检索结果-内蒙古大学图书馆

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Dankan Gowda, V. Srinivas, D. Srinivas, Rachakonda Ingole, Balaji Shesharao Jadhav, Priya Dongare Prasad, K.D.V. Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Sr University School of Business Telangana Warangal506371 India Aditya Institute of Technology and Management Department of Computer Science & Engineering Tekkali Andhra Pradesh Srikakulam India GA United States Department of Robotics and Automation Maharashtra Pune412115 India Symbiosis Institute of Business Management Hyderabad India Pune India

ISBN: (纸本)9798350388916

The use of IoT technology in healthcare systems has been adopted in patient monitoring because IoT technology has been adopted rapidly in the systems. This paper discusses on design and implementation of an IoT integrated smart assistive health care system to enhance the precision and speed of patient health assessment. In the proposed system, wearable sensors are used to capture respiratory rate, pulse rate, blood pressure, oxygen saturation, and body temperature with data to be sent to the cloud server as and when it is received. Some of the features are, however, small data transmission delays, high accuracy in the physiological signals and long durations of monitoring due to the low power consumption. The simulations showed that the response time falls below 500ms, and physicians retain up to a 2 % variance to clinical grade devices, which actualized robust and effective patient care. The incorporation of predicting capacities, thus providing ways of early identification of health complications, makes the system applicable in chronic disease treatments and telemedicine. © 2024 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Ying Zhang Xiangyu Zhu Ajian Liu Xun Lin Jun Wan Jing Zhang Zhen Lei State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences School of Computer Science and Engineering Beihang University School of Computer Science and Engineering Macau University of Science and Technology Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model’s parameters but also necessitates the provision of the image’s modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image’s modality to be known. Extensive experiments demonstrate CPL-CLIP’s superiority over existing methods on several flexible-modal FAS benchmarks.

关键词： Training Adaptation models Technological innovation Accuracy Face recognition Benchmark testing Vectors Robustness Data models Compounds

来源：评论

学校读者我要写书评

暂无评论

Xception for Tomato Leaf Disease Detection: Hyperparameter Tuning and Fine-tuning Approaches

Xception for Tomato Leaf Disease Detection: Hyperparameter T...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Yash Maini Sanjay Kumar Singh Pranshu Saxena East Delhi Campus University School of Automation and Robotics Guru Gobind Singh Indraprastha University Delhi Surajmal Vihar India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

Tomato cultivation is essential to world agriculture, affecting food security and economic stability. Tomasto leaf diseases must be detected accurately to maintain crop health and maximize yield. This work improves disease classification by using deep learning models, notably CNN, Xception, DenseNet, and a hyper-tuned Xception model. We used transfer learning and data augmentation to improve model performance on the Kaggle dataset, which contains 10,000 training images and 1,000 validation images from the Plant Village Repository organized into ten groups. The hyper-tuned Xception model achieved the maximum performance by meticulously tweaking hyperparameters such as learning rate, batch size, and network architecture, with an accuracy of 97.23%, precision of 95.73%, recall of 94.40%, and F1-score of 95.06%. These results show a considerable improvement over the CNN, Xception, and DenseNet models. The results highlight the efficiency of sophisticated deep learning algorithms and hyperparameter tweaking in achieving high classification accuracy, making the proposed model a robust tool for practical tomato leaf disease diagnostics.

关键词： Deep learning Training Accuracy Quantum computing Biological system modeling Computational modeling Transfer learning Stability analysis Tuning Diseases

来源：评论

学校读者我要写书评

暂无评论

A Modified Feature Selection Algorithm for Intrusion Detection System Based on Student Psychology-Based Optimization with Explainable AI

A Modified Feature Selection Algorithm for Intrusion Detecti...

引用

computer science and Data Engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Md. Raisul Islam Evan Mohammad Motiur Rahman Sk. Tanzir Mehedi Abdullah Nazib Rafiqul Islam Ziaur Rahman Computer Science and Engineering Mawlana Bhashani Science and Technology University Tangail Bangladesh Information and Communication Technology Mawlana Bhashani Science and Technology University Tangail Bangladesh School of Electrical Engineering and Robotics Queensland University of Technology Brisbane Queensland Australia School of Computing Mathematics and Engineering Charles Sturt University Bathurst Australia School of Computer Science Queensland University of Technology Brisbane Queensland Australia

