检索结果-内蒙古大学图书馆

AI-Powered Digital Twin for Sustainable Agriculture and Greenhouse Gas Reduction 21

AI-Powered Digital Twin for Sustainable Agriculture and Gree...

21st IEEE International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT, HONET 2024

作者： Li, Baihua Thompson, Mike Partridge, Tom Xing, Ruiming Cutler, Jack Alhnaity, Bashar Meng, Qinggang Loughborough University Department of Computer Science United Kingdom

ISBN: (纸本)9798350378078

Agricultural and livestock farming are important contributors to greenhouse gas (GHG) emissions, with methane emissions from ruminants being particularly significant. This research aims to showcase the innovative development of a digital twin platform integrated with AI for analyzing both current and historical GHG emissions. The digital twin harnesses AI for advanced predictive analytics, enabling the tracking and understanding of broad GHG emission trends over time. Key features of the platform include AI and machine learning models tailored for informative GHG estimation. It also offers interactive maps for visualizing spatial data and conducting association analysis. Users can benefit from dynamic historical data comparisons and utilize livestock emission calculators aligned with Intergovernmental Panel on Climate Change (IPCC) guidelines. The project supports Net Zero efforts by empowering farmers and organizational stakeholders to enhance environmental stew-Ardship and promote sustainable agriculture. © 2024 IEEE.

关键词： Greenhouse gas emissions

来源：评论

学校读者我要写书评

暂无评论

Refuting Approaches to the Log-Rank Conjecture for XOR Functions 51

Refuting Approaches to the Log-Rank Conjecture for XOR Funct...

引用

51st International Colloquium on Automata, Languages, and programming, ICALP 2024

作者： Hatami, Hamed Hosseini, Kaave Lovett, Shachar Ostuni, Anthony School of Computer Science McGill University Montreal Canada Department of Computer Science University of Rochester NY United States Department of Computer Science and Engineering University of California La Jolla San DiegoCA United States

ISBN: (纸本)9783959773225

The log-rank conjecture, a longstanding problem in communication complexity, has persistently eluded resolution for decades. Consequently, some recent efforts have focused on potential approaches for establishing the conjecture in the special case of XOR functions, where the communication matrix is lifted from a boolean function, and the rank of the matrix equals the Fourier sparsity of the function, which is the number of its nonzero Fourier coefficients. In this note, we refute two conjectures. The first has origins in Montanaro and Osborne (arXiv’09) and is considered in Tsang, Wong, Xie, and Zhang (FOCS’13), and the second is due to Mande and Sanyal (FSTTCS’20). These conjectures were proposed in order to improve the best-known bound of Lovett (STOC’14) regarding the log-rank conjecture in the special case of XOR functions. Both conjectures speculate that the set of nonzero Fourier coefficients of the boolean function has some strong additive structure. We refute these conjectures by constructing two specific boolean functions tailored to each. © Hamed Hatami, Kaave Hosseini, Shachar Lovett, and Anthony Ostuni.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Enhancing Early Detection of Brain Tumors: A Survey-Based Study on Convolutional Neural Network Classification

Enhancing Early Detection of Brain Tumors: A Survey-Based St...

引用

International Conference on Business Intelligence and Data Analytics, BIDA 2024

作者： Agarwal, Sunil Kumar Gupta, Yogesh Kumar Department of Computer Science Banasthali Vidyapith Rajasthan Banasthali India

ISBN: (纸本)9789819777167

A brain tumor is an aggressive malignancy that is one of the most common and dangerous diseases in the world. This paper proposed a method for brain tumor detection using Convolutional Neural Networks (CNN). The proposed method consists of some stages for tumor detection. The dataset consists of labeled images of two categories, tumor, and non-tumor. The performance of the proposed CNN model was compared to other research articles, showing its higher effectiveness with 98.6% accuracy. The paper also reports the results of a survey that aimed to analyze the importance of early cancer detection in reducing the mortality rate. The survey results show that 92% of the respondents agree or strongly agree with the statement. Overall, the paper presents an effective method for brain tumor detection and emphasizes the importance of early cancer detection in reducing the mortality rate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Violence Detection Technique Using Mobinet 6

Automatic Violence Detection Technique Using Mobinet

引用

6th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Karim, Md Abdul Islam Razin, Md. Jahidul Shopon, Md Alam, Tahira Chowdhury, Jamim Hossain Arman, Shajedul Hasan University of Asia Pacific Department of Computer Science and Engineering Dhaka Bangladesh University of Calgary Department of Computer Science Calgary Canada University of Skill Enrichment & Technology Department of Computer Science and Engineering Dhaka Bangladesh Panace Live Dhaka Bangladesh

