检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Nianzu Zeng, Kaipeng Lu, Haotian Wu, Yexin Yuan, Zexin Chen, Danni Jiang, Shengdian Wu, Jiaxiang Wang, Yimin Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Guangdong Institute of Intelligence Science and Technology China SEU-ALLEN Joint Center Institute for Brain and Intelligence Southeast University China XVERSE Technology China

Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders. As acquiring real-world morphology data is expensive, computational approaches for morphology generation have been studied. Traditional methods heavily rely on expert-set rules and parameter tuning, making it difficult to generalize across different types of morphologies. Recently, MorphVAE was introduced as the sole learning-based method, but its generated morphologies lack plausibility, i.e., they do not appear realistic enough and most of the generated samples are topologically invalid. To fill this gap, this paper proposes MorphGrower, which mimicks the neuron natural growth mechanism for generation. Specifically, MorphGrower generates morphologies layer by layer, with each subsequent layer conditioned on the previously generated structure. During each layer generation, MorphGrower utilizes a pair of sibling branches as the basic generation block and generates branch pairs synchronously. This approach ensures topological validity and allows for fine-grained generation, thereby enhancing the realism of the final generated morphologies. Results on four real-world datasets demonstrate that MorphGrower outperforms MorphVAE by a notable margin. Importantly, the electrophysiological response simulation demonstrates the plausibility of our generated samples from a neuroscience perspective. Our code is available at https://***/Thinklab-SJTU/MorphGrower. Copyright 2024 by the author(s)

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction

TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescr...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhou, Xingzhi Dong, Xin Li, Chunhao Bai, Yuning Xu, Yulong Cheung, Ka Chun Se, Simon Song, Xinpeng Zhang, Runshun Zho, Xuezhong Zhang, Nevin L. Hong Kong University of Science and Technology Department of Computer Science and Technology Hong Kong Hong Kong Beijing Jiaotong University Institute of Medical Intelligence Department of Artificial Intelligence Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing100044 China China Academy of Chinese Medical Sciences Guang'anmen Hospital Beijing China Henan University of Chinese Medicine School of Information Technology China Nvidia Nvaitc Hong Kong Hong Kong Nvidia Nvaitc Singapore

ISBN: (纸本)9798350386226

Traditional Chinese medicine (TCM) has relied on specific combinations of herbs in prescriptions to treat various symptoms and signs for thousands of years. Predicting TCM prescriptions poses a fascinating technical challenge with significant practical implications. However, this task faces limitations due to the scarcity of high-quality clinical datasets and the complex relationship between symptoms and herbs. To address these issues, we introduce DigestDS, a novel dataset comprising practical medical records from experienced experts in digestive system diseases. We also propose a method, TCM-FTP (TCM Fine-Tuning Pre-trained), to leverage pre-trained large language models (LLMs) via supervised fine-tuning on DigestDS. Additionally, we enhance computational efficiency using a low-rank adaptation technique. Moreover, TCM-FTP incorporates data augmentation by permuting herbs within prescriptions, exploiting their order-agnostic nature. Impressively, TCM-FTP achieves an F1-score of 0.8031, significantly outperforming previous methods. Furthermore, it demonstrates remarkable accuracy in dosage prediction, achieving a normalized mean square error of 0.0604. In contrast, LLMs without fine-tuning exhibit poor performance. Although LLMs have demonstrated wide-ranging capabilities, our work underscores the necessity of fine-tuning for TCM prescription prediction and presents an effective way to accomplish this. © 2024 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

A Word and Local Feature Aware Network for Chinese Spoken Language Understanding

A Word and Local Feature Aware Network for Chinese Spoken La...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Na Xu Yuwei Yin Yulong Ding Shuang-Hua Yang Department of Computer Science and Engineering Southern University of Science and Technology China TTE Lab Huawei China Department of Computer Science University of Reading UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Chinese SLU suffers from unclear word boundaries. Previous works were either missing the word information or afflicted by word segmentation errors. In this paper, we propose a novel Word and Local feature Aware Network (WLAN), which incorporates both word information and local features for Chinese SLU while avoiding word segmentation. In addition, in our knowledge we first time use the potential slots likely to co-occur with the predicted intent as specific guidance. Experimental results on two Chinese SLU datasets show that our model gets very competitive performance.

