检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： You, Yuning Cao, Yue Chen, Tianlong Wang, Zhangyang Shen, Yang Department of Electrical and Computer Engineering Texas A&M University United States Department of Computer Science and Engineering Texas A&M University United States Department of Electrical and Computer Engineering University of Texas Austin United States

Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions. Meanwhile, another relevant but very different question remains yet open: how to model and quantify the uncertainty of an optimization algorithm (a.k.a., optimizer) itself? To close such a gap, the prerequisite is to consider the optimizers as sampled from a distribution, rather than a few prefabricated and fixed update rules. We first take the novel angle to consider the algorithmic space of optimizers, and provide definitions for the optimizer prior and likelihood, that intrinsically determine the posterior and therefore uncertainty. We then leverage the recent advance of learning to optimize (L2O) for the space parameterization, with the end-to-end training pipeline built via variational inference, referred to as uncertainty-aware L2O (UA-L2O). Our study represents the first effort to recognize and quantify the uncertainty of the optimization algorithm. The extensive numerical results show that, UA-L2O achieves superior uncertainty calibration with accurate confidence estimation and tight confidence intervals, suggesting the improved posterior estimation thanks to considering optimizer uncertainty. Intriguingly, UA-L2O even improves optimization performances for two out of three test functions, the loss function in data privacy attack, and four of five cases of the energy function in protein docking. Our codes are released at https://***/Shen-Lab/Bayesian-L2O. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

DMSS:An Attention-Based Deep Learning Model for High-Quality Mass Spectrometry Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 577-589页

作者： Yihui Ren Yu Wang Wenkai Han Yikang Huang Xiaoyang Hou Chunming Zhang Dongbo Bu Xin Gao Shiwei Sun Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190Chinaand with University of Chinese Academy of SciencesBeijing 100049China Syneron Technology Guangzhou 510000China College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China Computer Science Program ComputerElectrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia Insitute of Computing Technology Chinese Academy of SciencesBeijing 100190China with Western Institute of Computing Technology Chongqing 400000China

Accurate prediction of peptide spectra is crucial for improving the efficiency and reliability of proteomic analysis,as well as for gaining insight into various biological *** this study,we introduce Deep MS Simulator(DMSS),a novel attention-based model tailored for forecasting theoretical spectra in mass *** has undergone rigorous validation through a series of experiments,consistently demonstrating superior performance compared to current methods in forecasting theoretical *** superior ability of DMSS to distinguish extremely similar peptides highlights the potential application of incorporating our predicted intensity information into mass spectrometry search engines to enhance the accuracy of protein *** findings contribute to the advancement of proteomics analysis and highlight the potential of the DMSS as a valuable tool in the field.

关键词： mass spectrometry proteomics machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

LSTM Based Neural Network Model for Anomaly Event Detection in Care-Independent Smart Homes

引用

computer Modeling in engineering & sciences 2024年第9期140卷 2689-2706页

作者： Brij B.Gupta Akshat Gaurav Razaz Waheeb Attar Varsha Arya Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413TaiwanChina Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Computer Engineering Ronin InstituteMontclairNJ 07043USA Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Business Administration Asia UniversityTaichung413TaiwanChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia School of Science and Technology Hong Kong Metropolitan University(HKMU)Hong KongChina

This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall *** balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification *** proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly *** model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and *** study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.

关键词： LSTM neural networks anomaly detection smart home health-care elderly fall prevention

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Malware Detection System 3

Machine Learning Based Malware Detection System

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Varshney, Gunjan Varshney, Sudeep Suman, Amrit Chouhan, Kuldeep Suman, Preetam Jss Academy of Technical Education Department of Electrical Engineering Uttar Pradesh Noida India Sharda School of Engineering & Technology Computer Science and Engineering Uttar Pradesh Greater Noida India Vit University Computer Science and Engineering Madhya Pradesh Bhopal India

ISBN: (纸本)9798350330724

As today's time is more dependent towards the internet, there are various types of malwares are being developed on daily basis, as per report presented by Kaspersky around 560,000 instances of malware created daily. Malware are being developed in such a way that they can replicate and change their signature based on the types of detection system present in organization. Due to urge of variety of malwares it is enables security researchers to shift towards use of Machine Learning for better protection towards variety of security systems. Use of machine learning makes the whole thing more productive and responsive. In this research we have suggested a system that detects diversity of viruses depending on their types response to the system, for the initial phase we have taken a Dataset of Malwares which contains 96,724 malware samples and 41,323 binaries, executable and dynamic link libraries which are legit files. Also we have contrasted the different types of machine learning Techniques which can be used for creating these types of system. © 2023 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Learning orientation detection system and its application to RGB images

Learning orientation detection system and its application to...

