检索结果-内蒙古大学图书馆

Proceedings of the 2024 5th International Conference on Big Data Economy and Information Management

作者： Min-Shiang Hwang Yung-Ling Chang Cheng-Ying Yang Chia-Chun Wu Department of Computer Science and Information Engineering Asia University Taichung Taiwan The Ph.D. Program in Artificial intelligence Asia University Taichung Taiwan Department of Computer Science University of Taipei Taipei Taiwan Department of Computer Science and Information Engineering National Quemoy University Kinmen Taiwan

ISBN: (纸本)9798400711862

Recently, Wei & Chen proposed a secure three-party mutual authentication protocol for RFID based on elliptic curve cryptography (ECC). Their approach can allow insecure communication between the reader and the backend, so their approach must achieve mutual authentication between the tag, reader, and backend. In addition, their method also satisfies the essential characteristics of RFID systems, such as confidentiality, anonymity, resistance to tracking attacks, and spoofing attacks. However, this article finds that its method cannot meet the mutual authentication and denial of service attacks.

关键词： ECC

来源：评论

学校读者我要写书评

暂无评论

Charging Scheme for Wireless Sensor Network Based on Area Scanning and Energy Detection

Charging Scheme for Wireless Sensor Network Based on Area Sc...

引用

作者： Ye Xiaojie Zau Kaming Electronic and Computer Engineering department Hong Kong University of Science and Technology computer engineering program Hong Kong University of Science and Technology

With the development of wireless sensor networks,the demand for wireless sensors increased *** the same time,there is a problem that the storage of energy is relatively low due to the small size of wireless sensors,which means that it needs to replace when sensors are out of *** will cost huge finance and pollute the ***,many scholars propose using wireless sensors that can recharge instead of primary wireless *** this case,choosing a suitable route to charge wireless sensors has become a significantly critical problem as there is a relationship between energy loss and the charging *** it is unstable or unsuitable to use solar energy and wind energy to charge,charging wireless sensors using drones,proposed by Kulaea ***1,Han Xu,and Bang Wang [1],has become a feasible ***,this solution still has some drawbacks as it only uses energy to charge the point with the lowest energy level by drones without considering the priority,the rest of the power,and the efficiency of time and *** report will use the data about the utilization rate of energy and make some comparisons to improve this solution.

关键词： Wireless Communication Networks Drones Priority Based On Energy Optimized Path Energy Transfer

来源：评论

学校读者我要写书评

暂无评论

Correction: Cross-linguistically consistent semantic and syntactic annotation of child-directed speech

引用

Language Resources and Evaluation 2024年第2期59卷 777-778页

作者： Szubert, Ida Abend, Omri Schneider, Nathan Gibbon, Samuel Mahon, Louis Goldwater, Sharon Steedman, Mark School of Informatics University of Edinburgh Edinburgh UK School of Computer Science and Engineering and the Department of Cognitive Science Hebrew University of Jerusalem Jerusalem Israel Departments of Linguistics and Computer Science Georgetown University Washington USA Centre for Clinical Brain Sciences University of Edinburgh Edinburgh UK

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on Information science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Long short-term memory (LSTM) model-based reinforcement learning for nonlinear mass spring damper system control

引用

Procedia computer science 2023年 216卷 213-220页

作者： Santo Wijaya Yaya Heryadi Yulyani Arifin Wayan Suparta Lukas Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta 55281 Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta 12930 Indonesia

The Neural Networks (NN) model which is incorporated in the control system design has been studied, and the results show better performance than the mathematical model approach. However, some studies consider that only offline NN model learning and does not use the online NN model learning directly on the control system. As a result, the controller's performance decreases due to changes in the system environment from time to time. The Reinforcement Learning (RL) method has been investigated intensively, especially Model-based RL (Mb-RL) to predict system dynamics. It has been investigated and performs well in making the system more robust to environmental changes by enabling online learning. This paper proposes online learning of local dynamics using the Mb-RL method by utilizing Long Short-Term Memory (LSTM) model. We consider Model Predictive Control (MPC) scheme as an agent of the Mb-RL method to control the regulatory trajectory objectives with a random shooting policy to search for the minimum objective function. A nonlinear Mass Spring Damper (NMSD) system with parameter-varying linear inertia is used to demonstrate the effectiveness of the proposed method. The simulation results show that the system can effectively control high-oscillating nonlinear systems with good performance.

