检索结果-内蒙古大学图书馆

International Conference on science technology engineering and Management (ICONSTEM)

作者： Maheswari G Ramya. R Babitha. S Sriram. R Jennis. M I RamPrasad. P Department of Information Technology Hindustan Institute of Technology and Science Chennai India Department of Artificial Intelligence and Data Science PSNA College of Engineering and Technology

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

This research provides a deep learning approach and handwriting recognition to understand medical notes. The system processes and interprets textual medical notes using connectionist temporal classification (CTC) and optical character recognition (OCR) techniques. The written text is transcribed using the OCR component, and then the CTC algorithm is utilized to analyze the text and give significance to particular note portions. The suggested system's ability to correctly understand and arrange written medical information is demonstrated by training it on prescription notes from doctors taken from a dataset. According to the final forecast, the system can read medical notes with high accuracy, making medical professionals' usage and accessibility of these records easier. The suggested paradigm offers fast and precise access to patient information, which could increase the efficacy and efficiency of medical care.

关键词： Deep learning Training Handwriting recognition Accuracy Optical recording Optical character recognition Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Study on Calculation of Regulated Neutron Spectrum Based on Moderator with Multi-dimensional Features

Study on Calculation of Regulated Neutron Spectrum Based on ...

引用

2024 International Conference on Materials Physics and Applications, ICMPA 2024

作者： Cao, Chenglong Cao, Pei Sun, Ming Chen, Huaijin Zhang, Haiyan Institution of Electronic Engineering National University of Defense Technology Hefei230031 China School of Artificial Intelligence and Big Data Hefei University Hefei230001 China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230027 China

Neutron transport simulation is one of the key techniques for calculating the regulated neutron spectrum, which is extremely accurate but comes with a significant time loss and is difficult to achieve convergence when there is deep penetration. Accurate regulation of the neutron spectrum is essential for research on experimental neutronics. In this study, a fast way to compute the regulated neutron spectrum using a moderator with multi-dimensional features was developed. The response matrix with different dimensions was generated for each moderator after it first created a moderator database by classifying common shielding materials based on various dimensions (such as shape, size, substance, etc.). Finally, neutron transport modeling enabled the speedy and precise estimation of regulated neutron spectrum via matrix transformation. The results demonstrated that the mean square error (MSE) of the normalized regulated neutron spectra computed using the Monte Carlo approach and the proposed technique were able to reach the order of 10-6. The anticipated method was confirmed by equating the results with those of the Monte Carlo method under a regulation system consisting of moderators of different dimensions. Furthermore, the MSE of the regulated neutron spectrum in the case of deep penetration of the simplified thermal reactor TRIGA of the two methods in the convergent energy domain could also reach the order of 10-6, and in the divergent domain, the suggested method in this study was able to give a heuristic neutron spectrum. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Moderators

来源：评论

学校读者我要写书评

暂无评论

FedDGL: Federated Dynamic Graph Learning for Temporal Evolution and data Heterogeneity 16

FedDGL: Federated Dynamic Graph Learning for Temporal Evolut...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Xie, Zaipeng Li, Likun Chen, Xiangbin Yu, Hao Huang, Qian Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China College of Artificial Intelligence and Automation Hohai University Nanjing China

Federated graph learning enhances federated learning by enabling privacy-preserving collaborative training on distributed graph data. While traditional methods are effective in managing data heterogeneity, they typically assume static graph structures, overlooking the dynamic nature of real-world graphs. Integrating federated graph learning with dynamic graph neural networks addresses this issue but often fails to retain previously acquired knowledge, limiting generalization for both global and personalized models. This paper proposes FedDGL, a novel framework designed to address temporal evolution, and data heterogeneity in federated dynamic graph learning. Unlike conventional approaches, FedDGL captures temporal dynamics through a global knowledge distillation technique and manages client heterogeneity using a global prototype-based regularization method. The framework employs contrastive learning to generate global prototypes, enhancing feature representation while utilizing a prototype similarity-based personalized aggregation strategy for effective adaptation to local and global data distributions. Experiments on multiple benchmark datasets show that FedDGL achieves significant performance improvements over state-of-the-art methods, with up to 9.02% and 8.77% gains in local and global testing, respectively, compared to FedAvg. These results highlight FedDGL’s effectiveness in improving personalized and global model performance in dynamic, heterogeneous federated graph learning scenarios. © 2024 Z. Xie, L. Li, X. Chen, H. Yu & Q. Huang.

关键词： Dynamic Graph Learning Federated Graph Learning Knowledge Distillation Personalized Aggregation Prototype Learning Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

Exploring Sensor-Based Smart Farming Technologies in the Internet of Things (IoT) 1

Exploring Sensor-Based Smart Farming Technologies in the Int...

