检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Yuhan Song, Mofei College of Software Engineering Southeast University Jiangsu Nanjing China Ministry of Education Jiangsu Nanjing China School of Computer Science and Engineering Southeast University Jiangsu Nanjing China

ISBN: (纸本)9798400706868

3D novelty detection plays a crucial role in various real-world applications, especially in safety-critical fields such as autonomous driving and intelligent surveillance systems. However, existing 3D novelty detection methods are constrained by the scarcity of 3D data, which may impede the model's ability to learn adequate representations, thereby impacting detection accuracy. To address this challenge, we propose a Unified Learning Framework (UniL) for facilitating novelty detection. During the pretraining phase, UniL assists the point cloud encoder in learning information from other modalities, aligning visual, textual, and 3D features within the same feature space. Additionally, we introduce a novel Multimodal Supervised Contrastive Loss (MSC Loss) to improve the model's ability to cluster samples from the same category in feature space by leveraging label information during pretraining. Furthermore, we propose a straightforward yet powerful scoring method, Depth Map Error (DME), which assesses the discrepancy between projected depth maps before and after point cloud reconstruction during novelty detection. Extensive experiments conducted on 3DOS have demonstrated the effectiveness of our approach, significantly enhancing the performance of the unsupervised VAE method in 3D novelty detection. Codes are avaliable at https://***/EugeneWon9/UniL. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Automatic SQL Query Generation from Code Switched Natural Language Questions on Electronic Medical Records

Automatic SQL Query Generation from Code Switched Natural La...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Haodi Nie, Jinyin Liu, Zeming Lei, Dong Song, Yuanfeng Shenzhen University College of Computer and Software Engineering Shenzhen China Microsoft Beijing China WeBank Co. Ltd Ai Group Shenzhen China

ISBN: (纸本)9798350386226

Electronic Medical Records (EMRs) meticulously document patient information in relational databases, presenting a challenging task for medical professionals to effectively retrieve this data. Natural Language Question to SQL query (NL2SQL), a critical task in natural language processing (NLP), shows promising performance in addressing this challenge. However, existing medical NL2SQL studies often focus on generating SQL queries from monolingual questions in English. None of them have studied medical NL2SQL for the Chinese *** Chinese EMRs, the questions are primarily in Chinese, while many medical terms, such as drugs and diseases, are commonly described in English. This phenomenon is generally known as code-switching (CS) in the field. Given that underlying systems are typically monolingual, CS has proven to pose significant accuracy challenges, as observed in many tasks such as Automatic Speech Recognition (ASR) and Machine Translation (MT). However, the potential effects on EMRs NL2SQL have not been explored. In this study, we investigate the CS-NL2SQL problem, focusing on CS in the context of Chinese questions for the NL2SQL task on EMRs. To assess the model's performance on this task, we construct the first CS-NL2SQL dataset named CS-MIMICSQL in medical domains. We then explore different CS-NL2SQL architectures along two dimensions: cascaded (translation followed by SQL generation) vs. end-to-end. Our results demonstrate that the proposed end-to-end structure can outperform much better than the cascaded baselines. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Learning Age of Information-Oriented Energy-Efficient Scheduling with Non-Orthogonal Multiple Access 13

Learning Age of Information-Oriented Energy-Efficient Schedu...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Li, Jinhua Cao, Yi Chan, Tse-Tin Pan, Haoyuan Shenzhen University College of Computer Science and Software Engineering Shenzhen China The Education University of Hong Kong Department of Mathematics and Information Technology Hong Kong

ISBN: (纸本)9798350355079

We propose a deep Q-network (DQN)-based user scheduling scheme aimed at low network-wide age of information (AoI) in a non-orthogonal multiple access (NOMA) uplink status update system. In our system, end users can harvest energy from wireless signals received on the radio-frequency band to extend the lifespan of their batteries. Given the battery replacement cost in many practical scenarios, our objective is to design a scheduling scheme to maintain a low AoI while efficiently utilizing energy harvesting and reducing the number of battery replacements. Considering the instantaneous AoI, remaining energy, and channel condition of end users, we model the user scheduling problem as a Markov decision process (MDP), which is solved by DQN. In particular, the choice of transmission power to save energy while enabling a high NOMA decoding rate is incorporated in the design of DQN. Experiments indicate that our DQN-based scheduling scheme achieves a low average AoI of the system with significantly fewer battery replacements compared to various benchmarking schemes. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digital Image Recognition based on Fusion of Multiple Machine Vision Algorithms 6

Handwritten Digital Image Recognition based on Fusion of Mul...

