检索结果-内蒙古大学图书馆

Conference on Lasers and Electro-Optics (CLEO)

作者： Elena Goi Steffen Schoenhardt Min Gu Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China

We present aberration detectors based on multi-layered perceptrons printed by twophoton nanolithography. Through all-optical inference, the perceptrons can collect phase information from a point spread function perfor... 详细信息

ISBN: (纸本)9781943580910

关键词： Detectors Lasers and electrooptics Nonhomogeneous media Nanolithography Electrooptical waveguides

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Traffic Flow Optimization Using AI and 5G Communication Networks 3

Autonomous Vehicle Traffic Flow Optimization Using AI and 5G...

引用

3rd IEEE International Conference on Device intelligence, Computing and Communication Technologies, DICCT 2025

作者： Shekhar, Jayant Rama Prabha, K.P. Prashanth, S. Umamaheswari, K. Rahul, S.G. Gayathri, K. Sharda School of Engineering and Technology Sharda University Department of Cse UP Greater Noida India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India Excel Engineering College Department of Aeronautical Engineering Tamil Nadu Namakkal India V.S.B. Engineering College Department of Information Technology Tamilnadu Karur India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India St. Joseph's Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India

ISBN: (纸本)9798331543358

Real-time optimization of autonomous vehicle (AV) traffic flow using 5G communication networks and AI algorithms could overcome the limitations of static traffic enforcement, which uses outdated technologies to manage fluctuating traffic demands. It allows dynamic flow. Such commodities cannot adapt in real time because to their rigorous handling requirements, which disrupts traffic dynamics and creates construction delays and traffic congestion. The study suggests transmitting real-time vehicle status data to nearest intelligent crossings via vehicular wireless networks (VWNs). These intersections enhance traffic flow and reduce 5G network congestion using AI algorithms. Predictive analytics will help AVs change routes while on the road to maximize travel efficiency. It finds that peak congestion, average route duration, and fuel use reduce vehicle CO2 emissions by 66.7%, 22%, and 15%, respectively. It determined that the proposed system was a viable design route for a deployable smart city transportation solution because it outperformed traditional techniques in economic and environmental criteria. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

HDLCP: Experimental Analysis and Development of Hybrid Deep Learning Methodology for Crime Scenario Assesment and Prediction

HDLCP: Experimental Analysis and Development of Hybrid Deep ...

引用

Cognitive, Green and Ubiquitous Computing (IC-CGU), International Conference on

作者： M Tamilselvi C.N. Ravi S. Jayasudha P Shahad S. Karthikeyan V.Samuthira Pandi Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Computer Science and Engineering CMR Engineering College Medchal Hyderabad India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of CSE (Artificial Intelligence) Madanapalle Institute of Technology & Science Madanapalle Andhrapradesh India Department of ECE KSR College of Engineering Tiruchengode Tamil Nadu India Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350361780

ISBN: (纸本)9798350361797

For a variety of reasons, prediction is utilized in nearly every industry. Many societal functions, like as crime prediction, are served by it. data mining tools abound when it comes to traditional prediction. These approaches lack accuracy when dealing with new kinds of data and are somewhat outdated. They take a lot of time as well. In place of the antiquated data mining methods, artificial Neural Networks function well. This study employs a Hybrid Deep Learning based Crime Prediction (HDLCP) model to forecast criminal activity; the model is then tested for accuracy using the Decision Tree (DT) technique for cross-validation. Using the current datasets, additional information is anticipated to be extracted. Criminal activity is perilous and pervasive, affecting societies all across the globe. Life expectancy, GDP growth, and national prestige are all impacted by crime rates. New methods and sophisticated technologies are required to enhance crime analytics in order to safeguard communities and ensure the safety of society as a whole. A number of crime probabilities in a certain area may be studied, detected, and predicted by the suggested approach. Using a number of data mining approaches, the author explains the many forms of criminal study and crime prediction.

关键词： Deep learning Industries Law enforcement Economic indicators Predictive models Ubiquitous computing Safety

来源：评论

学校读者我要写书评

暂无评论

An artificial Neural Network Model to Forecast Grain Crops in North-Kazakstan Agricultural Experimental Station

An Artificial Neural Network Model to Forecast Grain Crops i...

引用

2023 IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2023

作者： Mimenbayeva, Aigul Omirtay, Maylen Niyazova, Rozamgul Bekmagambetova, Gulmira Suleimenova, Raya Tursumbayeva, Ainur Astana It University Dept. of Computational and Data Sciences Astana Kazakhstan Astana It University Specialty Smart Technologies Astana Kazakhstan L. Gumilyov Eurasian National University Dept. of Artificial Intelligence Technologies Astana Kazakhstan S. Seifullin Kazakh Agrotechnical Research University Dept. of Computer Science Astana Kazakhstan Eurasian Technological University School of Engineering and Information Technology Almaty Kazakhstan S. Seifullin Kazakh Agrotechnical Research University Dept. of Information Systems Astana Kazakhstan

