检索结果-内蒙古大学图书馆

Proceedings of the 2024 AAAI/ACM Conference on AI, Ethics, and Society

作者： Felix B Mueller Rebekka Görge Anna K Bernzen Janna C Pirk Maximilian Poretschkin Fraunhofer IAIS Sankt Augustin Germany and Department of Computer Science University of Bonn Germany and Lamarr Institute of Machine Learning and Artificial Intelligence Germany Fraunhofer IAIS Sankt Augustin Germany and Lamarr Institute of Machine Learning and Artificial Intelligence Germany Faculty of Law University of Regensburg Germany

Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an important problem to solve, as it may violate existing copyright laws as well as the European AI Act. In this work, we propose a systematic analysis to quantify the extent of potential copyright infringements in LLMs using European law as an example. Unlike previous work, we evaluate instruction-finetuned models in a realistic end-user scenario. Our analysis builds on a proposed threshold of 160 characters, which we borrow from the German Copyright Service Provider Act and a fuzzy text matching algorithm to identify potentially copyright-infringing textual reproductions. The specificity of countermeasures against copyright infringement is analyzed by comparing model behavior on copyrighted and public domain data. We investigate what behaviors models show instead of producing protected text (such as refusal or hallucination) and provide a first legal assessment of these behaviors. We find that there are huge differences in copyright compliance, specificity, and appropriate refusal among popular LLMs. Alpaca, GPT 4, GPT 3.5, and Luminous perform best in our comparison, with OpenGPT-X, Alpaca, and Luminous producing a particularly low absolute number of potential copyright violations. Code can be found at ***/felixbmuller/llms-memorization-copyright.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis

引用

CAAI Transactions on intelligence Technology 2024年第4期9卷 879-893页

作者： Shuaiqi Liu Siqi Wang Chaolei Sun Bing Li Shuihua Wang Fei Li College of Electronic and Information Engineering Hebei UniversityBaodingChina Machine Vision Technology Innovation Center of Hebei Province BaodingChina The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Computer Science and Technology Henan Polytechnic UniversityJiaozuoChina

Diagnosing individuals with autism spectrum disorder(ASD)accurately faces great chal-lenges in clinical practice,primarily due to the data's high heterogeneity and limited sample *** tackle this issue,the authors constructed a deep graph convolutional network(GCN)based on variable multi‐graph and multimodal data(VMM‐DGCN)for ASD ***,the functional connectivity matrix was constructed to extract primary ***,the authors constructed a variable multi‐graph construction strategy to capture the multi‐scale feature representations of each subject by utilising convolutional filters with varying kernel ***,the authors brought the non‐imaging in-formation into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between *** extracting the deeper features of population graphs using the deep GCN(DeepGCN),the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD *** proposed algorithm was evaluated on the Autism Brain Imaging Data Exchange I(ABIDE I)dataset,achieving an accuracy of 91.62%and an area under the curve value of 95.74%.These results demon-strated its outstanding performance compared to other ASD diagnostic algorithms.

关键词： machine learning medical image processing medical signal processing

来源：评论

学校读者我要写书评

暂无评论

A Novel AI-Assisted e-Consult Platform Integrating Deep learning for Enhanced Healthcare Access and Diagnostic Precision

A Novel AI-Assisted e-Consult Platform Integrating Deep Lear...