引用

1st IEEE International Conference on Computing and data science, ICCDS 2024

作者： Palarimath, Suresh Maran, Pyingkodi Thenmozhi, K. Balakumar, C. Sujatha, T. Wilfred Blessing, N.R. College of Computing and Information Sciences University of Technology and Applied Sciences Information Technology Department Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Compute Science Bengaluru India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350365337

The Internet of Things (loT) is a new technology trend that is being used in almost every area of human life. IoT is used almost every aspect of people's lives. Significantly, with a projected increase in the world's population to 9.7 billion by 2050, agricultural output would need to increase at an even more rapid rate to fulfill the requirement. Modern tools, notably the Internet of Things, make this a reality. The IoT makes it possible for farms to function without human labor. It has several potential applications in agriculture, including large- scale farming, greenhouse farming and management. The sensors serve as the most crucial component of the loT. Sensing devices are mostly used for the purpose of learning about the soil and its surroundings. The sensor has several applications in agriculture, including but not limited to NPK (nitrogen, phosphorus, and potassium) measurement, disease detection, and soil moisture analysis. This study discusses how IoT applications contribute to efficient farming practices. It shows how the IoT can be applied to agriculture and exhibits the many sensors, applications, problems, strengths, and shortcomings that underpin this field. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Stratification of Depressed and Non-Depressed Texts from Social Media using LSTM and its Variants

引用

Procedia Computer science 2024年 235卷 1353-1363页

作者： Keerthan Kumar T G Anoop R Shashidhar G Koolagudi Trupthi Rao Ashwini Kodipalli Department of Information Science and Engineering Siddaganga Institute of Technology Tumkur India Department of artificial intelligence and Data Science Global academy of Technology Bengaluru India Department of Computer science and Engineering National Institute of Technology Karnataka Surathkal India

This work examines the performance of various LSTM (long short-term memory) variants on social media text data. This study evaluates the performance of LSTM models with different architectures, namely, classic LSTM, Bidirectional LSTM, Stacked LSTM, gated recurrent unit (GRU), and bidirectional GRU, on a social network dataset comprising texts extracted from multiple social media platforms. We aim to identify the most effective LSTM variant of the five considered LSTM models for text analysis through a comparative study of the models’ precision, recall, F1-score, and accuracy. The research findings show that the Classic LSTM and the GRU model perform better than the other models in accuracy. In contrast, the bidirectional models (Bidirectional LSTM and Bidirectional GRU) provide better precision scores than their respective primitive models. This research has significant implications for developing more efficient models for natural language processing applications. It offers beneficial insights into the implications involving the scrutiny of depression on social media platforms through text data analysis.

关键词： Depression Deep-Learning Gated Recurrent Unit Long Short Term memory Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic AI Collaboration Frameworks Using Real-Time Multimodal Feedback Loops for Complex Task Automation

Dynamic AI Collaboration Frameworks Using Real-Time Multimod...

引用

data science, Agents & artificial intelligence (ICDSAAI), International Conference on

作者： K. Saranya Veeramalai Sankaradass V. Antony Suresh Sunitha. T Department of Artificial Intelligence and Data Science Panimalar Institute of Technology Chennai India Department of ComputerScience and Engineering Chennai Institute of Technology Chennai India Department of Information Technology St. Joseph College of Engineering Chennai India Department of Artificial Intelligence and Data Science Saveetha Engineering College Chennai India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

AI solutions are introduced in various complex, unstructured and perpetually evolving contexts, wherein multiple agents are often needed to cooperate in order to accomplish a given set of objectives. In such environment, flexibility is crucial because such systems are required to alter their operation in accordance with changes occurring in the environment. However, there are problems associated with traditional multi-agent systems to provide the wanted level of flexibility in order to react promptly to the constantly changing environment and handle a variety of sensory inputs. This paper describes a new Dynamic AI Collaboration Framework to address these issues by incorporating multi-modal feedback from vision, audio and text, haptic feedback streams. This framework is composed by a Dynamic Role Assigner based on reinforcement learning that will assign the roles of the agents according to the variations of the environment. This can be done to a much larger extent than in the earlier examples, and flexible adaptive AI agents can alter their roles without any problems according to their assessment of the ongoing task and its environment. This paper also presents an evaluation of the effectiveness of the proposed framework in a number of simulated disaster-response scenarios where our approach proves to be 25% more efficient and 40% more dynamic as compared to the conventional static role allocation based approaches. The findings show that adopting remote multimodal feedback as well as dynamic role allocation strengthen synergistic interactions among AI participants and guarantee optimised performance in critical, transient situations. In this work numerous applications are presented for dynamic AI systems for example in disaster response and industrial automation, in collaborative creative processes and health care showing that dynamic systems have a variety of uses in different fields.