引用

6th International Conference on Information Technologies and Electrical engineering, ICITEE 2023

作者： Lin, Bingrong Yang, Zhi Yang, Minsheng Xie, Xiaole Wang, Xiong Liu, Huiting Lan, Yang College of Computer and Electrical Engineering Huan University of Arts and Science China College of Computer and Electrical Engineering Huan University of Arts and Science Key Laboratory of Distributed Electric Propulsion Vehicle Control Technology China

ISBN: (纸本)9798400708299

Handwritten digit recognition technology is increasingly used in a wide range of fields, but the recognition rate still has room for further improvement. Currently, there are a large number of studies focusing on the use of activation functions to improve the handwritten digit recognition rate, compared with ReLU, Sigmod and other activation functions, this paper chooses to take the Mish activation function to optimise the handwritten digit recognition algorithm, using Pytorch machine learning framework, designed a deep convolutional neural network model based on the MNIST dataset to carry out digit recognition, and to improve the accuracy of model recognition through the learning of image features for digit classification to improve the model recognition accuracy. The experimental results show that the Mish activation function can increase the accuracy of handwritten digit recognition to 99%. Keywords: Handwritten digit recognition, Deep convolutional neural network, Mish activation function, MNIST Dataset, Pytorch © 2023 ACM.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Federated Cooperative Learning for 3D Object Detection in Autonomous Driving

引用

IEEE Internet of Things Journal 2025年第12期12卷 20314-20325页

作者： Chi, Fangyuan Wang, Yixiao Nasiopoulos, Panos Leung, Victor C.M. University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Toronto AI Lab LG Electronics TorontoONM5V 1M3 Canada Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

In the rapidly evolving field of autonomous driving, accurately detecting and understanding dynamic environments remains a challenge. Federated learning (FL) offers a promising approach by integrating decentralized models from multiple Connected Autonomous Vehicles (CAVs) to enhance the performance of Deep Learning (DL) based object detection methods. However, traditional FL faces hurdles such as extensive data synchronization requirements, limited data variance, and high communication costs. This paper introduces a federated cooperative learning framework that addresses these challenges by combining data from both CAVs and Roadside Units (RSUs). The framework combines local cooperative perception with global federated learning through a parameter-efficient federated learning adapter (PEFLA) and a lazy communication (LazyComm) strategy, improving DL-based object detection capabilities across diverse driving scenarios while significantly reducing bandwidth requirements. We also present a novel multi-agent-multi-town dataset V2X-Fed, specifically developed to validate the effectiveness of our approach under various conditions. Notably, our framework retains 97.51% of the detection accuracy achieved by full-model federated learning, while utilizing only 1.4% of the bandwidth typically required, demonstrating substantial improvements over conventional federated learning strategies. This study underscores the potential of our tailored approach to substantially enhance autonomous vehicle technologies with minimal resource utilization. © 2014 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Transfer Learning Evolutionary Algorithm for Dynamic Multiobjective Optimization 13

Multi-Stage Transfer Learning Evolutionary Algorithm for Dyn...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Wang, Qianhui Zhu, Qingling Ji, Junkai College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

ISBN: (纸本)9798350308365

Recently, the application of transfer learning within dynamic multiobjective evolutionary algorithms (DMOEAs) has shown significant potential to solve dynamic multiobjective optimization problems (DMOPs). This approach utilizes the transfer learning technique which reuses information from previous environments to accelerate the search process in the new environment. However, the risk of negative transfer can lead to an erroneous search direction and inefficient use of computational resources. To address this issue, this paper proposes a novel multistage transfer learning DMOEA, named MSTL. The algorithm is designed to enhance the convergence and diversity of the population through the combination of the pre-transfer learning stage and the transfer learning and validation stage when environmental changes occur. In the pre-transfer learning stage, a suitable target domain, source domain, and validation classifier sample sets are generated guided by historical information. In the transfer learning and validation stage, the TrAdaboost technique to transfer knowledge from the target to the source domain, with the results verified by two validation classifiers to mitigate negative transfer. Experimental results demonstrate that our proposed algorithm outperforms four competing algorithms in terms of diversity and convergence on a widely recognized benchmark suite. © 2024 IEEE.

关键词： Dynamic multiobjective optimization evolutionary algorithm transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Approach for Improving TCP Congestion Detection Mechanism in IoTs

A Machine Learning-Based Approach for Improving TCP Congesti...