引用

Multi-Agent Systems for Collaborative intelligence (ICMSCI), International Conference on

作者： G Vijayasekaran Rajasree R S Parvez Alam Abhishek Suryavanshi Vinayak Ranjanagi Umar Farooq Mulla Dept of Computer Science and Engineering New Horizon College of Engineering Bengaluru Dept of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bengaluru

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

This study introduces the ‘AI-Assisted E-Consult’ initiative. The rapid digitization of healthcare is reshaping how medical services are delivered. This paper outlines the design of an AI-Driven E-Consult platform, serving as a digital interface that links patients, healthcare provider, and medical facilities. Utilizing state-of-the-art technologies such as AI and machine learning, the platform streamlines predictive health insights and appointment scheduling, thereby improving access to quality medical care. The platform employs Natural Language Processing (NLP) via the NLTK library and uses a Recurrent Neural Network (RNN) architecture trained on medical conversation datasets to power an AI chatbot. This chatbot analyzes symptoms and predicts potential health conditions, offering users preliminary insights into their health status. Furthermore, the system incorporates Haversine distance calculations to measure the geographical proximity between patients and doctors, enhancing logistical planning for consultations. To evaluate the platform's accuracy and performance, metrics such as Mean Squared Error (MSE) and Mean Absolute Error (MAE) will be used, ensuring precise predictions and operational effectiveness. The AI- Powered E-Consult platform is designed to eliminate healthcare barriers and maximize resource efficiency. Offering scalable, adaptable solutions tailored to the needs of contemporary healthcare, this platform represents a significant advancement toward a more accessible, efficient, and time-saving healthcare model, particularly for underserved populations.

关键词： Measurement Deep learning Recurrent neural networks Medical services Oral communication Chatbots Libraries Planning Medical diagnostic imaging Collaborative intelligence

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Random Forest and CNN for Surgery Mortality Prediction

Comparative Analysis of Random Forest and CNN for Surgery Mo...

引用

2023 IEEE International Conference on Network, Multimedia and Information Technology, NMITCON 2023

作者： Aaditya, P. Manu, R. Asif, Mohammed Jayanthi, M.G. Kannadaguli, Prashanth Cambridge Institute of Technology Artificial Intelligence and Machine Learning Bangalore India Cambridge Institute of Technology Computer Science and Technology Bangalore India Cambridge Institute of Technology Department of Cse Bangalore India Dhaarini Academy of Technical Education Bangalore India

ISBN: (纸本)9798350300826

Accurate surgical outcome forecasting is essential for patient safety, healthcare resource allocation, and healthcare professional's capacity to make well-informed choices. To address this, a paper has been initiated to create a machine learning (ML) and deep learning (DL) model that can effectively determine the likelihood of a patient surviving a surgery. The main goal of this paper is to compare the performance of both models and determine which one yields superior overall results and develop something that can help the healthcare industry in making judgements. To conduct this research, a comprehensive dataset comprising approximately 50,000 surgical cases from various hospitals has been acquired. The paper successfully developed and evaluated various models. The best-performing model was 'Random Forest', which achieved an accuracy of 92.51%. The deep learning models also showed useful results, with the best model achieving an accuracy of 91.3%. The process of fine-tuning the DL model has yielded a significant improvement in accuracy, increasing it from 91.3% to 93.4%. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

One-Shot Vision, AI for Effortless Identification of Individuals with and Without Glasses 5

One-Shot Vision, AI for Effortless Identification of Individ...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Tejesh, Gangadhar Karchi, Rashmi Hatture, Sanjeevakumar Sankanagoudra, Asharani Saini, Rashmi Nagarjuna College of Engineering and Technology Department of Artificial Intelligence and Machine Learning Karnataka Bengaluru India Nagarjuna College of Engineering and Technology Department of Information Science and Engineering Karnataka Bengaluru India G. B. Pant Institute of Engineering and Technology Department of Computer Science Uttarakhand Pauri Garhwal246194 India