引用

2024 International Conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Chen, Tianqi Qiu, Zhiyu Hua, Yuxiao Todo, Yuki Tang, Zheng Division of Electrical Engineering and Computer Science Graduate School of Natural Science & Technology Kanazawa University Ishikawa Kanazawa920-1152 Japan Faculty of Electrical Information and Communication Engineering Kanazawa University Ishikawa Kanazawa920-1192 Japan Faculty of Engineering University of Toyama Toyama930-8555 Japan

ISBN: (纸本)9781510685437

Our previous research showed that emulating dendritic neuron structure effectively addresses orientation detection challenges in learning tasks, reducing both learning time and costs compared to alternative neural network approaches. Our simulation model incorporates an On-Off Response mechanism in bipolar cells (BCs) and horizontal cells (HCs) for processing grayscale input images. To overcome limitations with single-channel input, we introduce color-selective cells. By integrating these cells, we enhance and select outputs of local orientation detection dendritic neurons, generating specific feature maps. These feature maps are generated using a biologically-inspired model that mimics the mechanism of color-selective cells. Additionally, global neurons are used to capture overall image features by aggregating outputs from local dendritic neurons. Our system utilizes backpropagation to update parameters of local orientation detection dendritic neurons. Furthermore, we integrate a learnable orientation detection neural network after the dendritic neuron stage. © 2024 SPIE.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Cyber Twin Technology for AI-Driven Real-Time Software Security in IoT Ecosystems 4

Cyber Twin Technology for AI-Driven Real-Time Software Secur...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Sunkara, Krishna Chaitanya Dhasmana, Gulshan Ravi, K.S. Nayana Yadav, M. Desai, Ishan Shankar, Rajmani Oracle Cloud Engineering Data Center NC United States Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India Vidyavardhaka College of Engineering Department of Mechanical Engineering Mysuru India Aj Institute of Engineering and Technology Department of Computer Science and Engineering Mangalore India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department of Electrical Engineering Gujarat India Faculty of Law Pune India

ISBN: (纸本)9798350352931

As Internet of Things (IoT) ecosystems grow more complex, ensuring real-time security has become a major challenge. Traditional security approaches are insufficient for handling dynamic and interconnected IoT networks, which are increasingly targeted by sophisticated cyber-attacks. To address these issues, new methodologies that combine real-time monitoring and adaptive security mechanisms are needed. Cyber Twin technology, an innovative extension of digital twin technology, presents a promising solution by creating AI-driven digital replicas of IoT devices and software systems for continuous security monitoring and management. This paper introduces a Cyber Twin Technology Framework for AI-driven real-time software security in IoT ecosystems. The framework employs advanced AI models, including Convolutional Neural Networks (CNNs) for anomaly detection and Generative Adversarial Networks (GANs) for synthetic data generation to simulate potential attack scenarios. A dynamic reinforcement learning module is integrated to optimize threat response strategies based on evolving threat patterns. By creating real-time digital replicas of IoT components, the Cyber Twin framework continuously monitors device behaviors, identifies anomalies, and autonomously initiates mitigation actions. The system is evaluated in a simulated IoT environment with over 500 interconnected devices. Experimental results demonstrate that the Cyber Twin framework achieved a 99.2% detection accuracy in identifying cyber threats, with a false positive rate of 1.3%. The dynamic response module reduced incident response time by 35% compared to traditional methods, enhancing the system's ability to neutralize potential threats in real-time. The use of GAN-based synthetic data also enabled proactive defense strategies, reducing attack success rates by 40% during testing. The Cyber Twin Technology Framework provides a robust solution for real-time software security in complex IoT ecosystems. By leveraging A

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Approach for Arabic Visual Speech Recognition

引用

computers, Materials & Continua 2022年第4期71卷 85-108页

作者： Nadia H.Alsulami Amani T.Jamal Lamiaa A.Elrefaei Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt

Lip-reading technologies are rapidly progressing following the breakthrough of deep *** plays a vital role in its many applications,such as:human-machine communication practices or security *** this paper,we propose to develop an effective lip-reading recognition model for Arabic visual speech recognition by implementing deep learning *** Arabic visual datasets that have been collected contains 2400 records of Arabic digits and 960 records of Arabic phrases from 24 native *** primary purpose is to provide a high-performance model in terms of enhancing the preprocessing ***,we extract keyframes from our ***,we produce a Concatenated Frame Images(CFIs)that represent the utterance sequence in one single ***,the VGG-19 is employed for visual features extraction in our proposed *** have examined different keyframes:10,15,and 20 for comparing two types of approaches in the proposed model:(1)the VGG-19 base model and(2)VGG-19 base model with batch *** results show that the second approach achieves greater accuracy:94%for digit recognition,97%for phrase recognition,and 93%for digits and phrases recognition in the test ***,our proposed model is superior to models based on CFIs input.

