检索结果-内蒙古大学图书馆

Human autonomy teaming-based safety-aware navigation through bio-inspired and graph-based algorithms

Biomimetic Intelligence & Robotics 2024年第4期4卷 76-91页

作者： Timothy Sellers Tingjun Lei Chaomin Luo Zhuming Bi Gene Eu Jan Department of Electrical and Computer Engineering Mississippi State UniversityStarkville 39762USA Department of Civil and Mechanical Engineering Purdue University Fort WayneFort Wayne 46805USA Department of Computer Science Asia UniversityTaichung 413305TaiwanChina

In the field of autonomous robots,achieving complete precision is challenging,underscoring the need for human intervention,particularly in ensuring *** Autonomy Teaming(HAT)is crucial for promoting safe and efficient human-robot collaboration in dynamic indoor *** paper introduces a framework designed to address these precision gaps,enhancing safety and robotic interactions within such *** to our approach is a hybrid graph system that integrates the Generalized Voronoi Diagram(GVD)with spatio-temporal graphs,effectively combining human feedback,environmental factors,and key *** integral component of this system is the improved Node Selection Algorithm(iNSA),which utilizes the revised Grey Wolf Optimization(rGWO)for better adaptability and ***,an obstacle tracking model is employed to provide predictive data,enhancing the efficiency of the *** insights play a critical role,from supplying initial environmental data and determining key waypoints to intervening during unexpected challenges or dynamic environmental *** simulation and comparison tests confirm the reliability and effectiveness of our proposed model,highlighting its unique advantages in the domain of *** comprehensive approach ensures that the system remains robust and responsive to the complexities of real-world applications.

关键词： Human autonomy teaming(HAT) Robot path planning Generalized Voronoi diagram(GVD) Spatio-temporal graphs Bio-inspired algorithms

来源：评论

学校读者我要写书评

暂无评论

Electronic structure prediction of multimillion atom systems through uncertainty quantification enabled transfer learning

引用

npj Computational Materials 2024年第1期10卷 1423-1437页

作者： Shashank Pathrudkar Ponkrshnan Thiagarajan Shivang Agarwal Amartya S.Banerjee Susanta Ghosh Department of Mechanical Engineering-Engineering Mechanics Michigan Technological UniversityHoughtonMIUSA Department of Electrical and Computer Engineering University of CaliforniaLos AngelesCA90095USA Department of Materials Science and Engineering University of CaliforniaLos AngelesCA90095USA Faculty member of the Center for Data Sciences Michigan Technological UniversityHoughtonMIUSA

The ground state electron density—obtainable using Kohn-Sham Density Functional Theory(KSDFT)simulations—contains a wealth of material information,making its prediction via machine learning(ML)models ***,the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation,making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system ***,we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data,while comprehensively sampling systemconfigurations using *** ML models are less reliant on heuristics,and being based on Bayesian neural networks,enable uncertainty *** show that our models incur significantly lower data generation costs while allowing confident—and when verifiable,accurate—predictions for a wide variety of bulk systems well beyond training,including systems with defects,different alloy compositions,and at multi-million-atom ***,such predictions can be carried out using only modest computational resources.

关键词： alloy prediction transfer

来源：评论

学校读者我要写书评

暂无评论

Survey on Ethical Challenges of Implementing AI in Healthcare 7

Survey on Ethical Challenges of Implementing AI in Healthcar...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Lalwani, Nikita Ur Rahim, Muhammad Abdul Basit Anand, Aravind Shaik, Sumair Pasha Moghe, Gauri Shashank Datta, Debarati California State University Long Beach Dept. of Computer Engineering and Computer Science Long Beach United States

ISBN: (纸本)9798350350890

In today's world, Artificial Intelligence (AI) and its usage concerning human tasks have become an integral part of our daily lives. Humans depend upon AI to provide faster and more efficient solutions. In the world of medicine, where every decision made by a doctor, physician, or consultant directly impacts the lives of those being treated or diagnosed, AI is making its way to help efficiently provide such results as the intelligence of a human being. Healthcare systems around the world are now making use of AI to help provide humane solutions using algorithms and Machine Learning (ML). Fallacies or inaccuracies in the arena of healthcare can have horrendous outcomes for the patient on whom the procedure is being carried out. Sometimes, certain ethics could be traded off by the system, such as confidentiality, autonomy, justice, and biased decisions leading to false results and victim blaming, which directs the masses into not trusting AI-related healthcare solutions. This situation can lead to mishaps like 'AI winter,' where the public could start disbelieving the results of AI solutions. This survey review makes an effort to analyze and address these pertinent ethical issues underlying the requirement for algorithmic translucency, concealment, and safeguarding the interests of all those involved. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Soulbound Token Certificate Verification System (SBTCert): Design and Implementation 14