ISBN: (纸本)9798350376685

Facial recognition is a challenging task, especially in the wild where there exist a substantial amount of variation in lighting, pose, and expression. One-shot knowledge acquisition is a form of machine learning that allows a model to learn to recognize a new class Upon observing just a single instance of that class. the proposed work of a one-shot learning strategy for facial recognition system that is specifically designed to detect persons with or without spectacles. The proposed work approach has the capability to achieve high accuracy on a limited dataset of labeled images, and possesses the capacity to adjust to unfamiliar images that were not encountered in prior training stages. In this work, One-shot learning aims to recognize individuals based on a limited number of examples with and without specs, making it suitable for scenarios where acquiring a large dataset is challenging. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Object-Centric Image to Video Generation with Language Guidance

arXiv

引用

arXiv 2025年

作者： Villar-Corrales, Angel Plepi, Gjergj Behnke, Sven Autonomous Intelligent Systems Computer Science Institute VI – Intelligent Systems and Robotics Center for Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Accurate and flexible world models are crucial for autonomous systems to understand their environment and predict future events. Object-centric models, with structured latent spaces, have shown promise in modeling object dynamics and interactions, but often face challenges in scaling to complex datasets and incorporating external guidance, limiting their applicability in robotics. To address these limitations, we propose TextOCVP, an object-centric model for image-to-video generation guided by textual descriptions. TextOCVP parses an observed scene into object representations, called slots, and utilizes a text-conditioned transformer predictor to forecast future object states and video frames. Our approach jointly models object dynamics and interactions while incorporating textual guidance, thus leading to accurate and controllable predictions. Our method’s structured latent space offers enhanced control over the prediction process, outperforming several image-to-video generative baselines. Additionally, we demonstrate that structured object-centric representations provide superior controllability and interpretability, facilitating the modeling of object dynamics and enabling more precise and understandable predictions. Videos and code are available at https://***/TextOCVP/. © 2025, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Flexible Ring Slot Antenna for Optimized 5G Performance in N77 and N78 Frequency Bands for Wearable Applications

引用

Progress in Electromagnetics Research C 2024年 150卷 47-55页

作者： Soni, Gaurav Kumar Yadav, Dinesh Kumar, Ashok Sharma, Chanchal Yadav, Manish Varun Department of Electronics and Communication Engineering Manipal University Jaipur Rajasthan Jaipur India Department of Electronics and Communication Engineering Government Mahila Engineering College Rajasthan Ajmer India Department of Computer Science Engineering in Artificial Intelligence and Machine Learning Saraswati College of Engineering Maharashtra Navi Mumbai India Department of Aeronautical and Automobile Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India

The growth of 5G communications has created a demand for advanced wearable and flexible antennas due to supporting the high speeds, low latency, and capability of mechanical deformation conditions such as bending and conformability. In this paper, the design and analysis of a defected ground structure (DGS)-based ring slot antenna for N77 (3.3–4.2 GHz) and N78 (3.3–3.8 GHz) frequency bands is demonstrated. The antenna is made of an RT/Duroid 5880 substrate and has a loss tangent (tan δ) of 0.0009 and dielectric constant (Εr) of 2.2. A DGS-based ring slot microstrip antenna is simulated, tested, and experimentally characterized on different body locations (leg, chest, and hand) along with bending, and their results are presented accordingly. The magnitude of S11 (|S11|) of the proposed antenna is −26.81 dB at resonant frequency of 3.45 GHz, with the impedance bandwidth of 22 MHz (3.486 GHz to 3.508 GHz), peak gain of 6.27 dBi, and radiation efficiency of 85.02%. The simulated specific absorption rate (SAR) for 1 g and 10 g human body tissues is 0.263 W/Kg and 0.076 W/Kg, respectively. The total volume of the antenna is 0.58λ0 × 0.58λ0 × 0.00595λ0 (at 3.5 GHz). The proposed antenna is suitable for 5G wearable devices. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

A Review of machine learning Algorithms in Diabetes Management 4

A Review of Machine Learning Algorithms in Diabetes Manageme...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Gayaki, Unnati Daronde, Subodh Tale, Abhay Barhate, Aditya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798331523923