Intrusion Detection Systems (IDS) play a vital role in safeguarding network security by monitoring and identifying both normal and intrusive activities. However, constructing an effective IDS from extensive datasets poses a significant challenge. The process of feature selection from these datasets is crucial, as it not only enhances accuracy but also reduces the time required to build the model. In this paper, we employ a modified version of the Student Psychology-Based Optimization (SPBO) algorithm to identify the most relevant features set for IDS. Following feature selection, various machine learning algorithms are employed for multi-level classification. To evaluate our approach, we utilize the NLS-KDD dataset. Our proposed algorithm surpasses several state-of-the-art feature selection methods in terms of accuracy, precision, recall, Fl-score, and finally faster convergence. Specif-ically, our proposed bio-inspired SPBO algorithm combined with the Random Forest (RF) algorithm achieves a comparable accuracy rate of 99.81 %. To ensure better comprehensibility, we employ two widely used Explainable Artificial Intelligence (XAI) techniques: SHapley Additive exPlanations (SHAP) and Local In-terpretable Model-Agnostic Explanations (LIME). These methods provide insightful explanations for our model's decisions, further enhancing its interpretability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Stiffness Control of Series Elastic Actuator Manipulators Based on Dynamic System

Adaptive Stiffness Control of Series Elastic Actuator Manipu...

引用

IEEE International Conference on Automation science and Engineering (CASE)

作者： Kunlin Guo Chao Zeng Weiyong Si Ning Wang Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control School of Automation Science and Engineering South China University of Technology Guangzhou China Department of Computer Science University of Liverpool Liverpool UK School of Computer Science and Electronic Engineering University of Essex Colchester Bristol Robotics Laboratory University of the West of England Bristol UK

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In traditional control methods, Series Elastic Actuator (SEA) joint manipulators are limited by their hardware and can only perform simple tasks with low stiffness. To address this issue, we propose a stiffness adjustment control strategy for SEA manipulators based on Dynamic Systems (DS) with good generalization performance. By enhancing the generalization capability of DS in complex tasks and combining posture control, the SEA manipulators can autonomously adjust control gains and postures according to task requirements to achieve higher stiffness at the end-effector. Experimental results involving the activation of air switches with different stiffness levels and installation angles have demonstrated the effectiveness of our proposed method. The results indicate that compared to traditional methods of adjusting the control gain and retraining DS for similar tasks, our approach exhibits superior generalization performance while maintaining end-effector stiffness during interactions.

关键词： Actuators computer aided software engineering Automation Adaptive systems Control systems End effectors Hardware Dynamical systems Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems

arXiv

引用

arXiv 2024年

作者： Sidrane, Chelsea Tumova, Jana The Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden

Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show that the system is generally functioning as desired, but a formal tool like reachability analysis can provide a guarantee of correctness. For linear systems, reachability analysis is straightforward and fast, but as more complex components are added to the control system such as nonlinear dynamics or a neural network controller, reachability analysis may slow down or become overly conservative. To address these challenges, much literature has focused on spatial refinement, e.g., tuning the discretization of the input sets and intermediate reachable sets. However, this paper addresses a different dimension: temporal refinement. The basic idea of temporal refinement is to automatically choose when along the horizon of the reachability problem to execute slow symbolic queries which incur less approximation error versus fast concrete queries which incur more approximation error. Temporal refinement can be combined with other refinement approaches and offers an additional "tuning knob" with which to trade off tractability and tightness in approximate reachable set computation. Here, we introduce an automatic framework for performing temporal refinement and we demonstrate the effectiveness of this technique on computing approximate reachable sets for nonlinear systems with neural network control policies. We demonstrate the calculation of reachable sets of varying approximation error under varying computational budget and show that our algorithm is able to generate approximate reachable sets with a similar amount of error to the baseline approach in 20-70% less time. © 2024, CC BY.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Implementation and Manufacturing of DT Sensor Ecosystem for Real-Time Monitoring of Virtual 3D Printers

引用

SN computer science 2023年第5期4卷 556页

作者： Reddy, K. Shyam Sunder Rajesh, R. Raj, P. Anantha Christu Arya, Namita Bhaskaran, R. Prasad, J. Laxmi Department of Information Technology Vasavi College of Engineering Hyderabad India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India Department of Robotics Engineering Karunya Institute of Technology and Sciences Karunya Nagar Tamil Nadu Coimbatore India Galgotias University Gautam Buddha Nagar Uttar Pradesh Greater Noida India Department of IT PSNA College of Engineering and Technology Tamil Nadu Dindigul India Department of Mechanical Engineering MLR Institute of Technology Telangana Hyderabad India

