检索结果-内蒙古大学图书馆

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： L. B. Abhang Ravindra Changala Anudeb Ghosh Prabhakar S Manage Vuda Sreenivasa Rao B Kiran Bala Automation and Robotics Dept Pravara Rural Engineering College Loni Under. SPPU University Pune Department of Information Technology Guru Nanak Institutions Technical Campus Hyderabad India Department of Environmental Studies Siksha - Bhavana Visva-Bharati Santiniketan Department of Electronics and Communication KLE Technological University's MSSCET Belagavi Campus Belagavi Karnataka Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram A.P the Department Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Trichy

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

The study explores the intersection of robotics and neuro-cognitive rehabilitation to offer personalized assistance for individuals with neurological disorders, emphasizing autism spectrum disorder (ASD). The proposed methodology integrates Genetic Algorithms (GAs) to optimize the performance of robotic interventions. The data collection phase involves compiling a comprehensive image dataset capturing facial expressions, gestures, and relevant visual cues associated with ASD. Leveraging robotic platforms designed for therapeutic interventions, feature extraction techniques identify intricate patterns within the data. Advanced algorithms, including GAs, classify the dataset into positive (ASD) and negative (non-ASD) categories. The framework introduces a Diagnosis Matrix for enhanced diagnostic precision, correlating observed robotic interactions with clinical assessments. An Ontology Knowledge base adapts responses based on evolving patient needs. The proposed method surpasses all others, achieving an accuracy of 95.08% and demonstrating superior precision, recall, and F1-score metrics. This indicates the efficacy of the proposed approach in achieving a well-balanced performance with high accuracy and robustness in correctly identifying positive instances. The results underscore the potential of the proposed method for classification tasks, showcasing its superiority in comparison to traditional SVM, CNN, and even a well-established deep learning architecture like VGG-16. The Receiver Operating Characteristic curve validates the model's discriminatory power.

关键词： Support vector machines Neurological diseases Visualization Knowledge based systems Receivers Ontologies Robustness

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cybersecurity: Development and Evaluation of a Secure data Sharing Paradigm Based on Blockchain technology

Enhanced Cybersecurity: Development and Evaluation of a Secu...

引用

Electronics, Communication and Signal Processing (ICECSP), International Conference on

作者： R. Geetha T. Vijayanandh Ananthi S.N. X. Mercilin Raajini V.S. Divya Sundar P Kumari Deepika Department of EEE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of CSE School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering S.A Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science St. Joseph's College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798350364590

ISBN: (纸本)9798350375381

As time goes on and technology gets better, various data-sharing technologies are becoming more and more integrated into many different businesses. Therefore, data exchange and security are crucial for the data's value to be realized. Nevertheless, it is challenging to verify the authenticity of a basic data sharing method in order to detect electronic data usage traces. An further difficulty is the reluctance of data suppliers to provide their data. Employing Blockchain's distributed ledger, smart contract, data trust, and traceability features. For the purpose of facilitating secure access to data, this study introduces a blockchain-based data-sharing architecture that optimizes to circumvent the security and control issues associated with traditional centralized data sharing and administration. In addition, the research evaluates the practicality and safety of the prototype. Furthermore, this paper proposes a Secured data Management Scheme (SDMS) that utilizes blockchain technology to optimize data sharing efficiency. To assess the efficacy of this model, it is cross-validated with the conventional data Privacy Handler (DPH) method. While present centralized security solutions fail to meet security requirements in an IoT setting, blockchain technology provides a decentralized solution. Through the use of a blockchain and a WiFi-enabled network model, this article seeks to offer a secure communication framework for Internet of Things (IoT) devices. According to the results, attitudes and character quirks have a role in how the intelligence community plans to use a blockchain-based data-sharing model for integrating systems. This research demonstrated the viability of using blockchain technology in an intelligence community-centric data-sharing strategy.