关键词： Convolutional neural network deep learning lip reading transfer learning visual speech recognition

来源：评论

学校读者我要写书评

暂无评论

Collaborative Computing in Non-Terrestrial Networks: A Multi-Time-Scale Deep Reinforcement Learning Approach

引用

IEEE Transactions on Wireless Communications 2024年第5期23卷 4932-4949页

作者： Cao, Yang Lien, Shao-Yu Liang, Ying-Chang Niyato, Dusit Shen, Xuemin Southwest Jiaotong University School of Information Science and Technology Chengdu611756 China Institute of Intelligent Systems National Yang Ming Chiao Tung University Tainan City711 Taiwan Chengdu611731 China Nanyang Technological University School of Computer Science and Engineering Jurong West639798 Singapore University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Constructing earth-fixed cells with low-earth orbit (LEO) satellites in non-terrestrial networks (NTNs) has been the most promising paradigm to enable global coverage. The limited computing capabilities on LEO satellites however render tackling resource optimization within a short duration a critical challenge. Although the sufficient computing capabilities of the ground infrastructures can be utilized to assist the LEO satellite, different time-scale control cycles and coupling decisions between the space- and ground-segments still obstruct the joint optimization design for computing agents at different segments. To address the above challenges, in this paper, a multi-time-scale deep reinforcement learning (DRL) scheme is developed for achieving the radio resource optimization in NTNs, in which the LEO satellite and user equipment (UE) collaborate with each other to perform individual decision-making tasks with different control cycles. Specifically, the UE updates its policy toward improving value functions of both the satellite and UE, while the LEO satellite only performs finite-step rollout for decision-makings based on the reference decision trajectory provided by the UE. Most importantly, rigorous analysis to guarantee the performance convergence of the proposed scheme is provided. Comprehensive simulations are conducted to justify the effectiveness of the proposed scheme in balancing the transmission performance and computational complexity. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Cryptographic Protocols for Securing Internet of Things (IoT) 15

Cryptographic Protocols for Securing Internet of Things (IoT...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Manimekala, B. Aravind, T. Sounderrajan, T. Rajakumareswaran, V. Kondreddi, Krishnaveni Mohanambal, K. Christ University Department of Computer Science Yeshwanthpur Bengaluru India Vel TecRangarajanDr.Sagunthala R&d Institute of Science and Technology Department of Cse School of Computing India Erode Sengunthar Engineering College Department of Ai and Data Science Tamil Nadu Thuduppathi India Erode Sengunthar Engineering College Department of Computer Science and Design Tamil Nadu Thuduppathi India Chaitanya Bharathi Institute of Technology Electrical and Electronics Engineering Ranga Reddy Telangana Gandipet500075 India Bannariamman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India

ISBN: (纸本)9798350370249

Cryptographic protocols are used to relax the ever-developing quantity of linked gadgets that make up the net of things (IoT). Those cryptographic protocols have been designed to make certain that IoT tool traffic stays cozy and personal, even while nevertheless allowing tool-to-device and cloud-to-tool communications. Examples of these protocols consist of TLS/SSL, PGP/GPG, IPsec, SSL VPN, and AES encryption. Every one of these protocols enables authentication, message integrity, and confidentiality via encryption and key trade. Moreover, a lot of these protocols are carried out in the form of diverse hardware and software answers, such as smart playing cards and gateways, to make certain that IoT traffic is secured. With the appropriate implementation of those cryptographic protocols, establishments can ensure that their IoT facts are blanketed and securely transmitted. © 2024 IEEE.

关键词： Authentication Communications Cryptographic EverDeveloping Gadgets Protocols

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Detection Using the EEG Signal Empirical Mode Decomposition and Machine Learning

Epileptic Seizure Detection Using the EEG Signal Empirical M...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Nassir, Jana Alasabi, Majeda Qaisar, Saeed Mian Khan, Muzammil Effat University Computer Science Department Jeddah22332 Saudi Arabia Effat University Electrical and Computer Engineering Department Jeddah22332 Saudi Arabia Cesi Engineering School Lineact Laboratory Villeurbanne69100 France University of Swat Department of Computer and Software Technology Swat Pakistan

ISBN: (纸本)9798350347050

Epileptic seizures affect millions of people worldwide. Medical treatments exist to help lessen the severity of the damage caused by these seizures. However, people with epilepsy still struggle with unexpected seizures. People who experience epileptic seizures have Electroencephalogram (EEG) signals that show different features in comparison to a healthy brain. In this study, EEG signals are studied to detect the seizures. The incoming signals are denoised by using linear phase filters. In next step these are divided in fix-length segments. Then, each segment is broken down using the Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs). For an automatic identification of EEG signals, features are extracted from the collected IMFs and then processed using machine learning techniques. A dataset on epilepsy that is available to the public is used for evaluation. To determine which is the best predictor for the under-consideration dataset, four different classification methods are performed and the results are examined. The system achieves a classification accuracy of 96.70%. © 2023 IEEE.

关键词： Empirical mode decomposition

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：