检索结果-内蒙古大学图书馆

International Conference on Trends in Electronics and Informatics (ICEI)

作者： J Bino C. Preethi M. Renukadevi T.K.S Rathish babu S. Kanageswari Leema Nelson Department of Electronics and Communication Engineering St. Joseph's Institute of Technology Department of Computer Science Engineering Sethu institute of technology Department of Computer Science Engineering SRM Institute of Science and technology Ramapuram Chennai Department of computer science and Application Loyola College Chennai Chitkara University Institute of Engineering & Technology Chitkara University Punjab India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Accurate and early diagnosis of renal cancer is important for the improvement of outcomes in patients; hence, timely intervention has much to do with the effectiveness of treatments and survival rates. While there has been an increase in medical imaging modalities, early detection of renal cancer has become quite plausible, though the complexity introduced in the characteristics of tumors calls for advanced methods for their reliable classification. In this work, a new LSTM+CNN-based model is developed for renal cancer disease detection by integrating sequential learning capability from LSTM networks together with the powerful feature extraction abilities of CNN. The system is designed to improve both the accuracy and efficiency in renal cancer diagnosis based on the medical imaging data using spatial and temporal features. Among these, the proposed LSTM+CNN-based model has turned in better accuracy with quicker processing time and better overall classification performance compared to the state-of-the-art models. The proposed model also allows for the non-invasive, high-precision differentiation of renal tumors into low- and high-grade ones, with a view to early diagnosis and prediction. These results provide a proof of the enormous potentials of deep learning models, especially the LSTM+CNN architecture, toward making renal cancer detection an efficient and practical clinical solution.

关键词： Deep learning Support vector machines Accuracy Computational modeling Predictive models Reliability Medical diagnosis Long short term memory Cancer Tumors

来源：评论

学校读者我要写书评

暂无评论

Wind-Bell Index: Towards Ultra-Fast Edge Query for Graph Databases 39

Wind-Bell Index: Towards Ultra-Fast Edge Query for Graph Dat...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Qiu, Rui Ming, Yi Hong, Yisen Li, Haoyu Yang, Tong Peking University School of Computer Science National Engineering Laboratory for Big Data Analysis Technology and Application Beijing China Peking University Academy for Advanced Interdisciplinary Studies China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350322279

Graphs are good at presenting relational and structural information, making it powerful in the representation of various data. For the efficient storage and processing of graph-like data, graph databases have been rapidly developed and extensively studied. However, graph databases mostly use adjacency lists as their basic data structure (e.g., Neo4j), which could result in poor performance of edge due to the skewed degree distribution of *** design the Wind-Bell Index to address this problem. Wind-Bell Index is a memory-efficient index data structure, which can be attached to existing graph databases to speed up the edge. We have fully implemented our data structure in Neo4j, the most popular graph database today, and conduct theoretical and experimental analysis to evaluate the performance. Theoretical results prove the high query efficiency of our algorithm. And experimental results show that the average edge query speed is increased by hundreds of times compared with the original query interface of Neo4j. We believe that the excellent performance and scalability of Wind-Bell Index make it suitable for the application in a variety of graph databases. © 2023 IEEE.

关键词： Graph Databases

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Employing Sequence-to-Sequence Stacked LSTM Autoencoder Architecture to Forecast Indian Weather

引用

Procedia computer science 2024年 235卷 2258-2268页

作者： Arpita Maharatha Ratnakar Das Jibitesh Mishra Soumya Ranjan Nayak Srinivas Aluvala Dept. of Computer Science & Application Odisha University of Technology and Research Bhubaneswar 751029 India School of Computer Engineering KIIT Deemed to be University Bhubaneswar 751024 Odisha India Department of Computer science and artificial intelligence SR University Warangal Telangana -506371 India

One of the buzz words in current research depends for a weather forecast is the atmospheric temperature, and this value may change at any time. Predicting air temperature exactly is necessary since it is particularly important for various communities and events. In today’s world of massive amounts of data and unforeseen data fluctuations, long-short term memory (LSTM), a sort of neural network method, is becoming more and more popular. The present work employed a sequence to sequence LSTM autoencoder to forecast Indian weather patterns. The prediction model was trained using historical data obtained from the Khordha district administration. The proposed method primarily emphasizes two phases of the procedure. The present study involves an examination of a proposed model, wherein a comparison is made between four distinct variants of LSTM techniques: vanilla LSTM, stacked LSTM, bidirectional LSTM, and convLSTM. The objective of this analysis is to predict temperature patterns. Additionally, this paper utilizes an LSTM autoencoder model to forecast the temperature for the subsequent two-year period in the Khordha district of Odisha, India. The experimental investigation demonstrates that the utilization of Stacking encoder-decoders with bidirectional LSTM cells leads to a notable enhancement in the accuracy of the model, resulting in maximum efficacy. A notably lower Mean Absolute Error (MAE) result suggests that the 9-layer stacked autoencoder model has superior performance in predicting both the minimum and maximum temperature.