ISBN: (纸本)9798350336917

The paper analyzes and predicts the yield of grain crops of LLP 'North-Kazakhstan Agricultural Experimental Station' for the last 30 years. The class of artificial neural networks-multilayer perceptron (MLP) was used as a research tool. The process of training of a model of a neural network consisting of 30 networks was performed on the basis of 70% training and 30% control samples. Based on the analysis of residuals histogram and scatter plot of the target and output function, the best neural network models MLP-1-7-1 (p=0.92), MLP-1-8-1 (p=0.97), MLP-1-5-1 (p=0.82) were selected. Next, using the best MLP 1-8-1 network, the model was tested the given data. Using time series projection, a graph was illustrated and a table of predicted grain yield values for the coming years was tabulated. The absolute error showed the high accuracy of the obtained best MLP 1-8-1 network for forecasting the amount of grain crop yield. The obtained model of artificial network can be applied in research and monitoring of agricultural production development. © 2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Is larger always better? Evaluating and prompting large language models for non-generative medical tasks

arXiv

引用

arXiv 2024年

作者： Zhu, Yinghao Gao, Junyi Wang, Zixiang Liao, Weibin Zheng, Xiaochen Liang, Lifang Wang, Yasha Pan, Chengwei Harrison, Ewen M. Ma, Liantao Institute of Artificial Intelligence Beihang University Beijing100191 China Centre for Medical Informatics University of Edinburgh EdinburghEH8 9YL United Kingdom Health Data Research UK United Kingdom School of Computer Science Peking University Beijing100871 China National Engineering Research Center for Software Engineering Peking University Beijing100871 China ETH Zürich Zürich8092 Switzerland

Background: The deployment of Large Language Models (LLMs) in medical fields is increasing, but few research evaluate their ability to manage both structured Electronic Health Record (EHR) data and unstructured clinical notes. This study provides a comprehensive benchmark of various models, including GPT-based LLMs, BERT-based language models, and conventional clinical predictive models to determine their efficacy in non-generative medical tasks using widely recognized datasets. Methods: We evaluated 14 language models (9 GPT-based and 5 BERT-based) alongside 7 conventional clinical predictive models on the MIMIC dataset, which encompasses comprehensive ICU patient records, and the TJH dataset, which includes EHR data from early COVID-19 patients. The performance of these models was assessed through a series of both supervised and unsupervised tasks, including mortality and readmission predictions, disease hierarchy reconstruction, and biomedical sentence matching. The study focused on comparing zero-shot prediction capabilities of LLMs with conventional models and the effectiveness of finetuned BERT-based models in handling clinical texts. Results: LLMs demonstrated promising zero-shot predictive abilities on structured EHR data when equipped with well-designed prompting strategies, often surpassing traditional models trained with limited datasets. However, in tasks involving unstructured medical texts, LLMs did not outperform existing BERT-based models. Both in supervised and unsupervised scenarios, the performance of finetuned BERT models was superior, suggesting that the additional cost and complexity of implementing LLMs might not be justifiable for non-generative tasks. Conclusion: While LLMs show significant potential in interpreting structured EHR data through zero-shot learning, their application in processing unstructured medical texts is less advantageous compared to finetuned BERT models. The findings underscore the importance of selecting appropriate mo

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Traffic Flow Optimization Using AI and 5G Communication Networks

Autonomous Vehicle Traffic Flow Optimization Using AI and 5G...

引用

Device intelligence, Computing and Communication Technologies, (DICCT), International Conference on

作者： Jayant Shekhar Rama Prabha K. P S. Prashanth Umamaheswari K Rahul S G K. Gayathri Department of CSE Sharda School of Engineering and Technology Sharda University Greater Noida UP India School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu India Department of Aeronautical Engineering Excel Engineering College Namakkal Tamil Nadu India Department of Information Technology V.S.B. Engineering College Karur Tamilnadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science St. Joseph's Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331543358

ISBN: (纸本)9798331543365

关键词： 5G mobile communication Smart cities Heuristic algorithms Real-time systems artificial intelligence Vehicle dynamics Autonomous vehicles Optimization Traffic congestion Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Identification and Classification of Rice Plant Diseases for Precision Agriculture

Deep Learning-based Identification and Classification of Ric...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： N. Venkatesh Swagata Sarkar A Sunil T.Guru Priya R Aarthi K.Mekala Devi School of CS&AI SR University &Warangal Artificial intelligence and Data Science Sri Sairam Engineering College Sai Leo Nagar West Tambaram Chennai computer science and engineering rajarajeswari college of engineering Ramohalli cross Bangalore Mysore road Kumbalgod Karnataka Electronics and Communication Engineering Periyar Maniammai Institute of Science and Technology PMIST VALLAM Department of ECE R.M.D Engineering College Chennai ECE Department S.A. Engineering college Chennai