Diabetes is a prevalent and chronic disease affecting millions worldwide, posing significant challenges in its management and treatment. This review article aims to explore the current and potential future roles of machine learning (ML) in diabetes management, focusing on progress, applications, and challenges. It discusses various ML techniques, including support vector machines (SVM), logistic regression, decision trees, ensemble methods, and advanced deep learning approaches such as long short-term memory (LSTM) networks and convolutional neural networks (CNN). These methods have demonstrated benefits in analytics, patient monitoring, decision support systems, personalised treatment, and patient engagement. However, significant challenges persist, such as computational complexity, data quality, limited interoperability of systems, and ethical concerns regarding AI use in healthcare. The article addresses these challenges by fostering collaboration between AI implementers and health care professionals. This collaboration is essential to develop long-term, legally compliant, and solution-oriented frameworks that enhance patient care and diabetes management and pave the way for more efficient and ethical AI applications in healthcare. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Designing Autotuned Student Models by Knowledge Distillation from Self-Supervised Teacher Models

引用

SN computer science 2025年第5期6卷 1-16页

作者： Kishore, Jaydeep Mukherjee, Snehasis Department of Computer Science and Engineering Shiv Nadar Institution of Eminence Delhi NCR Greater Noida India Department of Artificial Intelligence and Machine Learning Manipal University Jaipur Rajasthan Jaipur 303007 India

As deep learning-based models continue to be developed, optimizing model accuracy and efficiency remains a challenging task. This paper applies a knowledge distillation-based approach to train a student model from a pretrained self-supervised teacher model for application to image classification. The study further describes how hyperparameters such as the number of layers, number of units, dropout, and learning rate for the multi layered perceptron (MLP) classifier following the student model are automatically tuned (autotuned), along with the hyperparameters used in knowledge distillation (balancing factor alpha and beta, and the temperature) using an efficient combination of Gaussian process and tree-structured Parzen estimator (TPE) algorithms. Additionally, the paper uses a linear combination of hard target, soft target, Barlow-Twins loss and cosine similarity loss functions. The experiments were conducted on three benchmark datasets: CIFAR-10, CIFAR-100, and Caltech-101, and the results are promising compared to the state-of-the-art self-supervised models. The source code for this study is publicly available at github. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bayesian optimization BO-GP BO-TPE Ensemble learning Hyperparameter optimization Knowledge distillation Self-supervised

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Yield Predictions with Real-Time IoT Sensor Data and machine learning Integration 5

Enhancing Agricultural Yield Predictions with Real-Time IoT ...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Chandiraprakash, N. Chinnasamy, A. Ashok, M. Malla Reddy College of Engineering Department of Artificial Intelligence and Machine Learning Hyderabad India School of Computing Department of Data Science and Business Systems SRMIST kattankulathur campus Chennai India Malla Reddy College of Engineering Hyderabad India

ISBN: (纸本)9798331518097

This research extends previous studies on the effects of climate change on agricultural yield predictions by integrating advanced machine learning (ML) methods with real time environmental sensing data. It builds on the basic usage of Long Short-Term Memory (LSTM) and Random Forest (RF) methods by employing real time data streams from IoT based field sensors that measure soil moisture, nutrient levels and pest activity. The aim is to enhance the prediction model's adaption to changing climatic circumstances, therefore increasing their utility in agricultural management. This study proposes a dynamic adaptation feature that uses real time data to make timely adjustments to crop management predictions. Moreover, the integration of Convolutional Neural Network (CNN) with LSTM is being investigated to increase the spatial and temporal accuracy of these predictions. By integrating conventional climatic data with detailed micro environmental elements from IoT sensors, this method obtains a aspects which affects the crop growth. This study also focuses on developing a userfriendly interface that allows farmers to easily access predictive developments and recommendations, allowing for more informed decision making. This technique is predicted to make substantial advances in precision agriculture, giving more effective methods for regulating agricultural productivity in dynamic climatic variability. These results may improve food security and sustainability by optimizing resource utilization and reducing the environmental impact of farming operations. © 2024 IEEE.

关键词： Smart agriculture

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：