检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Shijie Ma Fei Zhu Zhun Zhong Xu-Yao Zhang Cheng-Lin Liu MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science University of Nottingham Nottingham UK

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes. Given that knowledge learned from old classes is not fully transferable to new classes, and that novel categories are fully unlabeled, GCD inherently faces intractable problems, including imbalanced classification performance and inconsistent confidence between old and new classes, especially in the low-labeling regime. Hence, some annotations of new classes are deemed necessary. However, labeling new classes is extremely costly. To address this issue, we take the spirit of active learning and propose a new setting called Active Generalized Category Discovery (AGCD). The goal is to improve the performance of GCD by actively selecting a limited amount of valuable samples for labeling from the oracle. To solve this problem, we devise an adaptive sampling strategy, which jointly considers novelty, informativeness and diversity to adaptively select novel samples with proper uncertainty. However, owing to the varied orderings of label indices caused by the clustering of novel classes, the queried labels are not directly applicable to subsequent training. To overcome this issue, we further propose a stable label mapping algorithm that transforms ground truth labels to the label space of the classifier, thereby ensuring consistent training across different active selection stages. Our method achieves state-of-the-art performance on both generic and fine-grained datasets. Our code is available at https://***/mashijie1028/ActiveGCD

关键词： Training computer vision Uncertainty Computational modeling Clustering algorithms Transforms Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Centralized Model-Predictive Control with Human-Driver Interaction for Platooning

arXiv

引用

arXiv 2022年

作者： Kennedy, Justin M. Heinovski, Julian Quevedo, Daniel E. Dressler, Falko The School of Electrical Engineering and Robotics Queensland University of Technology Australia The School of Electrical Engineering and Computer Science TU Berlin Germany

Cooperative adaptive cruise control presents an opportunity to improve road transportation through increase in road capacity and reduction in energy use and accidents. Clever design of control algorithms and communication systems is required to ensure that the vehicle platoon is stable and meets desired safety requirements. In this paper, we propose a centralized model predictive controller for a heterogeneous platoon of vehicles to reach a desired platoon velocity and individual inter-vehicle distances with driver-selected headway time. As a novel concept, we allow for interruption from a human driver in the platoon that temporarily takes control of their vehicle with the assumption that the driver will, at minimum, obey legal velocity limits and the physical performance constraints of their vehicle. The finite horizon cost function of our proposed platoon controller is inspired from the infinite horizon design. To the best of our knowledge, this is the first platoon controller that integrates human-driven vehicles. We illustrate the performance of our proposed design with a numerical study, demonstrating that the safety distance, velocity, and actuation constraints are obeyed. Additionally, in simulation we illustrate a key property of string stability where the impact of a disturbance is reduced through the platoon. Copyright © 2022, The Authors. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Infused Learning for Fine-Grained Plant Disease Recognition

Knowledge-Infused Learning for Fine-Grained Plant Disease Re...

引用

IEEE International Conference on Image Processing

作者： Jamil Ahmad Wail Gueaieb Abdulmotaleb El Saddik Giulia De Masi Fakhri Karray Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada Autonomous Robotics Research Center Technology Innovation Institute Abu Dhabi UAE School of Electrical and Computer Engineering University of Waterloo Canada

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Domain knowledge exists in various forms, including text, ontologies, graphs, images, audio, and videos. In plant disease detection, most works solely utilize images with disease labels, neglecting textual descriptions of visual disease symptoms used by human experts for diagnosis. These text descriptions and sample images aid expert identification of visual symptoms. We propose a novel method that leverages text descriptions and image data by modeling domain-specific knowledge about visual symptoms in leaf images as separate feature channels. Each channel corresponds to specific features whose absence or presence in the image influences model predictions. We introduce a channel attention-guided fusion module for weighting each channel based on the input and corresponding output. The combined feature channels are transformed into a standardized 3-channel input format, which can then be processed by any pre-trained convolutional neural network (CNN) as input for feature extraction and subsequent classification. Furthermore, intermediate activations of the channel attention layer combined with the weights from the fusion layer make model predictions explainable. Experimental results on three publicly available datasets of apple and cucumber leaf diseases demonstrate improvements of up to 5% utilizing various state-of-the-art CNN architectures, indicating the efficacy of incorporating textual disease descriptions using the proposed approach.

关键词： Training Visualization Plant diseases Predictive models Feature extraction Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

arXiv

引用

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

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

Visual Sensor-Based Trajectory Multimodality Prediction via Anchor-Free Query Attention Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Ruiping Cheng, Jun Yu, Junzhi Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore639798 Singapore Peking University College of Engineering Beijing100871 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

As a core component of intelligent surveillance and autonomous driving systems, visual sensor-based trajectory multimodality prediction can significantly improve their perception and decision-making capabilities. Numerous existing trajectory prediction methods are dedicated to enhance prediction performance. However, they still fail to effectively model the complex spatiotemporal interactions among pedestrians and trajectory multimodality. To address the above challenges, this article presents one new trajectory multimodality prediction method via anchor-free query-based attention network, which can more effectively capture spatiotemporal interactions and model trajectory multimodality. First, the initial trajectory proposal module employs target-centered query-based attention to capture complex spatiotemporal interactions and generate multiple trajectory proposals corresponding to the multiple modes of the future trajectory, which allows the model to use different interaction information when decoding trajectory points at different time steps. Second, the novel trajectory refinement module utilizes the learnable trajectory proposals to construct proposal-level interaction mechanisms to refine future trajectories. Experimental results conducted on ETH and UCY datasets demonstrate that the proposed model can provide the state-of-the-art prediction performance. © 1963-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of IoT Enabled Smart Assistive Systems for Healthcare Applications 2

Design and Implementation of IoT Enabled Smart Assistive Sys...