ISBN: (纸本)9798350396133

Deep learning holds great significance in machine learning since it effectively addresses a wide range of problems. The ability to identify violence from various video surveillance systems is one such crucial real-world application. Many crimes are occurring in numerous public spaces as a result of inadequate security. Many methods have been proposed to solve this specific problem, however they have drawbacks. Additionally, they are ineffective since they are dependent on certain conditions. Therefore, we presented an efficient automatic violence detection method for video datasets. We created a video dataset consisting of 1000 videos, half of which featured violent content and the other half did non-violent content. We used a Deep Neural Network technique called MobilNet for detecting violence from videos. Additionally, we employed a variety of deep learning and machine learning strategies to increase the precision. With the training data, the classification model showed an accuracy of 97.50% while with the test data, the accuracy was 95.60%. Performance evaluation results demonstrated that the suggested method identified violent content in videos successfully. The method for video violence detection performed better than many other methods already in use. © 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

Strain modified nano-scale Ge/Ge0.98Sn0.02 exotic pin photo-sensor array for IR sensing: theoretical reliability and experimental feasibility studies

引用

Optical and Quantum Electronics 2024年第12期56卷 1-20页

作者： Bhadra, Bias Chinara, Suchismita Kundu, Abhijit Department of Computer Science and Engineering Chaibasa Engineering College Jharkhand Chaibasa India Department of Computer Science and Engineering NIT Rourkela Odisha Rourkela India Department of Electronics and Communication Engineering Chaibasa Engineering College Jharkhand Chaibasa India

In this paper, the superiority of Ge/Ge0.98Sn0.02asymmetrical supper lattice structure based vertically doped nano-scale pin photo-sensor under operating wavelength of 1200 nm to 2200 nm is reported. The authors have developed non-linear Strain Modified Quantum-Corrected Drift–Diffusion (SMQCDD) model for analyzing the electrical and optical characteristics of the photo-sensor. The inclusion of a small amount of Sn (2%) into the pure Ge material creates in-plane bi-axial strain in the intrinsic region (i-region) of the device. This results in increases in the value of the out-plane mobility of the charge particles. As a result, the overall performance of the photo-sensor enhances significantly. The authors have used in-plane induced bi-axial strain to accelerate the out-plane mobility of the charge particles by incorporation of the exotic asymmetrical supper lattice structure in the i-region of the photo-sensor. The validation of the non-linear SMQCDD model is performed through comparison of the simulated data obtained from SMQCDD model with the experimental results under a-like thermal/structural/electrical conditions. Additionally, the authors have designed 3X2 array of photo-sensors and studied the photo-electrical characteristics at the said operating wavelength. The proposed device offers better performance in terms of quantum efficiency (0.619: single-type photo-sensor;0.708: array-type photo) and photo-responsivity (0.056 A/W: single-type photo-sensor;0.808 A/W:for array-type photo-sensor)at 1600 nm wavelength compared to its conventional flat Si counterpart. The developed exotic pin photo-sensor can be used as a sensing device for applications in optical communication and bio-medical systems. As far as the authors are aware, this is the first report on nano-scale Ge/Ge0.98Sn0.02exotic pin photo-sensor. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Nanocrystals

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning based Approach towards the Analysis of Chronic Kidney Disease 2

A Machine Learning based Approach towards the Analysis of Ch...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Farooq, Sheikh Afaan Suryakanta Anupriya Ali, Aleem Chandigarh University Department of Computer Science Mohali India

ISBN: (纸本)9798350364699

Chronic kidney disease (CKD) is characterized by a decline, in kidney function, which can lead to impairment or complete cessation of kidney function. This lasting condition involves a progression of kidney function decline and the risk of eventual kidney failure. It is essential to preserve function and prevent complications through care. The University of California manages an AI database that contains updated information, on this condition. Using AI methods this research delves into CKD and its symptoms based on the dataset mentioned earlier. This study in conclusion correctly categorizes this disorder with a notable 99.64% precision rate. The main aim of this work is to create a clear and precise model for precisely recognizing chronic kidney disease. © 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

Exploring Robustness in Doctor-Patient Conversation Summarization: An Analysis of Out-of-Domain SOAP Notes 6

Exploring Robustness in Doctor-Patient Conversation Summariz...