A full-featured digital representation of all the characteristics of a physical system or object is known as a Digital Twin (DT) and smart manufacturing is made possible in large part by our relationship to the environment. A DT system is simulated in real time and with high accuracy. While, maintaining constant synchronization provides a comprehensive system with physical system management. The use of a DT for a 3D printer is covered in this article which presents the 3D printer’s settings and relevant warnings in real time and uses a lightweight Augmented Reality (AR) model to let users control the basic printer functions that encourage communication between two parties. The tri-model simulates actual physical behavior while operating simultaneously and digital model features. To verify the architecture and method that have been proposed, further investigation is done using a case study of a DT facility using open-source 3D printing. Additionally, future research and conclusions are highlighted to offer illuminating information finally to the two industries and the academic world. We have an economical DT ecosystem, robust and reproducible, thereby allowing the addition of DT capabilities to legacy equipment;creating analytics using historical data that have been collected. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： 3D printing Cost-efficient Digital model DT Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection

arXiv

引用

arXiv 2024年

作者： Song, Ziying Jia, Feiyang Pan, Hongyu Luo, Yadan Jia, Caiyan Zhang, Guoxin Liu, Lin Ji, Yang Yang, Lei Wang, Li School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Lab of Traffic Data Analysis and Mining China Horizon Robotics The University of Queensland Australia Hebei University of Science and Technology China Tsinghua University China Beijing Institute of Technology China

In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods are often compromised by imprecise sensor calibration, resulting in feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach includes the L-Instance module, which directly outputs LiDAR instance features within LiDAR BEV features. Then, we introduce the C-Instance module, which predicts camera instance features through RoI (Region of Interest) pooling on the camera BEV features. We propose the InstanceFusion module, which utilizes contrastive learning to generate similar instance features across heterogeneous modalities. We then use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves state-of-the-art performance, with an mAP of 70.3%, surpassing BEVFusion by 1.8% on the nuScenes validation set. Importantly, our method outperforms BEVFusion by 7.3% under conditions with misalignment noise. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

DCHM: Dynamic Collaboration of Heterogeneous Models Through Isomerism Learning in a Blockchain-Powered Federated Learning Framework 39

DCHM: Dynamic Collaboration of Heterogeneous Models Through ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hao, Zhihao Zhang, Bob Li, Haisheng School of Computer Science and Artificial Intelligence Beijing Key Laboratory of Commercial Data Security Protection and Intelligent Governance Beijing Technology and Business University Beijing China Department of Computer and Information Science Faculty of Science and Technology University of Macau Taipa Macao Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa Macao

ISBN: (纸本)157735897X

Solutions to time-varying problems are crucial for research areas such as predicting changes in human body shape over time. While recurrent neural networks have made significant advancements in this field, their reliance on centralized processing has led to challenges such as model silos and data isolation. In response, distributed AI systems like federated learning have emerged to facilitate dynamic collaboration among models;however, they still depend on central coordinators, which pose risks to system security and efficiency. Moreover, traditional federated learning primarily supports homogeneous models and lacks effective strategies for the interaction of heterogeneous models. To address these limitations, we propose a novel method called Dynamic Collaboration of Heterogeneous Models (DCHM), based on Isomerism Learning, which leverages a consortium blockchain network to enhance model credibility and facilitate coordination among heterogeneous models. Additionally, we introduce a Distributed Hierarchical Aggregation (DHA) algorithm that enables permissioned nodes within each group to aggregate local model results and share them for standardized processing. After several iterative cycles, these nodes perform secondary integration of local results to produce global outcomes. Experimental results demonstrate that DCHM effectively analyzes the temporal variability of body shape changes with high efficiency. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Extended Convergence Result for Behaviour Tree Controllers

arXiv

引用

arXiv 2023年

作者： Sprague, Christopher Iliffe Ögren, Petter The Robotics Perception and Learning Lab. School of Electrical Engineering and Computer Science Royal Institute of Technology KTH StockholmSE-100 44 Sweden

Behavior trees (BTs) are an optimally modular framework to assemble hierarchical hybrid control policies from a set of low-level control policies using a tree structure. Many robotic tasks are naturally decomposed into a hierarchy of control tasks, and modularity is a well-known tool for handling complexity, therefor behavior trees have garnered widespread usage in the robotics community. In this paper, we study the convergence of BTs, in the sense of reaching a desired part of the state space. Earlier results on BT convergence were often tailored to specific families of BTs, created using different design principles. The results of this paper generalize the earlier results and also include new cases of cyclic switching not covered in the literature. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

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：