关键词： Surveys data privacy Smart contracts Signal processing Blockchains Safety Security Internet of Things Computer crime Business

来源：评论

学校读者我要写书评

暂无评论

Flying Neural Network-Based Optimistic Financial Early Alert System in AI Model

Flying Neural Network-Based Optimistic Financial Early Alert...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Saikrishna Boggavarapu S. Shabbir Ali G. Manikandan R. Mohanraj Devesh Pratap Singh Revathi. R Department of Information Technology University of the Cumberlands Prospect Heights IIIioni United States Department of Electronics & Communication Engineering KL University Guntur India Department of Electronics and Communication Engineering Saveetha School Of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Chennai India Department of Artificial Intelligence and Data Science St.Martin's Engineering College Secunderabad Telangana India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttrakhand India Department of Computer Science Karpagam Academy of Higher Education Coimbatore

An innovative method for early warnings in the area of financial risk management is the Flying Neural Network-based Optimistic Financial Early Alert System (FNN-OFEAS). The FNN-OFEAS outperforms conventional models and rule-based systems because it makes use of the Flying Neural Network architecture and incorporates sentiment analysis. Using a fictitious dataset including past stock prices, financial ratios, economic indicators, and sentiment analysis data, this study details the development, use, and findings of the FNN-OFEAS. The results show that the system is effective at capturing complicated temporal correlations, recognising non-linear patterns, and factoring in market sentiment, all of which contribute to improved risk identification in a timely and accurate manner. Early risk identification, investment decision assistance, regulatory compliance, and financial stability evaluation are just few of the real-world uses for the FNN-OFEAS. Its application is beneficial for financial institutions, investors, regulators, and policymakers since it enhances decision-making, reduces risk, and sheds light on previously hidden information. More work has to be done to improve the model architecture, include other data sources, provide real-time implementations, evaluate the model's resilience, and make it easier to comprehend the results. Addressing financial risks and bolstering financial stability in volatile market settings is one area where the FNN-OFEAS shows promise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond a binary theorizing of prosociality

arXiv

引用

arXiv 2024年

作者： Shen, Chen He, Zhixue Guo, Hao Hu, Shuyue Tanimoto, Jun Shi, Lei Holme, Petter Faculty of Engineering Sciences Kyushu University Fukuoka816-8580 Japan School of Statistics and Mathematics Yunnan University of Finance and Economics Kunming650221 China Department of Computer Science and Technology Tsinghua University Beijing100084 China Shanghai Artificial Intelligence Laboratory Shanghai China Interdisciplinary Graduate School of Engineering Sciences Kyushu University Fukuoka816-8580 Japan Department of Computer Science Aalto University Espoo02150 Finland Center for Computational Social Science Kobe University Kobe650-0017 Japan

A stylized experiment, the public goods game, has taught us the peculiar reproducible fact that humans tend to contribute more to shared resources than expected from economically rational assumptions. There have been two competing explanations for this phenomenon: either contributing to the public good is an innate human trait (the prosocial preference hypothesis) or a transitory effect while learning the game (the confused learner hypothesis). We use large-scale experimental data from a novel experimental design to distinguish between these two hypotheses. By monitoring the effects of zealots (persistently cooperating bots) and varying the participants’ awareness of them, we find a considerably more complex scenario than previously reported. People indeed have a prosocial bias, but not to the degree that they always forego taking action to increase their profit. While our findings end the simplistic theorizing of prosociality in the public goods game, an observed positive, cooperative response to zealots has actionable policy implications. © 2024, CC BY-NC-SA.

关键词： Public policy

来源：评论

学校读者我要写书评

暂无评论

Transformers in medical image analysis

引用

Intelligent Medicine 2023年第1期3卷 59-78页

作者： Kelei He Chen Gan Zhuoyuan Li Islem Rekik Zihao Yin Wen Ji Yang Gao Qian Wang Junfeng Zhang Dinggang Shen Medical School of Nanjing University NanjingJiangsu 210093China National Institute of Healthcare Data Science at Nanjing University NanjingJiangsu 210093China BASIRA Laboratory Faculty of Computer and Informatics EngineeringIstanbul Technical UniversityIstanbulTurkey School of Science and Engineering ComputingUniversity of DundeeUK State Key Laboratory for Novel Software Technology Nanjing UniversityNanjingJiangsu 210093China School of Biomedical Engineering ShanghaiTech UniversityShanghai 201210China Department of Research and Development Shanghai United Imaging Intelligence Co.Ltd.Shanghai 200030China Shanghai Clinical Research and Trial Center Shanghai 201703China

Transformers have dominated the field of natural language processing and have recently made an impact in the area of computer *** the field of medical image analysis,transformers have also been successfully used in to full-stack clinical applications,including image synthesis/reconstruction,registration,segmentation,detection,and *** paper aimed to promote awareness of the applications of transformers in medical image ***,we first provided an overview of the core concepts of the attention mechanism built into transformers and other basic ***,we reviewed various transformer architectures tailored for medical image applications and discuss their *** this review,we investigated key challenges including the use of transformers in different learning paradigms,improving model efficiency,and coupling with other *** hope this review would provide a comprehensive picture of transformers to readers with an interest in medical image analysis.