引用

2022 International Conference on Frontiers of Information Technology, FIT 2022

作者： Arif, Madeha Qamar, Usman Riaz, Amreen College of Electrical and Mechanical Engineering Nust Department of Computer Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350345933

TCP provides suboptimal performance when it comes to wireless or mobile networks. End-to-end connectivity with reliability is a big challenge in IoTs that have restricted memory and processor resources. Mainly, TCP was prepared for only wired networks and its performance will be ruined if we applied it on wireless and ad-hoc networks. IoTs have several issues related to TCP that need to be addressed and have been addressed in past. This paper addresses multiple issues that IoT enables an application to face during data transmissions with mobile nodes. Many researchers have proposed approaches based on certain algorithms and machine-learning techniques that have been summarized in this paper. A new algorithm has also been proposed that focuses on the differentiation of the data loss as congestion loss or random loss in a TCP-driven network transmission using an unsupervised machine learning approach. The proposed algorithm is both memory and computation efficient. It is self-evolving and adaptive as well. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Investigation of Latest CASE Tools for Database engineering: A Systematic Literature Review

Investigation of Latest CASE Tools for Database Engineering:...

引用

2022 International Conference on Frontiers of Information Technology, FIT 2022

作者： Yousaf, Nazish Arif, Madeha Awan, Misbah Mehboob Butt, Wasi Haider Nust College of Electrical and Mechanical Engineering Department of Computer Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350345933

computer Aided software engineering (CASE) tools aid in development of software at various stages. They provide automation of processes to some extent. Database handling requires reliability and integrity with security. Multiple CASE tools help in achieving all these, reduce the cost and time as well. Database implementations are made much easier with implementation of such tools. The purpose of this Systematic Literature Review (SLR) is to investigate various CASE Tools and analyze them categorizing into various domains. This paper has covered 49 researches between years 2015 to 2022, including 18 CASE tools belonging to 12 domains of Database development and maintenance in software development process. The paper highlights various domains in which CASE tools are being used. Moreover, multiple CASE tools for database handling that are frequently being used in the identified domains are also presented. After carrying out a parametric analysis, leading tools in top domains are identified. It is concluded that benefits of CASE tools in terms of database (DB) management automation, time and cost optimization are undeniable. They are the most important and core components of an efficient software development process. © 2022 IEEE.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Fortifying Healthcare Data Security in the Cloud:A Comprehensive Examination of the EPM-KEA Encryption Protocol

引用

computers, Materials & Continua 2024年第5期79卷 3397-3416页

作者： Umi Salma Basha Shashi Kant Gupta Wedad Alawad SeongKi Kim Salil Bharany Computer Science and Information Technology Jazan UniversityJazanSaudi Arabia CSE Eudoxia Research UniversityNew CastleUSA Department of Information Technology College of Computer ScienceQassim UniversityBuraydahSaudi Arabia National Center of Excellence in Software Sangmyung UniversitySeoulKorea Department of Computer Science and Engineering Lovely Professional UniversityPhagwaraPunjabIndia

A new era of data access and management has begun with the use of cloud computing in the healthcare *** the efficiency and scalability that the cloud provides, the security of private patient data is still a majorconcern. Encryption, network security, and adherence to data protection laws are key to ensuring the confidentialityand integrity of healthcare data in the cloud. The computational overhead of encryption technologies could leadto delays in data access and processing rates. To address these challenges, we introduced the Enhanced ParallelMulti-Key Encryption Algorithm (EPM-KEA), aiming to bolster healthcare data security and facilitate the securestorage of critical patient records in the cloud. The data was gathered from two categories Authorization forHospital Admission (AIH) and Authorization for High Complexity *** use Z-score normalization forpreprocessing. The primary goal of implementing encryption techniques is to secure and store massive amountsof data on the cloud. It is feasible that cloud storage alternatives for protecting healthcare data will become morewidely available if security issues can be successfully fixed. As a result of our analysis using specific parametersincluding Execution time (42%), Encryption time (45%), Decryption time (40%), Security level (97%), and Energyconsumption (53%), the system demonstrated favorable performance when compared to the traditional *** suggests that by addressing these security concerns, there is the potential for broader accessibility to cloudstorage solutions for safeguarding healthcare data.

关键词： Cloud computing healthcare data security enhanced parallel multi-key encryption algorithm(EPM-KEA)

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：