引用

6th Workshop on Clinical Natural Language Processing, ClinicalNLP 2024, held at NAACL 2024

作者： Chen, Yu-Wen Hirschberg, Julia Department of Computer Science Columbia University United States

ISBN: (纸本)9798891761094

Summarizing medical conversations poses unique challenges due to the specialized domain and the difficulty of collecting in-domain training data. In this study, we investigate the performance of state-of-the-art doctor-patient conversation generative summarization models on the out-of-domain data. We divide the summarization model of doctor-patient conversation into two configurations: (1) a general model, without specifying subjective (S), objective (O), and assessment (A) and plan (P) notes;(2) a SOAP-oriented model that generates a summary with SOAP sections. We analyzed the limitations and strengths of the fine-tuning language model-based methods and GPTs on both configurations. We also conducted a Linguistic Inquiry and Word Count analysis to compare the SOAP notes from different datasets. The results exhibit a strong correlation for reference notes across different datasets, indicating that format mismatch (i.e., discrepancies in word distribution) is not the main cause of performance decline on out-of-domain data. Lastly, a detailed analysis of SOAP notes is included to provide insights into missing information and hallucinations introduced by the models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Continual Federated Learning for Dynamic Data Environments

Continual Federated Learning for Dynamic Data Environments

引用

2024 IEEE Pacific Rim Conference on Communications, computers and Signal Processing, PACRIM 2024

作者： Yao, JingTao Sharma, Akshat University of Regina Department of Computer Science Regina Canada

ISBN: (纸本)9798350362312

Federated learning lets smartphones, computers, or other such end devices learn without transmitting their raw data. Instead of sending personal data to a common server, each device does its own learning locally. Consequently, updated parameters from all devices are transferred to a central server to improve a global model for classification purposes. This approach ensures the privacy of individual data by keeping it decentralized (on device) and still allowing the models to learn collectively. Federated learning models often face the challenge of becoming outdated once training is complete, particularly when confronted with new data as the model is static. To avoid this issue, we incorporate continual learning into federated learning, which allows the devices' data to be sent as streams. This ensures that the global model remains adaptable, continually incorporating novel information without forgetting what it has learned in the past. The results of the study suggest that such a combined approach might be more effective than conventional federated learning methods. Twelve experiments were carried out applying continual learning to a federated learning setup for image classification tasks using the 10-fold cross-validation method on the MNIST, Fashion-MNIST and CIFAR-10 datasets;thus, the performance of the framework is calculated. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Speedy Gonzales: A Collection of Fast Task-Specific Models for Spanish 13

Speedy Gonzales: A Collection of Fast Task-Specific Models f...

引用

13th Joint Conference on Lexical and Computational Semantics, StarSEM 2024

作者： Cañete, José Bravo-Marquez, Felipe Department of Computer Science University of Chile Chile Chile

ISBN: (纸本)9798891761063

Large language models (LLM) are now a very common and successful path to approach language and retrieval tasks. While these LLM achieve surprisingly good results it is a challenge to use them on more constrained resources. Techniques to compress these LLM into smaller and faster models have emerged for English or Multilingual settings, but it is still a challenge for other languages. In fact, Spanish is the second language with most native speakers but lacks of these kind of resources. In this work, we evaluate all the models publicly available for Spanish on a set of 6 tasks and then, by leveraging on Knowledge Distillation, we present Speedy Gonzales, a collection of inference-efficient task-specific language models based on the ALBERT architecture. All of our models (fine-tuned and distilled) are publicly available on: https://***/dccuchile. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

LAGRANGIAN FLOW NETWORKS FOR CONSERVATION LAWS 12

LAGRANGIAN FLOW NETWORKS FOR CONSERVATION LAWS

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Torres, Fabricio Arend Negri, Marcello M. Inversi, Marco Aellen, Jonathan Roth, Volker Department of Mathematics and Computer Science University of Basel Switzerland

We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. By construction, the proposed LFlows satisfy the continuity equation, a PDE describing mass conservation in its differential form. Our model is based on the insight that solutions to the continuity equation can be expressed as time-dependent density transformations via differentiable and invertible maps. This follows from classical theory of the existence and uniqueness of Lagrangian flows for smooth vector fields. Hence, we model fluid densities by transforming a base density with parameterized diffeomorphisms conditioned on time. The key benefit compared to methods relying on numerical ODE solvers or PINNs is that the analytic expression of the velocity is always consistent with changes in density. Furthermore, we require neither expensive numerical solvers, nor additional penalties to enforce the PDE. LFlows show higher predictive accuracy in density modeling tasks compared to competing models in 2D and 3D, while being computationally efficient. As a real-world application, we model bird migration based on sparse weather radar measurements. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Numerical methods

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：