检索结果-内蒙古大学图书馆

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Bandaru, Prudhvi Narayana Anuradha, G. Bora, Himavarshini Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence And Data Science Andra Pradesh India Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science And Engineering Andra Pradesh India

ISBN: (纸本)9798350394474

The health of a plant has remained an indispensable factor for sustainable and enriching crop production to fulfill the Nation's food demands. A degradation in the health of the crop leads to low crop yields. Out of a wide range of factors affecting the health of the crop the most concerning factor remains the plant diseases and pests. More than 50% of India's population is engaged in agricultural practices. In the agricultural sector, India is among the top 3 exporters of Dried Chilli. However, Chilli exports have faced a descent in recent years owing to crop yield loss due to diseases caused by fungi or pests. Anthracnose is the most prevalent disease in Chilli plants. The process of anthracnose disease detection in Chilli crops is a tedious process due to a lack of laboratory facilities and expertise. Such a situation demands for development of an 'automated detection of anthracnose disease in Chilli plant' system which puts the process of early and precise detection of plant disease at ease. computer Vision advancements make it possible for automatic disease detection using visible symptoms on the crop. Keeping this in view, this paper proposes an automated model for the detection of anthracnose in the Chilli plant using a Mobile Net-based convolutional neural network (CNN). Over the last few years researchers such as Boulent et al. stated in their article that the integration of aerial image data and AI-based methods holds promise for offering an effective, high-throughput technique for detecting plant diseases in real-world conditions. Hence the dataset utilized for our model is aerial images using UAV (unnamed aerial vehicle). The proposed system for anthracnose detection in Chilli developed using Mobile Net achieved an accuracy of 99.6%. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference 38

Latent Plan Transformer for Trajectory Abstraction: Planning...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kong, Deqian Xu, Dehong Zhao, Minglu Pang, Bo Xie, Jianwen Lizarraga, Andrew Huang, Yuhao Xie, Sirui Wu, Ying Nian Department of Statistics and Data Science UCLA United States Salesforce Research United States Akool Research United States Xi'an Jiaotong University China Department of Computer Science UCLA United States

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of step-wise rewards as one key technical challenge. We introduce the Latent Plan Transformer (LPT), a novel model that leverages a latent variable to connect a Transformer-based trajectory generator and the final return. LPT can be learned with maximum likelihood estimation on trajectory-return pairs. In learning, posterior sampling of the latent variable naturally integrates sub-trajectories to form a consistent abstraction despite the finite context. At test time, the latent variable is inferred from an expected return before policy execution, realizing the idea of planning as inference. Our experiments demonstrate that LPT can discover improved decisions from suboptimal trajectories, achieving competitive performance across several benchmarks, including Gym-Mujoco, Franka Kitchen, Maze2D, and Connect Four. It exhibits capabilities in nuanced credit assignments, trajectory stitching, and adaptation to environmental contingencies. These results validate that latent variable inference can be a strong alternative to step-wise reward prompting. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ROBUST ADVERSARIAL REINFORCEMENT LEARNING VIA BOUNDED RATIONALITY CURRICULA 12

ROBUST ADVERSARIAL REINFORCEMENT LEARNING VIA BOUNDED RATION...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Reddi, Aryaman Tölle, Maximilian Peters, Jan Chalvatzaki, Georgia D'Eramo, Carlo Department of Computer Science TU Darmstadt Germany Germany Systems AI for Robot Learning Germany Center for Cognitive Science TU Darmstadt Germany Center for Artificial Intelligence and Data Science University of Würzburg Germany

Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement Learning (RL). To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabilizing forces exercised by an adversary in a competitive zero-sum Markov game, whose optimal solution, i.e., rational strategy, corresponds to a Nash equilibrium. However, finding Nash equilibria requires facing complex saddle point optimization problems, which can be prohibitive to solve, especially for high-dimensional control. In this paper, we propose a novel approach for adversarial RL based on entropy regularization to ease the complexity of the saddle point optimization problem. We show that the solution of this entropy-regularized problem corresponds to a Quantal Response Equilibrium (QRE), a generalization of Nash equilibria that accounts for bounded rationality, i.e., agents sometimes play random actions instead of optimal ones. Crucially, the connection between the entropy-regularized objective and QRE enables free modulation of the rationality of the agents by simply tuning the temperature coefficient. We leverage this insight to propose our novel algorithm, Quantal Adversarial RL (QARL), which gradually increases the rationality of the adversary in a curriculum fashion until it is fully rational, easing the complexity of the optimization problem while retaining robustness. We provide extensive evidence of QARL outperforming RARL and recent baselines across several MuJoCo locomotion and navigation problems in overall performance and robustness. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Group Decision-Making Approach Employing Large Language Models to Detect Assertive Groups 23

A Large-Scale Group Decision-Making Approach Employing Large...