关键词： Wireless LAN Particle separators Semantics Neural networks Rendering (computer graphics) Task analysis

来源：评论

学校读者我要写书评

暂无评论

ICSGD-Momentum: SGD Momentum based on Inter-gradient Collision 22

ICSGD-Momentum: SGD Momentum based on Inter-gradient Collisi...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Zou, Weidong Cao, Weipeng Xia, Yuanqing Zhong, Bineng Li, Dachuan School of Automation Beijing Institute of Technology Beijing China Shenzhen China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798331527471

Deep neural networks (DNNs) are widely used in fields like computer vision and natural language processing. A key component of DNN training is the optimizer. SGD-Momentum is popular in many DNN methodologies, such as ResNet and DenseNet, due to its simplicity and effectiveness. However, its slow convergence rate limits its use. To overcome this, we introduce inter-gradient collision into SGD-Momentum, inspired by the elastic collision model in physics. This new method, called ICSGD-Momentum, aims to improve convergence. We provide theoretical proof of convergence and establish a regret bound for ICSGD-Momentum. Experiments on benchmarks including function optimization, CIFAR-100, ImageNet, Penn Treebank, COCO, and YCB-Video show that ICSGD-Momentum accelerates training and enhances the generalization performance of DNNs compared to optimizers like SGD-Momentum, Adam, RAdam, Adabound, and AdaBelief. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Early Stage Design of a mHealth Intervention for Managing Gestational Diabetes Mellitus in Bangladeshi Women 25th

Early Stage Design of a mHealth Intervention for Managing...

引用

25th International Conference on Human-computer Interaction, HCII 2023

作者： Islam, Ashraful Ahmed, Eshtiak Islam, Md Rakibul EMPATHY Lab Center for Computational and Data Sciences Independent University Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh Faculty of Information Technology and Communication Sciences Tampere University Tampere Finland Computer Science Department University of Wisconsin - Eau Claire Eau ClaireWI United States

ISBN: (纸本)9783031492112

Gestational Diabetes Mellitus (GDM) is a rising concern worldwide, particularly in low-resource countries such as Bangladesh, where access to healthcare facilities is limited and awareness of GDM management is inadequate. This work proposes an early-stage design of user interfaces (UIs) for a mobile health (mHealth) intervention using the Bengali language that allows users to input daily measures of blood glucose, weight, and other GDM-related health data. The intervention is designed to provide users with personalized feedback based on their input and the necessary coaching for managing GDM. It also reminds users to take medication if prescribed by their doctors. The app has six key features: blood glucose tracking, food logging, medication reminders, activity tracking, educational resources, and personalized recommendations. Overall, this work provides a valuable contribution to the field of mHealth-based maternal and child health in Bangladesh. However, further research is necessary to evaluate the effectiveness and feasibility of the intervention in real-world scenarios. Such evaluations will provide valuable insights into its potential impact and help refine the design to better serve the needs of GDM patients in Bangladesh. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Automated File labeling for Heterogeneous Files Organization Using Machine Learning

引用

computers, Materials & Continua 2023年第2期74卷 3263-3278页

作者： Sagheer Abbas Syed Ali Raza MAKhan Muhammad Adnan Khan Atta-ur-Rahman Kiran Sultan Amir Mosavi School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Department of Computer Science GC University LahorePakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Software Pattern Recognition and Machine Learning LabGachon UniversitySeongnam13120Korea Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia Department of CIT The Applied CollegeKing Abdulaziz UniversityJeddah31261Saudi Arabia John von Neumann Faculty of Informatics Obuda UniversityBudapest1034Hungary Institute of Information Engineering Automation and MathematicsSlovak University of Technology in BratislavaBratislava81107Slovakia Faculty of Civil Engineering TU-DresdenDresden01062Germany