关键词： Automation Collaboration Reinforcement learning Dynamic scheduling Real-time systems Resource management artificial intelligence Transient analysis Streams Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Advancing Early Detection: CNN for Automated Blood Cancer Diagnosis and Anomaly Detection 2

Advancing Early Detection: CNN for Automated Blood Cancer Di...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Raji, V. Seetharaman, Anburaman Kasi, Baskar Govindaraju, Sakthi Paarkavy, B. S K P Engineering College Department of Computer Science and Engineering Tiruvannamalai India Sri Venkateswaraa College of Technology Department of Artificial Intelligence and Data Science Chennai India Galgotias University School of Computer Science and Engineering Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India Saveetha Engineering College Department of AI&DS Chennai India

ISBN: (纸本)9798350368109

The evaluation and diagnosis of diseases related to blood cancer can be intricate and time-consuming. This complexity is compounded by the reliance on manual analyses employing techniques that consume a significant amount of time. Numerous methods have been created over the past ten years for the finding, analysis, and categorization of human blood cancer. The lack of methods or models that can automatically analyze human blood cells to detect the presence of cancer, however, is still a significant issue. The development of such a model holds the potential to enhance the early detection and prevention of these diseases, thereby facilitating more prompt medical diagnoses. In our ongoing research, we present our current endeavors in the creation of a Deeper with Convolutions Neural Network (DCNN) Learning Model capable of recognizing anomalies in blood cells. We employ a Hybrid Ensemble DCNN Learning technique for the identification of blood cancer. With accuracy rates surpassing 99%, this method is one of the most sophisticated deep learning models. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Investigating the Utility of data Mining for Automated Credit Scoring 15

Investigating the Utility of Data Mining for Automated Credi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Yadav, Dhyan Garima Soni, Rudransh Anandhasilambarasan, D. Sasirekha, R. Prema, S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Karnataka Bangalore India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore641021 India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Department of Artificial Intelligence & Data Science Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350370249

data mining is a powerful device for automatic credit scoring. This paper will look into the application of statistics mining for automated credit score scoring by discussing its advantages and downsides. The form may even look at cutting-edge research in the location and discuss the demanding situations that information mining techniques pose while used for automatic credit score scoring. Similarly, the paper will provide pointers on how statistics mining techniques can improve the effectiveness of computerized credit score scoring. Subsequently, a precis of the paper's conclusions and implications for future studies could be supplied. © 2024 IEEE.

关键词： Conclusions Implications Improve Information Scoring

来源：评论

学校读者我要写书评

暂无评论

IoT-Driven Mushroom Farm Automation Using Neural Turing Machines (NTM) 4

IoT-Driven Mushroom Farm Automation Using Neural Turing Mach...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Manoj Kumar, S. Monica, C.L. Sunith Babu, L. Manikandan, V. Subramani, Dinesh Malik, Subhash Madanapalle Institute of Technology & Science Department of Mechanical Engineering Angallu India V.R.Siddhartha Engineering College Department of Environmental Science Vijayawada India M. S. Ramaiah Institute of Technology Department of Mechanical Engineering Bengaluru India Department of Computer Science and Engineering Bengaluru India Department of Artificial Intelligence and Data Science Erode India Maharishi Markendeshwar Engineering College Department of Mechanical Engineering Mullana India

ISBN: (纸本)9798350352931

Mushroom cultivation leads global agriculture due to its impact on worldwide trade. One of the main challenges in this area is optimal weather, especially temperature and humidity. Unfortunately, traditional farming's inability to achieve these conditions often leads to low yields. The recommended procedure involves collecting sensor data, constructing the model, and training it. Preprocessing includes spectral smoothing, normalization, and reflectance calibration. Sensors measure motion, temperature, light, and soil moisture. Photo feature extraction uses edge detection to identify objects. The model is trained using NTM. The suggested NTM-based model beats top-tier models like Random Forest (RF) and Support Vector Machine (SVM) with 92.35 percent accuracy. This increasing accuracy shows the model's mushroom production optimization. This proposed uses sensor data and current image processing techniques to improve mushroom farming conditions. NTM-based mushroom cultivation is more efficient and yields more than conventional methods. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Dermatology: Revolutionizing Dermatological Diagnostics with AI and Emergency Care Solutions

Next-Gen Dermatology: Revolutionizing Dermatological Diagnos...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Yashas D M Shivani Kashyap Charan PR Hemanth Kumar GP Abhishek BK Deekshith C Dept of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bengaluru Dept of Information Science and Engineering New Horizon College of Engineering Bengaluru Dept of Artificial Intelligence and Machine Learning BNM Institute of Technology Bengaluru Dept of Artificial Intelligence and Data Science Siddaganga Institute of Technology Tumkur Dept of Computer Science and Engineering Vidyavardhaka College of Engineering Mysore

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

Skin health conditions should be diagnosed and treated on time so as to prevent complications and promote better health results. This paper presents an AI-based system that makes use of Convolutional Neural Networks with the InceptionV3 Architecture for predicting skin diseases at higher levels. The model, which is based on the large DermaNet dataset, classifies skin disorders fast and effectively. The system is coupled with a simple Telegram based application for the users to get a complete solution. A user can upload a photo of the affected skin area and get a diagnosis within seconds, an explanation of the disease and how severe it is in percentage. The bot also has a location and contact sharing feature that assists users in finding nearby doctors and clinics that can provide further assistance. It further provides on the spot appropriate cures for the particular condition diagnosed. Moreover, this makes it possible for the customer to fill the healthcare void in particular the neglected ones by making it easy for them to access real time high quality services. By equipping users with relevant information and appropriate actions required at the right time, this project has showcased how AI has the ability to transform the dermatological field.

关键词： Deep learning Dermatology Medical services Transforms Chatbots Skin Real-time systems Convolutional neural networks artificial intelligence 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：