关键词： Model-based Reinforcement Learning Random-Shooting Policy LSTM MPC Nonlinear System

来源：评论

学校读者我要写书评

暂无评论

ArT: All-round Thinker for Unsupervised Commonsense Question Answering 29

ArT: All-round Thinker for Unsupervised Commonsense Question...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Wang, Jiawei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like knowledge bases (KBs), which are usually highly resource consuming in construction. Recently pre-trained language models (PLMs) show effectiveness as an alternative for commonsense clues when they play a role of knowledge generator. However, existing work either relies on large-scale in-domain or out-of-domain labeled data, or fails to generate knowledge of high quality in a general way. Motivated by human thinking experience, we propose an approach of All-round Thinker (ArT) by fully taking association during knowledge generating. In detail, our model first focuses on key parts in the given context, and then generates highly related knowledge on such a basis in an association way like human thinking. Besides, for causal reasoning, a reverse thinking mechanism is especially added to further enhance bidirectional inferring between cause and effect. ArT is totally unsupervised and KBs-free. We evaluate it on three commonsense QA benchmarks: COPA, SocialIQA and SCT. On all scales of PLM backbones, ArT shows its brilliant performance and outperforms previous advanced unsupervised models. Our code is available at https://***/WangJW424/ commonsenseQA-ArT. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), V Congreso Internacional en

作者： E. Jiménez-Delgado C. Quesada-López A Méndez-Porras A Lara-Petitdemange J Alfaro-Velasco Graduate Program in Computer Science and Informatics University of Costa Rica Computer Engineering Department Technological Institute of Costa Rica School of Computer Science and Informatics University of Costa Rica

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

In this study, two deep learning models for automatic tattoo detection were analyzed; a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures.

关键词： Training Analytical models Accuracy Computational modeling Transfer learning computer architecture Real-time systems Computational efficiency Convolutional neural networks Tuning

来源：评论

学校读者我要写书评

暂无评论

Semantic-Preserving Adversarial Code Comprehension 29

Semantic-Preserving Adversarial Code Comprehension

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Yiyang Wu, Hongqiu Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the trade-off between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blockchain Scalability: Innovative Solutions for Optimized Performance in Decentralized Networks 7

Enhancing Blockchain Scalability: Innovative Solutions for O...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Srivastav, Akanksha Agarwal, Sheenu Jain, Arpit Tayal, Shikha Jain, Shalu Sharma, Khemraj Tula's institute U.K. Dehradun India Uttarakhand Technical University Department of Electronics and Communication Engineering U.K. Dehradun India Koneru Lakshamaiah Education Foundation Department of Computer Science & Engineering A.P. Vadessahwaram India Tula's Institute Department of Computer Science & Engineering Uttarakhand Dehradun India Maharaja Agrasen Himalayan Garhwal University Uttarakhand Pauri Garhwal India Nanhua University Program in Management Sciences Department: Department of Business Administration Dalin Chiayi62248 Taiwan

ISBN: (纸本)9798350350067

A substantial number of people are presently making use of decentralised cryptocurrencies that are built on blockchain technology. These crypto currencies have garnered a lot of interest over the course of the last few years and are currently being used by their users. Being the first use of blockchain technology, Bitcoin has been a resounding success, which drives further research and improvement in the sector concerned with blockchain technology. Bitcoin was the first usage of blockchain technology. Bitcoin, on the other hand, is susceptible to significant performance issues due to the fact that it has a high transaction latency and a limited throughput. The operations of the cryptocurrency are considerably impacted as a result of these concerns. As a result of the fact that other cryptocurrencies that rely on proof-of-work also carry over its deficiencies, there has been an increase in the number of concerns about the scalability of blockchain technology. The fact that this is the case makes scaling blockchain technology more challenging. All during the course of this investigation, an effort is made to analyse and classify the various scaling mechanisms that are now being used for blockchains. In addition to this, we are going to look at a variety of various approaches and present a list of possible solutions to the issue of scalability that the blockchain technology is now dealing. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Stunting Classification in Toddlers: Implementation and Evaluation of the Decision Tree Algorithm

Stunting Classification in Toddlers: Implementation and Eval...

引用

2024 International Conference on Information Technology and Computing, ICITCOM 2024

作者： Alita, Debby Ahmad, Imam Jafar Rumandan, Rhaishudin Erkamim, Moh Widyasmoro Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Institut Agama Islam Negeri Ambon Islamic Education Management Study Program Ambon Indonesia Universitas Tunas Pembangunan Smart City Information Systems Study Program Surakarta Indonesia Universitas Muhammadiyah Yogyakarta Faculty of Engineering Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350379839

Stunting in toddlers is a chronic nutritional issue that affects the physical and cognitive development of children, with serious long-term consequences such as reduced cognitive function and an increased risk of chronic diseases in adulthood. Therefore, early identification and prevention efforts for stunting are crucial. Classifying toddlers into categories of at-risk for stunting or not is essential to provide timely and appropriate interventions. This study employs data mining techniques using the decision tree algorithm to expedite the stunting detection process and improve the accuracy of nutritional status classification in children. The results indicate that the constructed decision tree model can classify children's nutritional status with an accuracy of 83.26%. The decision tree achieves high accuracy in classifying stunting in toddlers due to its ability to handle complex data and identify significant patterns within the data. © 2024 IEEE.

关键词： Classification Data Mining Decision Tree Stunting

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：