File labeling techniques have a long history in analyzing the anthological trends in computational *** situation becomes worse in the case of files downloaded into systems from the ***,most users either have to change file names manually or leave a meaningless name of the files,which increases the time to search required files and results in redundancy and duplications of user ***,no significant work is done on automated file labeling during the organization of heterogeneous user files.A few attempts have been made in topic ***,one major drawback of current topic modeling approaches is better *** rely on specific language types and domain similarity of the *** this research,machine learning approaches have been employed to analyze and extract the information from heterogeneous corpus.A different file labeling technique has also been used to get the meaningful and`cohesive topic of the *** results show that the proposed methodology can generate relevant and context-sensitive names for heterogeneous data files and provide additional insight into automated file labeling in operating systems.

关键词： Automated file labeling file organization machine learning topic modeling

来源：评论

学校读者我要写书评

暂无评论

Rice Leaves Disease Diagnose Empowered with Transfer Learning

引用

computer Systems science & Engineering 2022年第9期42卷 1001-1014页

作者： Nouh Sabri Elmitwally Maria Tariq Muhammad Adnan Khan Munir Ahmad Sagheer Abbas Fahad Mazaed Alotaibi College of Computer and Information Sciences Jouf UniversitySakaka72341Saudi Arabia Department of Computer Science Faculty of Computers and Artificial IntelligenceCairo University12613Egypt School of Computer Science National College of Business Administration and EconomicsLahore54000Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnam13557Korea Department of Information System Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia

In the agricultural industry,rice infections have resulted in significant productivity and economic *** infections must be recognized early on to regulate and mitigate the effects of the *** diagnosis of disease severity effects or incidence can preserve production from quantitative and qualitative losses,reduce pesticide use,and boost ta country’s *** the health of a rice plant through its leaves is usually done as a manual ocular *** this manuscript,three rice plant diseases:Bacterial leaf blight,Brown spot,and Leaf smut,were identified using the Alexnet *** research shows that any reduction in rice plants will have a significant beneficial impact on alleviating global food hunger by increasing supply,lowering prices,and reducing production's environmental impact that affects the economy of any *** would be able to get more exact and faster results with this technology,allowing them to administer the most acceptable treatment *** Using Alex Net,the proposed approach achieved a 99.0%accuracy rate for diagnosing rice leaves disease.

关键词： Rice bacterial leaf blight brown spot leaf smut machine learning alexnet

来源：评论

学校读者我要写书评

暂无评论

Resource Management approaches to Internet of Vehicles

引用

Multimedia Tools and Applications 2023年第30期82卷 46811-46844页

作者： Hosseinzadeh, Mehdi Abbasi, Shirin Rahmani, Amir Masoud Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam13120 Korea Republic of Computer Engineering Department Science and Research Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

The Internet of Vehicles (IoV) has become a significant issue in designing smart cities. Many applications and services are provided in IoV for various purposes. They need the resources for the computation and data collection. One of the open issues in IoV is resource management because of resource limitation, resource heterogeneity, and dynamic networks. To our knowledge, no systematic and thorough research in resource management methodologies was conducted in IoV, despite the critical nature of resource management challenges. This paper analyzes the recently published studies on resource management in IoV. Our analysis shows that resource allocation has the most utilization rate of resource management approaches at 30%. The most critical parameter in resource allocation is cost, which includes energy, time, price, and processing capacity. The analytical reports show those cost parameters have the most evaluation in the approaches by 19%. Furthermore, we propose a taxonomy for resource management in IoV and extract challenges and open issues in this field. It can be a start point to suggest new methods for resource management in IoV. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Investigating the Transferability of Evasion Attacks in Network Intrusion Detection Systems Considering Domain-Specific Constraints 25th

Investigating the Transferability of Evasion Attacks in N...