Because they reduce both the quality and yield of crops, plant diseases seriously threaten our food supply’s reliability. Plant diseases often result in a significant reduction or complete absence of grain yield in various agricultural contexts. Classifying rice plant diseases and insects pose a significant challenge due to the intricate structure of their composition and the striking resemblance 5bserved among various disease types and insect species. Diseases and insects in crops must be discovered and categorized as soon as possible, ideally before they may spread. There are a number of methods for spotting plant diseases, but deep learning is now the gold standard. The authors provide a novel deep-learning approach for detecting diseases in rice fields using photographs. Convolutional Neural Networks with attention mechanism (CNNAM) can be used to detect diseases in rice plants. Due to its reliability in picture identification and classification, CNNs have been widely employed by researchers for plant disease identification. The identification of rice plant diseases, however, has only been the subject of a small number of studies. This research illuminates the present state of rice plant disease and the methods of disease detection based on Deep Learning. Deep learning models excel about more conventional machine learning methods. With the suggested model, authors were able to categorize rice photos with a 99.8 percent accuracy by learning latent patterns in the raw images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Innovative Solutions for Crop Health A Hybrid Approach to Cotton Root Rot Severity Assessment

Innovative Solutions for Crop Health A Hybrid Approach to Co...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Gautam Rana Deepak Banerjee Rahul Chauhan Mukesh Singh Bura Vijay Kumar VLSI Centre of Excellence Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Dehradun Uttarakhand India Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

The proposed study aims to enhance our comprehension and control of the gravity of cotton root rot by integrating agricultural practices with technological advancements. The combination of a CNN, which possesses knowledge, with an SVM greatly enhances its ability to detect root rot. It possesses great strength, exhibits high adaptability, and demonstrates exceptional speed in task execution. The test results indicate that Cotton, a significant component of global agriculture, is currently confronted with a persistent issue caused by detrimental root rot. The cause of this issue is Phymatotrichopsis omnivora, which has the potential to negatively impact productivity if not well managed. Effectively managing illnesses relies on meticulous and prompt attention to the severity of root rot. Executing this challenging undertaking requires innovative concepts to achieve success. This study used a mixed model as a response. The method combines the properties of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) to develop a sophisticated approach for quantifying the severity of cotton root rot infections. Our inquiry starts with a substantial collection of 9,000 dispersed photographs. These high-resolution photographs depict the several manifestations of root rot in plants in proximity. Demonstrating the effectiveness of our blend model, we present a comprehensive accuracy rate of 98.56%. This demonstrates its proficiency in providing accurate and comprehensive threat assessments. The model’s accuracy, memory recall, and F1 score serve as indicators of its performance.

关键词： Support vector machines Adaptation models Accuracy Music data models Threat assessment Numerical models Cotton Convolutional neural networks Gravity

来源：评论

学校读者我要写书评

暂无评论

Flying Neural Network-Based Optimistic Financial Early Alert System in AI Model

Flying Neural Network-Based Optimistic Financial Early Alert...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Saikrishna Boggavarapu S. Shabbir Ali G. Manikandan R. Mohanraj Devesh Pratap Singh Revathi. R Department of Information Technology University of the Cumberlands Prospect Heights IIIioni United States Department of Electronics & Communication Engineering KL University Guntur India Department of Electronics and Communication Engineering Saveetha School Of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Chennai India Department of Artificial Intelligence and Data Science St.Martin's Engineering College Secunderabad Telangana India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttrakhand India Department of Computer Science Karpagam Academy of Higher Education Coimbatore

An innovative method for early warnings in the area of financial risk management is the Flying Neural Network-based Optimistic Financial Early Alert System (FNN-OFEAS). The FNN-OFEAS outperforms conventional models and rule-based systems because it makes use of the Flying Neural Network architecture and incorporates sentiment analysis. Using a fictitious dataset including past stock prices, financial ratios, economic indicators, and sentiment analysis data, this study details the development, use, and findings of the FNN-OFEAS. The results show that the system is effective at capturing complicated temporal correlations, recognising non-linear patterns, and factoring in market sentiment, all of which contribute to improved risk identification in a timely and accurate manner. Early risk identification, investment decision assistance, regulatory compliance, and financial stability evaluation are just few of the real-world uses for the FNN-OFEAS. Its application is beneficial for financial institutions, investors, regulators, and policymakers since it enhances decision-making, reduces risk, and sheds light on previously hidden information. More work has to be done to improve the model architecture, include other data sources, provide real-time implementations, evaluate the model's resilience, and make it easier to comprehend the results. Addressing financial risks and bolstering financial stability in volatile market settings is one area where the FNN-OFEAS shows promise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

arXiv

引用

arXiv 2022年

作者： Hao, Yanbin Wang, Shuo Cao, Pei Gao, Xinjian Xu, Tong Wu, Jinmeng He, Xiangnan The CCCD Key Lab of Ministry of Culture and Tourism School of Data Science School of Information Science and Technology University of Science and Technology of China Anhui 230026 China The Wuhan Research Institute of Posts and Telecommunications Hubei Wuhan430205 China The School of Computer Science and Information Engineering School of Artificial Intelligence Hefei University of Technology Anhui 230009 China The School of Data Science School of Computer Science and Technology University of Science and Technology of China Anhui 230026 China The Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Hubei Wuhan430070 China

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ( Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

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：