A Soulbound Token Certificate Verification System (SBTCert):...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Tumati, Tarun Vihar Tian, Yun Jiang, Xunfei California State University Northridge Department of Computer Science NorthridgeCA91330 United States California State University Fullerton Department of Computer Science FullertonCA92834 United States

ISBN: (纸本)9798350360134

Certificate authentication is considered to be one of the most tedious and complex processes. Moreover, different types of documents like banking documents, education certificates, and government documents might need a specific type of authentication and verification. For example, the process of verifying the authenticity of education certificates with conclusive evidence can take up to months and consume a lot of human effort. Hence, universities and colleges have no option but to consider the documents submitted by students, even if they might be fabricated. Sometimes an artfully generated forged certificate is almost impossible to detect and can be treated as the original. With the increase of forged documents, the credibility of both the document holder and the issuing authority is jeopardized. On the other hand, when students go through multiple phases of education, they are compelled to submit several documents to secure admission to universities or colleges, or sometimes even more frequently for scholarships and tuition concessions. Therefore, hosting these certificates in a secure and tamper-proof manner on a decentralized blockchain only allows participating parties to read or verify data to reduce errors and make it more transparent. In this paper, we proposed and implemented a Soulbound Token Certification (SBTCert) Verification System, a blockchain-based digital certificate platform, that aims to enhance the verification model without compromising security, authentication, decentralization, and confidentiality. The system provides a secure and reliable platform for universities, students, and staff to manage, issue, and verify educational certificates. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Learning a Diffusion Model Policy from Rewards via Q-Score Matching 41

Learning a Diffusion Model Policy from Rewards via Q-Score M...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Psenka, Michael Escontrela, Alejandro Abbeel, Pieter Ma, Yi Department of Electrical Engineering and Computer Science University of California Berkeley United States

Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous space. However, previous works fail to exploit the score-based structure of diffusion models, and instead utilize a simple behavior cloning term to train the actor, limiting their ability in the actor-critic setting. In this paper, we present a theoretical framework linking the structure of diffusion model policies to a learned Q-function, by linking the structure between the score of the policy to the action gradient of the Q-function. We focus on off-policy reinforcement learning and propose a new policy update method from this theory, which we denote Q-score matching. Notably, this algorithm only needs to differentiate through the denoising model rather than the entire diffusion model evaluation, and converged policies through Q-score matching are implicitly multi-modal and explorative in continuous domains. We conduct experiments in simulated environments to demonstrate the viability of our proposed method and compare to popular baselines. Source code is available from the project website: https://***/qsm. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Softmax Trees for Many-Class Classification 40

Adaptive Softmax Trees for Many-Class Classification

引用

40th Conference on Uncertainty in Artificial Intelligence, UAI 2024

作者： Kairgeldin, Rasul Gabidolla, Magzhan Carreira-Perpiñán, Miguel Á. Department of Computer Science and Engineering University of California MercedCA United States

NLP tasks such as language models or document classification involve classification problems with thousands of classes. In these situations, it is difficult to get high predictive accuracy and the resulting model can be huge in number of parameters and inference time. A recent, successful approach is the softmax tree (ST): a decision tree having sparse hyperplane splits at the decision nodes (which make hard, not soft, decisions) and small softmax classifiers at the leaves. Inference here is very fast because only a small subset of class probabilities need to be computed, yet the model is quite accurate. However, a significant drawback is that it assumes a complete tree, whose size grows exponentially with depth. We propose a new algorithm to train a ST of arbitrary structure. The tree structure itself is learned optimally by interleaving steps that grow the structure with steps that optimize the parameters of the current structure. This makes it possible to learn STs that can grow much deeper but in an irregular way, adapting to the data distribution. The resulting STs improve considerably the predictive accuracy while reducing the model size and inference time even further, as demonstrated in datasets with thousands of classes. In addition, they are interpretable to some extent. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Predicting Microbe-Disease Association Based on Heterogeneous Network and Global Graph Feature Learning

引用

Chinese Journal of Electronics 2022年第2期31卷 345-353页

作者： WANG Yueyue LEI Xiujuan PAN Yi School of Computer Science Shaanxi Normal University Department of Computer Science Georgia State University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences

Numerous microbes inhabit human body,making a vast difference in human health. Hence, discovering associations between microbes and diseases is beneficial to disease prevention and treatment. In this study,we develop a prediction method by learning global graph feature on the heterogeneous network(called HNGFL).Firstly, a heterogeneous network is integrated by known microbe-disease associations and multiple *** on microbe Gaussian interaction profile(GIP) kernel similarity, we consider different effects of these microbes on organs in the human body to further improve microbe similarity. For disease similarity network, we combine GIP kernel similarity, disease semantic similarity and disease-symptom similarity. And then, an embedding algorithm called GraRep is used to learn global structural information for this network. According to vector feature of every node, we utilize support vector machine classifier to calculate the score for each microbe-disease pair. HNGFL achieves a reliable performance in cross validation, outperforming the compared methods. In addition, we carry out case studies of three diseases. Results show that HNGFL can be considered as a reliable method for microbe-disease association prediction.

关键词： microorganisms global graph feature learning support vector machines patient diagnosis global structural information disease semantic similarity disease-symptom similarity HNGFL pattern classification graph theory microbe Gaussian interaction profile kernel similarity bioinformatics support vector machine classifier GraRep diseases learning (artificial intelligence) microbe-disease association prediction heterogeneous network Gaussian processes GIP kernel similarity

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Fraudulent Transaction Detection: SMOTE-Autoencoder Framework

A Hybrid Approach for Fraudulent Transaction Detection: SMOT...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Patankar, Yathartha Sood, Kanika California State University Fullerton Department of Computer Science Fullerton United States

ISBN: (纸本)9798350364910

Fraudulent transactions pose significant challenges across various industries, especially finance, leading to severe financial and reputational damage. Traditional rule-based fraud detection systems struggle to adapt to evolving fraudulent behaviors, often resulting in high false negative and false favorable rates. This paper introduces an advanced approach that combines the Synthetic Minority Oversampling Technique (SMOTE) with autoencoder-based anomaly detection to enhance fraud detection performance. SMOTE addresses class imbalance in transaction datasets, reducing false negatives, while the autoencoder architecture captures latent patterns and anomalies indicative of fraud. The proposed method is evaluated using a dataset processed through principal component analysis (PCA) to simulate real-world transaction environments. The results demonstrate its ability to detect fraud accurately, significantly minimizing false positives and negatives. These findings underscore the superiority of the proposed approach over traditional methods and highlight its potential to enhance fraud detection frameworks and contribute to the advancement of fraud detection techniques. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Activation-Descent Regularization for Input Optimization of ReLU Networks 41

Activation-Descent Regularization for Input Optimization of ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Hongzhan Gao, Sicun Department of Computer Science & Engineering University of California San Diego United States

We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation patterns to propose methods with superior local descent properties. To accomplish this, we convert the discrete space of activation patterns into differentiable representations and propose regularization terms that improve each descent step. Our experiments demonstrate the effectiveness of the proposed input-optimization methods for improving the state-of-the-art in various areas, such as adversarial learning, generative modeling, and reinforcement learning. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimised Data Encryption and Search Efficiency Framework Using Memory Modules for IoT Applications 2

Optimised Data Encryption and Search Efficiency Framework Us...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Gakhar, Suket Kulkarni, Soham Sunil Kumar, Anant Sharma, Vipin Kumar Arora, Sneha Department of Computer Science and Engineering Kurukshetra University Kurukshetra India Department of Computer Science University of California Irvine Irvine United States Department of Computer Science and Engineering Manipal Institute of Technology Manipal India Department of Electronics and Communication Engineering Lovely Professional University Phagwara India

ISBN: (纸本)9798331530389

The proliferation of IoT devices necessitates secure and efficient mechanisms for data encryption and retrieval. This paper presents an optimized framework that leverages AES encryption integrated with memory modules to enhance security and operational efficiency. The proposed system introduces a dynamic key generation mechanism to mitigate key reuse vulnerabilities and incorporates a memory module to achieve reductions in encryption and search execution times by 80% and 79%, respectively, compared to traditional methods. The framework also ensures secure cloud storage of encrypted data and supports privacy-preserving retrieval using trapdoor functions. A Java-based implementation validates the system's scalability, robustness, and platform independence for real-world IoT applications. By addressing key challenges such as data integrity, confidentiality, and low-latency operations, the proposed framework offers a comprehensive solution tailored to the evolving needs of the IoT ecosystem. © 2025 IEEE.

关键词： Data integrity

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：