关键词： Transformer Medical image analysis Deep learning Diagnosis Registration Segmentation Image synthesis Multi-task learning Multi-modal learning Weakly-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

arXiv

引用

arXiv 2022年

作者： Yu, Erxin Du, Lan Jin, Yuan Wei, Zhepei Chang, Yi School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China Faculty of Information Technology Monash University Australia

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks. © 2022, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

arXiv

引用

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimal Experiment Design for Sloppy Systems

引用

IFAC-PapersOnLine 2022年第23期55卷 121-126页

作者： Prem Jagadeesan Karthik Raman Arun K. Tangirala Department of Chemical Engineering Indian Institute of Technology (IIT) Madras Department of Biotechnology Bhupat and Jyoti Mehta School of Biosciences IIT Madras Robert Bosch Centre for Data Science and Artificial Intelligence (RBCDSAI) IIT Madras Centre for Integrative Biology and Systems mEdicine (IBSE) IIT Madras Chennai 600 036 India

In complex dynamical systems, precise and accurate estimation of parameters and quality of predictions depends on the information contained in the experimental data. Choosing experimental schemes that maximize information contained in the data is known as Optimal Experimental Design (OED). Fisher Information Matrix and variance-covariance matrix are the central ideas of OED. However, using OED in a class of models known as sloppy models renders the model less predictive, even though the parameters are estimated with substantial precision. This work introduces a new information gain index as an experiment design criterion in the Bayesian framework. The proposed design criterion is based on what is known as the Bhattacharyya coefficient. Our previous studies show that the information gain index indicates a loss of practical identifiability. Further, it is also an indication of sloppy and stiff parameters. Hence, we extend the information index and its interpretation to joint Gaussian distributions; then, using simulations, we demonstrate that the new experiment design criterion selects experiments that minimize prediction and parameter uncertainty in sloppy models.

关键词： Bayesian Optimal Experiment Design Sloppy Models Bhattacharyya Coefficient

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Multi-scale Contrastive Learning for Gastroenteroscopy Class...

引用

Annual IEEE Symposium on Computer-Based Medical Systems

作者： Dan Li Xuechen Li Zhibin Peng Wenting Chen Linlin Shen Guangyao Wu Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology ShenZhen University Shenzhen China City University of Hong Kong Hong Kong SAR China Shenzhen Institute of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University General Hospital

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kron-based Model-order Reduction of Open Mass-action Kinetics Chemical Reaction Networks

arXiv

引用

arXiv 2022年

作者： Negara, Mohamad Agung Prawira Burohman, Azka Muji Jayawardhana, Bayu The Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen9747AG Netherlands Electrical Engineering Faculty of Engineering University of Jember Jl. Kalimantan Tegalboto No.37 Krajan Timur Sumbersari Kec. Sumbersari Jawa Timur Kabupaten Jember68121 Indonesia The Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Faculty of Science and Engineering University of Groningen Groningen9747AG Netherlands

We propose a Kron-based model-order reduction method for mass-action kinetics chemical reaction networks (CRN) with constant inflow and proportional outflow. The reduced-order models preserve the CRN structure and we establish that the resulting reduced-order models have the same DC-gain or zero-moment as that of the full-order ones. Subsequently, we present the spectrum interlacing property of the Kron-reduced open CRN and propose the use of Gramians-based approach for single-species single-substrate chemical network to get the upper-bound of approximation error and to use it in determining a good set of nodes to be removed systematically. Finally, we evaluate the applicability and efficacy of our results in two well-known biochemical kinetic models: the activated sludge model (ASM) 1 and McKeithan’s T-cell receptor model. © 2022, CC BY.

关键词： Kinetics

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：