Rough sets Clustering algorithms Food products Information systems

来源：评论

学校读者我要写书评

暂无评论

A Comparative Exploration of Machine Learning and Graph Deep Learning Models for Discriminatory Speech Detection

A Comparative Exploration of Machine Learning and Graph Deep...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： J Kavya K N Pragathy Reddy Phanindra Maddipatla Anjali Kesanapalli Arti Arya Dept. of Computer Science Engineering PES University Bengaluru Karnataka India

ISBN: (数字)9798350371314

ISBN: (纸本)9798350371321

In an era marked by digital expansion, discriminatory speech remains a widespread concern, exerting significant societal implications. This study presents an overview of discriminatory speech detection techniques and explores the complexities involved in identifying discriminatory speech by utilizing a variety of datasets from various fields. The importance of preprocessing methods and feature engineering is next examined, opening the door for more in-dept. study. Furthermore, the paper delves into traditional Machine Learning (ML) algorithms and state-of-the-art Deep Learning (DL) models along with a crucial component of using graph-based structures with Natural Language Processing (NLP) techniques and the use of graphs to extract contextual information. Using both graphs and NLP algorithms enhances the identification process by uncovering contextual connections within textual data.

关键词： Deep learning Voice activity detection Machine learning algorithms Computational modeling Feature extraction Natural language processing Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Key Vertex Pairs Extraction for Graph Classification Based on Probability Distribution Learning

Key Vertex Pairs Extraction for Graph Classification Based o...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Jianming Huang Hiroyuki Kasai Dept. of Computer Science and Communication Engineering WASEDA University Tokyo Japan

Graph classification is a hot topic of machine learning for graph-structured data, and it is also a very potential and valuable research. However, the difficulty of graph classification is challenging and special, which is quite different from the normal classification problems. One of the most difficult points of graph classification is that the numbers of vertex neighbors in graphs are usually variable, which makes the number of weights uncertain and ambiguous. Recent work such like the graph attention network apply the transformer on the graph neural network. However, the learned attentions cannot strictly reveal the importance of each part of graph, which makes the model less explainable. Moreover, for small datasets, it performs less effectively because of the excessive parameters. In order to overcome these difficulties, we propose a lightweight model with an edge weighting function based on the probability distributions of node pair features learned by the Gaussian mixture model. Although the proposed framework is simple, the experimental results shows its effectiveness on small datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Gramian Angular Fields (GAF) and Markov Transition Field (MTF) Images data by Using them as Input to the Deep Learning Neural Network Solar Flare Production Platform

Comparison Between Gramian Angular Fields (GAF) and Markov T...

引用

2022 International Conference on engineering and MIS, ICEMIS 2022

作者： Nagem, Tarek A M Hamad Alshareef, Sohil Mohamed, Abdelhafid Gihedan, Akram Albargathe, Salma Libyan British University Dept. Computer System Design Benghazi Libya University of Benghazi Dept. Software Engineering Benghazi Libya College of Computer Technology Dept. Software Engineering Benghazi Libya Darna University Dept. Computer Science Algoba Libya

ISBN: (数字)9781665454360

ISBN: (纸本)9781665454360

The prediction of solar storms from real-time satellites data is an essential to protect various aviation, power, and communication infrastructures. For this reason, current research interest is focusing on creating systems that can predict solar fare accurately. This paper combers Gramian Angular Fields (GAF) images and Markov Transition Field (MTF) images that have been generated by converting pre-flare Geostationary Operational Environmental Satellite (GOES) data from 2010 to 2016. After that, the deep learning neural network for the solar flare production platform accepts both MTF and GAF images as input to generate the predictions. Furthermore, this paper;investigated using MTF and GAF images spritely as input to the solar flare production platform. After that, the results of MTF and GAF images were compared using various prediction verification measures. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Scratchpad Spiking Neural Network Accelerator

A Scratchpad Spiking Neural Network Accelerator

引用

Computing and Machine Intelligence (ICMI), International Conference on

作者： Rasha Karakchi Dept. Computer Science and Engineering University of South Carolina Columbia SC

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

Spiking Neural Networks (SNNs) have recently been used as a computational model for applications such as deep learning, image recognition and machine learning. Similar to the biological brain, SNN neurons depend on the membrane level to fire an output. If the level exceeds a specified threshold, the neuron sends an output to activate next neurons. This leads to an unbalanced workload among the neurons. The dynamically-changing membrane level is stored inside a neuron. In hardware, this storage can be implemented as a register or on-chip memory, which determines the amount of consumed resources and, in turns, affects the network scalability. SNN accelerators have recently been implemented on UltraScale FPGAs devices for high-performance purposes. On-chip memories on these devices are classified as distributed memory, Block RAMs (BRAMs) and Ultra RAMs (URAMs). In this paper, we explored the impact of using different on-chip memories to store the membrane level of SNN neurons. We implemented a parameterizable SpIking Neural networK (SINK) accelerator where the network capacity and weight_width are parameters. SINK has the ability to run in four different modes based on the memory type. We ran SINK on UltraScale Zyncl04 FPGA device and measure the utilization of the hardware resources (LUTs), registers, memory, power consumption and performance. The results show that URAM can be the best fit to store the membrane level, since it used 30%, 11 % and 2% less LUTs, Regs, and power 2% respectively comparing with BRAM and distributed memory

关键词： Neurons Memory management Random access memory Spiking neural networks Biomembranes Hardware System-on-chip

来源：评论

学校读者我要写书评

暂无评论

On Fusing ChatGPT and Ensemble Learning in Discontinuous Named Entity Recognition in Health Corpora

arXiv

引用

arXiv 2024年

作者： Chen, Tzu-Chieh Lin, Wen-Yang Dept. of Computer Science and Information Engineering National University of Kaohsiung Taiwan

Named Entity Recognition (NER) has traditionally been a key task in natural language processing (NLP), aiming to identify and extract important terms from unstructured text data. However, a notable challenge for contemporary deep-learning NER models has been identifying discontinuous entities, which are often fragmented within the text. To date, methods to address Discontinuous Named Entity Recognition (DNER) have not been explored using ensemble learning to the best of our knowledge. Furthermore, the rise of large language models (LLMs, such as ChatGPT) in recent years has shown significant effectiveness across many NLP tasks. Most existing approaches, however, have primarily utilized ChatGPT as a problem-solving tool rather than exploring its potential as an integrative element within ensemble learning algorithms. In this study, we investigated the integration of ChatGPT as an arbitrator within an ensemble method, aiming to enhance performance on DNER tasks. Our method combines five state-of-the-art (SOTA) NER models with ChatGPT using custom prompt engineering to assess the robustness and generalization capabilities of the ensemble algorithm. We conducted experiments on three benchmark medical datasets, comparing our method against the five SOTA models, individual applications of GPT-3.5 and GPT-4, and a voting ensemble method. The results indicate that our proposed fusion of ChatGPT with the ensemble learning algorithm outperforms the SOTA results in the CADEC, ShARe13, and ShARe14 datasets, achieving improvements in F1-score of approximately 1.13%, 0.54%, and 0.67%, respectively. Compared to the voting ensemble method, our approach achieved improvements of about 0.63%, 0.32%, and 0.09%. Furthermore, compared to GPT-3.5 and GPT-4, our average results were approximately 7.42%, 0.89%, and 0.54% higher. The results demonstrate the effectiveness of our proposed fusion method of ChatGPT and ensemble algorithms, showcasing its potential to enhance NLP applications in

关键词： Contrastive Learning

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：