引用

23rd International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2024

作者： Carbó-García, Santiago Trillo, José Ramón Tapia, Juan Miguel Pérez, Ignacio Javier Herrera-Viedma, Enrique Cabrerizo, Francisco Javier Andalusian Research Institute in Data Science and Computational Intelligence Department of Computer Science and Artificial Intelligence University of Granada Granada Spain Department of Quantitative Methods for Business and Economics University of Granada Granada Spain

ISBN: (纸本)9781643685380

Large-Scale Group Decision-Making, propelled by the advent of Large Language Models and the imperative for assertiveness in decision-making processes, emerges as a pivotal area of research. This paper navigates through the landscape of Large-Scale Group Decision-Making, delineating its significance across diverse domains, including social networks and e-democracy. Amidst its nascent status, Large-Scale Group Decision-Making encounters formidable challenges, particularly in information management and fostering consensus among a multitude of experts. This paper aims to illuminate the goals and hurdles facing Large-Scale Group Decision-Making approaches through an exhaustive review of contemporary literature and methodologies. By confronting these challenges head-on, Large-Scale Group Decision-Making holds the potential to redefine decision-making paradigms, bolster assertiveness, and elevate collective problem-solving capabilities in an increasingly interconnected world. © 2024 IOS Press. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Real Time Fruit Recognition and Calories Estimation Using CNN and Model Deployment on Amazon's AWS 3

Real Time Fruit Recognition and Calories Estimation Using CN...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Roy, Vikas Kumar Roy, Ganpati Kumar Thakur, Vasu Baliyan, Nikhil Goyal, Nupur Chauhan, Yash Ruprecht Karl University of Heidelberg Department of Data and Computer Science Germany Sharda University Department of Computer Science and Engineering Greater Noida India RIT Roorkee Department of Computer Science and Engineering Uttarakhand Roorkee India Graphic Era Deemed to Be University Department of Mathematics Dehradun India Graphic Era Deemed to Be University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350303360

To carry out vigorous and effective fruit recognition in farming is difficult since there are a number of variations. Lately, various deep-learning approaches presented an outstanding result in numerous visual-guided agricultural usage. These approaches need labelling on training data, which is a tedious work. This study presented a customized five layers CNN architecture and various pretrained deep learning algorithms i.e., VGG-16, DenseNet-121 and InceptionV3are used to recognise the fruit and their calories for helping farmers, patients and peoples to estimate the fruit calories for their health and in farming. The model is trained and validated on integrated datasets which is downloaded from Kaggle and IEEE dataport having 10 classes of different fruits. After extensive experiments, highest accuracy obtained was 99.60% by five layers of CNN and proposed deep learning model has been deployed on Amazon AWS EC2 instance using WinSCP, PuTTY and PuTTYgen. Flask (Python Framework), HTML, CSS and JavaScript is used for website development and connected to its parent website which help users to recognize the fruit and their calories. © 2023 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting Detection Based on High-Pass Filter Attention Network

引用

computer Systems science & Engineering 2022年第12期43卷 1145-1154页

作者： Can Xiao Feng Li Dengyong Zhang Pu Huang Xiangling Ding Victor S.Sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer Science Texas Tech UniversityLubbock79409USA

Image inpainting based on deep learning has been greatly *** original purpose of image inpainting was to repair some broken photos, suchas inpainting artifacts. However, it may also be used for malicious operations,such as destroying evidence. Therefore, detection and localization of imageinpainting operations are essential. Recent research shows that high-pass filteringfull convolutional network (HPFCN) is applied to image inpainting detection andachieves good results. However, those methods did not consider the spatial location and channel information of the feature map. To solve these shortcomings, weintroduce the squeezed excitation blocks (SE) and propose a high-pass filter attention full convolutional network (HPACN). In feature extraction, we apply concurrent spatial and channel attention (scSE) to enhance feature extraction and obtainmore information. Channel attention (cSE) is introduced in upsampling toenhance detection and localization. The experimental results show that the proposed method can achieve improvement on ImageNet.

关键词： Image inpainting detection spatial attention channel attention full convolutional network high-pass filter

来源：评论

学校读者我要写书评

暂无评论

Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition

引用

植物表型组学（英文） 2024年第4期6卷 828-840页

作者： Jianwu Lin Xin Zhang Yongbin Qin Shengxian Yang Xingtian Wen Tomislav Cernava Quirico Migheli Xiaoyulong Chen Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China School of Biological Sciences Faculty of Environmental and Life SciencesUniversity of SouthamptonSouthampton S017 1BJUK Dipartimento di Agraria and NRD-Nucleo di Ricerca sulla Desertificazione Università degli Studi di SassariSassariItaly Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University Guizhou Provincial Science and Technology DepartmentGuiyang 550025China College of Life Sciences Guizhou UniversityGuiyang 550025China

Accurate identification of plant diseases is important for ensuring the safety of agricultural *** neural networks(CNNs)and visual transformers(VTs)can extract effective representations of images and have been widely used for the intelligent recognition of plant disease ***,CNNs have excellent local perception with poor global perception,and VTs have excellent global perception with poor local *** makes it difficult to further improve the performance of both CNNs and VTs on plant disease recognition *** this paper,we propose a local and global feature-aware dual-branch network,named LGNet,for the identification of plant *** specifically,we first design a dual-branch structure based on CNNs and VTs to extract the local and global ***,an adaptive feature fusion(AFF)module is designed to fuse the local and global features,thus driving the model to dynamically perceive the weights of different ***,we design a hierarchical mixed-scale unit-guided feature fusion(HMUFF)module to mine the key information in the features at different levels and fuse the differentiated information among them,thereby enhancing the model's multiscale perception ***,extensive experiments were conducted on the Al Challenger 2018 dataset and the self-collected corn disease(SCD)*** experimental results demonstrate that our proposed LGNet achieves state-of-the-art recognition performance on both the Al Challenger 2018 dataset and the SCD dataset,with accuracies of 88.74％and 99.08％,respectively.