引用

25th International Conference on Information Security Applications, WISA 2024

作者： Mbow, Mariama Roman, Rodrigo Seal, Ayan Wang, Kevin I-Kai Mohanty, Sraban Kumar Sakurai, Kouichi Department of Information Science and Technology Kyushu University Fukuoka Japan Lab University of Malaga Málaga Spain PDPM Indian Institute of Information Technology Design and Manufacturing Jabalpur482005 India Department of Electrical Computer and Software Engineering The University of Auckland Auckland1010 New Zealand

ISBN: (纸本)9789819616237

Recently, adversarial attacks against machine learning-based network intrusion detection systems (NIDS) have gained significant attention in cybersecurity. This study investigates the transferability of these adversarial attacks in the context of NIDS. In addition, most existing studies in adversarial learning against NIDS adopted attack strategies designed originally for image classification without considering network traffic characteristics. However, this is impractical and will fail in the real world as network traffic features are constrained, and ignoring the functional behavior of the network traffic features leads to invalid network traffic flow or produces adversarial samples that do not retain their original functionality (malicious or benign). To address these issues, we propose a constrained momentum iterative fast gradient sign method (C-MIFGSM) to generate adversarial network flows that can successfully evade an ML-based IDS through transfer-based attacks while preserving the functional behavior of the network traffic. Our approach was validated using several target NIDS models built with the NSLKDD benchmark dataset. Experimental results demonstrate that even without knowledge of the target model and under feature constraints, it is possible to generate adversarial network traffic flows that achieve a high evasion attack success rate against NIDS built with deep learning and classical ML models. For example, the attack degraded the detection rate of the DoS traffic drops from 92.35% to 20.27% for the MLP model with an evasion increase rate of 78.04%. © 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

Hybrid Deep Learning based Attack Detection and Classification Model on IoT Environment 5

Hybrid Deep Learning based Attack Detection and Classificati...

引用

5th IEEE International Conference on Electrical, computer and Communication Technologies, ICECCT 2023

作者： Lal, Jaya Dipti Ayoub, Shahnawaz Hakim, Prashant D. Prabagar, S. Dwivedi, Vijay Kumar Tiwari, Mohit Shri G S Institute of Technology and Science Department of Electronics and Communication Engineering Madhya Pradesh Indore India Shri Venkateshwara University Department of Computer Science Uttar PradeshGujrala Amroha India Thakur College of Science and Commerce Department of Information Technology Maharashtra Mumbai India School of Computer Science and Engineering & Information Science Presidency University Networks and IoT Lab Department of Information Science Engineering Karnataka Bengaluru India Vishwavidyalaya Engineering College Department of Mathematics Chhattisgarh Ambikapur India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9781665493604

The Internet of Things (IoT) is becoming an active research area because of its largescale challenges and implementation. But security is the major concern while seeing the dramatic expansion in its applications and size. It is challenging to independently put security mechanism in all the IoT devices and upgrade it according to newer threats. Furthermore, machine learning (ML) techniques could better apply the massive quantity of data produced by IoT devices. Thus, several Deep Learning (DL) based algorithms were introduced for detecting attacks in IoT. Therefore, this study develops a galactic swarm optimization with Deep Learning based Attack Detection and Classification (GSODL-ADC) Model in IoT Environment. The presented GSODL-ADC technique concentrates on the identification of attacks in the IoT environment. The presented GSODL-ADC technique utilizes deep autoencoder (DAE) as a classifier model which properly recognizes the attacks in the IoT environment. Followed by this, the GSO approach is utilized for the optimum hyperparameter adjustments of the DAE model, which leads to enhanced attack detection efficacy. The experimental evaluation of the GSODL-ADC algorithm is tested against benchmark dataset. The obtained experimental values signify the betterment of the GSODL-ADC technique for attack recognition purposes. © 2023 IEEE.

关键词： Internet of things

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：