引用

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

Internet of Things Enabled Automatic Meter Reading

Internet of Things Enabled Automatic Meter Reading

引用

Smart Devices (ICSD), International Conference on

作者： Sarthak Malik Shikha Agarwal Srinivas Aluvala Jyoti S. Bali Rachit Garg Mohemmed Hussien School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Ajay Kumar Garg Engineering College Ghaziabad UP India School of Computer Science & Artificial Intelligence SR University Warangal Dept of Robotics and Automation Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune The Islamic University Najaf Iraq

ISBN: (数字)9798350394412

ISBN: (纸本)9798350394429

The world is currently going through a huge transition towards digitalization and sustainability. Sustainability focuses on responsible resource management and environmental preservation, whereas digitalization entails the conversion of many processes and systems into connected, digital forms. Energy management, which aims to offer clean and affordable energy solutions while minimising waste and environmental damage, is one of the important sectors garnering significant attention in this context. Energy management involves the methodical optimisation of energy use in a variety of contexts, including commercial and industrial facilities and residential settings. The energy metre, a tool used to measure electricity, gas, or other energy kinds, is essential to this project. Traditional energy metres are evolving into "smart" energy metres, which may send consumption data periodically or in real-time in addition to measuring energy usage. The usability of energy metres is considerably increased by this feature for both consumers and energy suppliers. Industry 4.0 refers to the fourth industrial revolution, which is characterised by the incorporation of digital technologies into manufacturing and industrial processes, in the broader context of business and technology. Internet of Things (IoT), artificial intelligence (AI), and automation are key technologies advancing this transformation. These technologies are essential for improving productivity, sustainability, and efficiency across sectors. A key component of increasing energy management practises is the Internet of Things (IoT). The internet of things (IoT) is a network of connected gadgets and sensors that can gather and send data. IoT-enabled devices are crucial to the real-time monitoring and management of energy use in the field of energy management. These gadgets are capable of collecting information from many sources, such as energy metres, and transmitting it for analysis and well-informed decision-making. An

关键词： Cloud computing Accuracy Electricity Sensor phenomena and characterization Real-time systems Internet of Things Servers Energy management Sustainable development Monitoring

来源：评论

学校读者我要写书评

暂无评论

Incentivizing Participation in SplitFed Learning: Convergence Analysis and Model Versioning

Incentivizing Participation in SplitFed Learning: Convergenc...

引用

International Conference on Distributed Computing Systems

作者： Pengchao Han Chao Huang Xingyan Shi Jianwei Huang Xin Liu School of Information Engineering Guangdong University of Technology Guangzhou China Department of Computer Science The University of California Davis USA School of Data Science The Chinese University of Hong Kong Shenzhen China School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Shenzhen China

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

In SplitFed learning (SFL), a global model is split into two segments, where distributed clients train the first segment in a federated manner and a main server trains the other. Existing studies focus on algorithm development but ignore the important issue of incentives, without which self-interested clients may be unwilling to participate. We fill this gap by presenting a first incentive study in SFL. One challenge is that the design requires an understanding of how clients' participation affects the model performance. To this end, we provide a first convergence analysis for SFL considering partial client participation to guide the mechanism design. Another challenge is that monetary payment may not be viable for large distributed systems. To this end, we propose a model-versioning mechanism where the main server assigns different versions of models (of different qualities) to clients as incentives. The design is further complicated by clients' multi-dimensional private information. To this end, we design the model-versioning mechanism so that it decouples clients' decisions and admits a weakly dominant strategy at equilibrium. We prove that our mechanism is feasible, effective, and incentive compatible. Experimental results show that our mechanism greatly improves client participation and model accuracy compared to a benchmark.

关键词： Analytical models Accuracy Mechanism design Benchmark testing Numerical models Servers Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification on MRI in Light of Molecular Markers

arXiv

引用

arXiv 2024年

作者： Liu, Jun Yuan, Geng Zeng, Weihao Tang, Hao Zhang, Wenbin Lin, Xue Xu, XiaoLin Huang, Dong Wang, Yanzhi Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Department of Electrical & Computer Engineering College of Engineering Northeastern University BostonMA United States University of Maryland Baltimore CountyMD United States

In research findings, co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas. The ability to predict 1p19q status is critical for treatment planning and patient follow-up. This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection. Although public networks such as RestNet and AlexNet can effectively diagnose brain cancers using transfer learning, the model includes quite a few weights that have nothing to do with medical images. As a result, the diagnostic results are unreliable by the transfer learning model. To deal with the problem of trustworthiness, we create the model from the ground up, rather than depending on a pre-trained model. To enable flexibility, we combined convolution stacking with a dropout and full connect operation, it improved performance by reducing overfitting. During model training, we also supplement the given dataset and inject Gaussian noise. We use three–fold cross-validation to train the best selection model. Comparing InceptionV3, VGG16, and MobileNetV2 fine-tuned with pre-trained models, our model produces better results. On a validation set of 125 codeletion vs. 31 not codeletion images, the proposed network achieves 96.37% percent F1-score, 97.46% percent precision, and 96.34% percent recall when classifying 1p/19q codeletion and not codeletion images. © 2024, CC BY.

关键词： Diseases

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：