关键词： global plant disease dual-branch feature-aware local networks recognition

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Video Surveillance-Based Framework for Early Plant Disease Detection Using Jetson TX1 and Novel LeafNet-104 Algorithm 4th

A Real-Time Video Surveillance-Based Framework for Early Pla...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Murthy, Jamuna S. Dhanashekar, K. Siddesh, G.M. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India The Ohio State University Columbus United States

ISBN: (纸本)9789819726134

The precise and timely identification of plant diseases plays a pivotal role in safeguarding crop health and optimizing agricultural yields. This paper introduces an innovative framework designed for plant disease detection using video surveillance-based cameras strategically deployed on the Nvidia Jetson TX1 hardware platform within agricultural farms. Leveraging the capabilities of deep learning and the novel neural network architecture known as LeafNet-104, this framework empowers real-time disease detection on plants. Through the deployment of video surveillance cameras, continuous monitoring and early disease detection become achievable, enabling farmers to take prompt corrective measures and mitigate further crop damage. The Nvidia Jetson TX1, with its robust high-performance computing capabilities, enables on-device processing, rendering it ideal for real-time applications. To assess the efficacy of the proposed framework, comprehensive experiments were conducted on an actual agricultural farm. The dataset encompassed various plant species and disease types. Evaluation metrics such as accuracy, precision, recall, and the F1-score were employed to gauge the performance of the LeafNet-104 algorithm. The experimental findings underscored the framework's capacity to accurately and swiftly detect and classify plant diseases in real time, attaining an impressive accuracy rate of 97.5%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Text Classification Using Language Models with Global Label-Wise Attention Mechanisms 4th

Hierarchical Text Classification Using Language Models with...

引用

4th Southern African Conference for Artificial Intelligence Research, SACAIR 2023

作者： du Toit, Jaco Dunaiski, Marcel Department of Mathematical Science Computer Science Division Stellenbosch University Stellenbosch South Africa School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (纸本)9783031490019

Hierarchical text classification (HTC) is a natural language processing task with the objective of categorising text documents into a set of classes from a structured class hierarchy. Recent HTC approaches combine encodings of the class hierarchy with the language understanding capabilities of pre-trained language models (PLMs) to improve classification performance. Furthermore, label-wise attention mechanisms have been shown to improve performance in HTC tasks by placing larger weight on more important parts of the document for each class individually to obtain label-specific representations of the document. However, using label-wise attention mechanisms to fine-tune PLMs for downstream HTC tasks has not been comprehensively investigated in previous work. In this paper, we evaluate the performance of a HTC approach which adds label-wise attention mechanisms, along with a label-wise classification layer, to a PLM which is subsequently fine-tuned on the downstream HTC dataset. We evaluate several existing label-wise attention mechanisms and propose an adaptation to one of the approaches which separates the attention mechanisms for the different levels of the hierarchy. Our proposed approach allows the prediction task at a certain level to leverage the information gained from the predictions performed at all ancestor levels. We compare the different label-wise attention mechanisms on three HTC benchmark datasets and show that our proposed approach generally outperforms the other label-wise attention mechanisms. Furthermore, we show that without using the complex techniques proposed in recent HTC approaches, our relatively simple approach outperforms state-of-the-art approaches on two of the three benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Prevention of Security Attacks at Wireless Network Layers using Machine Learning Techniques 18

Prevention of Security Attacks at Wireless Network Layers us...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Ramisetty, Sowjanya Ghantasala, G. S. Pradeep Gupta, Gaurav Sonia Kg Reddy College of Engineering & Technology Department of Computer Science and Engineering Hyderabad India Alliance University Department of Computer Science and Engineering Bengaluru India Shoolini University Yogananda School of Artificial Intelligence Computers and Data Sciences Solan India

ISBN: (纸本)9789380544519

Wireless sensor networks have great potential for use in flood control, weather forecasting systems, the military, and the healthcare industry. A WSN's nodes are connected to one another and share information. When sending data between nodes, data security is essential. In the world of networking, security is a top priority. data travels along a path when it is transferred from one location to another, increasing the likelihood that a rogue node would enter the network. Detecting malicious nodes within a network presents a formidable challenge, particularly due to external assaults on data packets during their transmission between nodes. Hackers take advantage of weaknesses to manipulate and alter data as it travels from the source node to the destination node. This paper looked at machine learning algorithm-based preventive measures and layer-level security challenges. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Machine Learning Security Security attacks Wireless Sensor Networks

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：