检索结果-内蒙古大学图书馆

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

作者： Park, Joohan Youn, Jiseung Ahn, Seyoung Kim, Soohyeong Cho, Sunghyun Hanyang University Computer Science and Engineering Ansan Korea Republic of Hanyang University Computer Science and Engineering Major in Bio-Artificial Intelligence Ansan Korea Republic of

ISBN: (纸本)9798350313277

Cellular networks face a significant problem of high preamble collision rates due to numerous machine-type communication devices (MTCD) attempting to connect. Moreover, addressing the issue of reducing the collision rate while satisfying various types of Quality-of-Service (QoS) has become even more challenging. A Space-Air-Ground Integrated Network (SAGIN) can be a good solution to reduce the preamble collision rate while meeting the QoS of MTCDs. To address this issue, a network selection scheme is proposed in this paper. The network selection scheme consists of a dynamic Access class barring (ACB) value setting phase and a network selection phase. In the dynamic ACB value setting phase, the ACB value is dynamically adjusted based on the strength of the QoS. In the network selection phase, the MTCD selects a network to attempt random access from the space network, air network, or ground network based on the configured ACB value. Simulations are performed to demonstrate the performance of the proposed scheme. The experiments confirm that the proposed scheme achieves a higher random access success rate and a lower average preamble transmission count compared to traditional random access methods. © 2023 IEEE.

关键词： Deadline Machine-type communication devices Quality-of-service Random Access SAGIN

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Generative Model For Causal Effect Estimation in Healthcare 14

Leveraging Deep Generative Model For Causal Effect Estimatio...

引用

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

作者： Kim, Yushin Lee, Sejong Cho, Sunghyun Hanyang University Computer Science and Engineering Major in Bio-Artificial Intelligence Ansan Korea Republic of Hanyang University Computer Science and Engineering Ansan Korea Republic of

ISBN: (纸本)9798350313277

Deep generative models have risen to prominence in diverse domains, including healthcare. In particular, their application in causal effect estimation has the potential to drive significant advancements in personalized medicine. In this study, we conducted an empirical analysis to investigate the impact of selection bias on continuous treatment effect estimation using deep generative models. Our results demonstrate that the presence of selection bias can lead to estimation performance disparities of up to 8 to 9 times. Such significant deviations pose severe risks in medical applications, where accurate treatment effect estimation is crucial for patient outcomes. Therefore, this paper underscores the criticality of addressing these challenges and proposes directions for future research to ensure the robust application of AI in healthcare. © 2023 IEEE.

关键词： Artificial Intelligence Causal Effect Estimation Deep Generative Learning

来源：评论

学校读者我要写书评

暂无评论

An Edge Computing Algorithm Based on Multi-Level Star Sensor Cloud

引用

computer Modeling in engineering & Sciences 2023年第8期136卷 1643-1659页

作者： Siyu Ren Shi Qiu Keyang Cheng The Open University of Chengdu Major in Computer ApplicationChengdu610000China Xi’an Institute of Optics and Precision Mechanics Chinese Academy of Sciences.Xi’an710119China School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang212013China

Star sensors are an important means of autonomous navigation and access to space information for *** have been widely deployed in the aerospace *** satisfy the requirements for high resolution,timeliness,and confidentiality of star images,we propose an edge computing algorithm based on the star sensor *** sensors cooperate with each other to forma sensor cloud,which in turn extends the performance of a single *** research on the data obtained by the star sensor has very important research and application ***,a star point extraction model is proposed based on the fuzzy set model by analyzing the star image composition,which can reduce the amount of data ***,a mappingmodel between content and space is constructed to achieve low-rank image representation and efficient ***,the data collected by the wireless sensor is delivered to the edge server,and a differentmethod is used to achieve privacy *** a small amount of core data is stored in edge servers and local servers,and other data is transmitted to the *** show that the proposed algorithm can effectively reduce the cost of communication and storage,and has strong privacy.

关键词： Star-sensing sensor cloud fuzzy set edge computing mapping

来源：评论

学校读者我要写书评

暂无评论

Augmented Intelligence Assisted Deep Learning Approach for Multi-Class Skin Cancer Classification 1

引用

3rd International Conference on Novel and Intelligent Digital Systems, NiDS 2023

作者： Batool, Amreen Byun, Yung-Cheol Department of Computer Engineering Major of Electronic Engineering Institute of Information Science Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (数字)9783031440977

ISBN: (纸本)9783031440960

Skin cancer is the most common type of cancer in the world. An important aspect of skin cancer diagnosis is detecting lesions as early as possible. Over the past five years, deep learning-based techniques have performed better on image classification tasks. There still needs to be a compromise in analysis accuracy due to image occlusions and imbalanced datasets. The main drawbacks of image occlusion and imbalanced datasets are to need for help to produce generalized models, increased computational overhead, loss of information of occluded regions, etc. Therefore, a robust approach is required to tackle the aforementioned challenges to produce a generalized model for lesion cancer cell classification. This study proposes an augmented-assisted deep learning approach based on DenseNet for multi-class lesion cancer cell classification and detection. In this study, an open-source dataset of lesion cancer cell images is used. Furthermore, data augmentation generates synthetic images to balance the class distribution to avoid over-fitting and poor generalization-related issues. In addition, a robust multi-class classifier based on a DenseNet121 architecture is developed to classify seven skin lesion classes that resize all images to the same size. According to the experimental results, our proposed multi-class classifier achieved an accuracy of 93% and 90.17% using training and validation images set. Similarly, our proposed classifier achieved an accuracy of 90% using a testing (unseen) image set. In the case of skin lesion identification, this research has a positive impact on supporting dramatists in the clinic with more accurate decisions. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Tourist Attraction Recommendation Using a Word2Vec-Based Approach Enhanced by XGBoost Classifier 14th

Tourist Attraction Recommendation Using a Word2Vec-Based App...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Ko, Jiyoung Kim, Jisoo Byun, Yung-Cheol Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Collage of Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

Recently, online recommendation systems that recommend travel products or services have been widely used. Many companies are working to develop effective recommendation systems to improve customer interaction and gain competitiveness. This paper is a study on the development of a tourist attraction recommendation system in Jeju Island using embedding based on the Word2Vec algorithm. In this study, we propose a method to predict the place to be visited next by considering the places the traveler has visited as words and the entire itinerary as a sentence. We propose a study that recommends nearby tourist destinations by applying the Word2Vec algorithm to tourists’ travel data and then learning the pattern by Xgboost Classifier model. Based on the results predicted through a machine learning model, nearby vectors are found and the five optimal tourist destinations are recommended. It was confirmed that the proposed method has higher accuracy when the mouth bedding vector has a 4-dimensional dimension than when it is 1-dimensional. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Road Situation Classification Using Long-Term Recurrent Convolutional Network 14th

Efficient Road Situation Classification Using Long-Term Recu...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Dofitas, Cyreneo Gil, Joon-Min Byun, Yung-Cheol Department of Electronic Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

The state of a road encompasses various factors, including the presence of vehicles and pedestrians. On-the-road surveillance cameras are crucial in tracking information regarding pedestrians, moving vehicles, and objects in the road vicinity. With the increasing adoption of deep learning models in vehicle monitoring systems, there is a focus on identifying and classifying conditions relevant to driving comfort and road safety. This study addresses the issue of an imbalanced dataset. However, the scarcity of publicly available datasets and efficient detection techniques poses challenges in accurately classifying road situations. In this paper, we propose a long-term recurrent convolutional network (LRCN) comprised of two groups integrated with convolutional neural networks (CNN) and long short-term memory (LSTM) networks with multiple layers of LSTM blocks for road situation detection in videos. Our model for road situation classification achieves an accuracy of 71% when using the original dataset captured from the camera. However, employing data augmentation to balance the dataset resulted in an increased accuracy of 90%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Group-based Random Access with Age of Information Minimization in 6G umMTC 14

Group-based Random Access with Age of Information Minimizati...

引用

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

作者： Youn, Jiseung Park, Joohan Ahn, Seyoung Kim, Soohyeong Cho, Sunghyun Major in Bio-Artificial Intelligence Hanyang University Dept. of Computer Science & Engineering Ansan Korea Republic of Hanyang University Dept. of Computer Science & Engineering Ansan Korea Republic of

ISBN: (纸本)9798350313277

6G has defined ultra-massive machine type communication (umMTC) as a key scenario in response to the advancement of IoT technologies. The presence of a large number of machine-type communication devices (MTCDs) in umMTC calls for the research of efficient random access (RA) schemes. To address the problem of high collision rates in dense networks, a group-based RA approach has been introduced. In the group-based RA approach, we design an optimal congestion control method to minimize the Age of Information (AoI). Since AoI and collision rate are in a trade-off relationship, we aim to maximize the successful RA rate by iteratively searching for the optimal congestion control factor. Simulation results represent that the proposed scheme achieves a 10% collision rate and an average AoI of less than 100 age, enabling the 90% successful RA rate in 100,000 MTCDs deployment scenario. © 2023 IEEE.

关键词： AoI Group-based random access umMTC

来源：评论

学校读者我要写书评

暂无评论

A study on the knowledge-based information system for evacuation situation awareness in the case of fire 12

A study on the knowledge-based information system for evacua...

引用

2023 12th International Conference on Information and Electronics engineering, ICIEE 2023

作者： Kim, Yong Jun Byun, Yung-Cheol Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Jeju National University Institute of Information Science & Technology Jeju63243 Korea Republic of

This study is on designing a knowledge-based information system for evacuation situation awareness in case of fire. First, in the design of this system, various progress of urban fires was stored and learned in the database so that multiple fire situations could be recognized. In addition, it is to be actively applied to fire disaster prevention through the knowledge-based Fire Dynamics Simulator information system so that it can be actively used for situational information of evacuees and property protection. Moreover, this system is designed to reduce damage to human life and property in the event of a fire in a building, etc. For this purpose, fire extinguishment can be predicted based on building information such as structure and building materials. Natural disasters leading to significant fires can be prevented by predicting fire evolution between buildings. Damage to human life and property due to fire can be contained. This system is a knowledge-based information system that optimizes ubiquitous technologies. It can respond to minimize damage by periodically recognizing the situation of evacuees in case of fire and notifying the central control center of the problem. © Published under licence by IOP Publishing Ltd.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Metaphor Detection with Additional Auxiliary Context 16

Metaphor Detection with Additional Auxiliary Context

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Hayashi, Takuya Sasaki, Minoru Graduate School of Sci. and Eng. Ibaraki Univ. Major in Computer and Information Sciences Hitachi Japan College of Engineering Ibaraki Univ. Department of Computer and Information Sciences Hitachi Japan

ISBN: (纸本)9798350377903

'Metaphor detection' refers to the detection of figurative expressions and metaphors in sentences and text data. Metaphor expressions are expressions that cannot be interpreted literally and their meaning needs to be inferred. Traditionally, linguistic features such as word classes have been used as input for specific machine learning models to infer Metaphor content. In previous studies, detection has been performed on a single input sentence, which has the problem that the context before and after the sentence cannot be properly captured. Therefore, in order to perform effective Metaphor detection for sentences with little context information, this study proposes a method to generate and add sentences that complement the context using ChatGPT. Using this method, we compared the predictions made by the Metaphor detection model for both the dataset to which the complementary sentences were added and the original dataset. The results show that adding supplementary context to the dataset improves the accuracy of Metaphor detection. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Exploration of Diffusion-Based Test Case Generation of Autonomous Driving Systems

Exploration of Diffusion-Based Test Case Generation of Auton...

引用

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

作者： Lee, Joonwoo Uk-Jin Lee, Scott Hanyang University Major in Bio-Artificial Intelligence Department of Applied Artificial Intelligence Ansan Korea Republic of Hanyang University Department of Computer Science and Engineering Ansan Korea Republic of

ISBN: (纸本)9798331510756

Autonomous driving systems demand extensive testing to guarantee safety and reliability. However, real-world testing is often costly and limited in variety. This paper investigates the use of diffusion models to generate synthetic driving images as a means of augmenting test datasets for autonomous driving systems. Leveraging their capability to produce diverse and highly realistic images, diffusion models can simulate various driving conditions, including rare or challenging scenarios that are difficult to replicate. By incorporating these synthetic images into the testing pipeline, self-driving systems can be assessed across a wider range of conditions, enhancing their robustness and safety. © 2025 IEEE.

关键词： Autonomous Driving Diffusion Test Generation

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：