关键词： LSTM CNN Weather Forecasting Temperature

来源：评论

学校读者我要写书评

暂无评论

A Multistep Ahead Predictive Analysis of Crude Oil 2

A Multistep Ahead Predictive Analysis of Crude Oil

引用

2nd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2023

作者： Mohapatra, Srikanta Kumar Singh, Kamakhya Narayan Sarangi, Prakash Kumar Sahu, Premananda Mohanty, Jayashree Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School Of Computer Application KIIT Deemed University Odisha India Hyderabad India School of Computer science and Engineering Lovely professional University Punjab India Chandigarh University Dept.of AIT-CSE Punjab Chandigarh Mohali India

ISBN: (纸本)9798350333763

The population is increasing in a rapid manner and the number of vehicles is increasing in the same ratio. Also, crude oils are very useful towards the energy needs in the industries. As a result, a day will come when we face the issue of feeling the vehicles with the petrol to run the vehicle and to run the industries. So, the solution is to find out the period up to which we can use the crude oil which is currently present in the world. To get a conclusion the most populated countries India and China is taken as reference. For simulation purpose time series based Artificial Neural Network application along with Facebook Prophet is used. Facebook Prophet is used to predict future situations in time series data related to oil production and consumption in two top countries by population, China, and India, over a period of 32 years. NeuralProphet is used for modelling time-series based on neural networks forecasting the near-term oil crisis. The dataset used in this study contains three characteristics, namely population, oil production, and consumption, and is obtained from different government sources. The best part of this model is that it can predict multi step ahead of given current data as required. The method based on NeuralProphet is best suit for the time series prediction for short period or long period. It can be used in multistep ahead prediction methods. It is predicted that by 2050 the scarcity of the petroleum is most. So, the solution is either to reduce the uses of vehicles, control the population or simply go for an alternate fuel like hydrogen could be considered a suitable substitute for oil. This prediction highlights the need for sustainable energy sources to meet the energy demand in the future. In conclusion, this paper presents NeuralProphet approach for forecasting future oil consumption and production trends combining the Facebook Prophet and NeuralProphet method. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

application of ML in Agriculture Field With Its Enhancement Methods

Application of ML in Agriculture Field With Its Enhancement ...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Shobit Agrawal Sonika Bhardwaj Nandini Sharma Varun Mishra Department of Computer Science and Engineering GL Bajaj Group of Institutions Mathura Uttar Pradesh India Department of Computer Engineering and Application GLA University Mathura Uttar Pradesh India

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

Food is essential for humanity and is primarily produced through agriculture. While addressing fundamental human needs, agriculture also serves as a global source of employment. Recent advancements in machine learning (ML) research have not only enhanced agricultural gains but also brought about additional benefits, including resource optimizations. ML, functioning as an advanced technology, provides farmers with detailed advice and insights into crop yield and resources optimization, aiding in the reduction of farming losses. This article comprehensively examines recent ML applications and trends in agriculture, showcasing its potential for more accurate and effective farming, yielding high-quality results with reduced human labor. The findings emphasize the considerable space for innovation in meeting the demands of businesses seeking sustainable and optimized agricultural practices. These technologies, can be crucially helpful in agriculture in automation Furthermore, the paper serves as a potential milestone for future research in various directions of agriculture.

关键词： Technological innovation Humanities Employment Machine learning Forestry Market research Agriculture

来源：评论

学校读者我要写书评

暂无评论

Optimized Pedestrian Detection Leveraging YOLOv9: A Thorough Deep Learning Framework for Autonomous Vehicle System

Optimized Pedestrian Detection Leveraging YOLOv9: A Thorough...

引用

Intelligent Signal Processing and Effective Communication Technologies (INSPECT), IEEE International Conference on

作者： Hemant Kumar Pushpa Mamoria Deepak Kumar Dewangan Department of Computer Science & Engineering Chhatrapati Shahu Ji Maharaj University Kanpur India Department of Computer Application Chhatrapati Shahu Ji Maharaj University Kanpur India Department of Computer Science & Engineering ABV-IIITM Gwalior India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

Pedestrian detection for an autonomous vehicle system is the crucial and foremost important aspect for accurate identification of pedestrian on the road scene environment. For this study a YOLOv9-C state-of-the-art deep learning model is used. YOLOv9 is renowned for its accuracy and efficiency in real time application. Model is trained on KITTI dataset. This dataset has a number of classes but for this study only pedestrian class is used. Dataset provides a number of images of urban scene environment where number of objects are there and trained model is perfectly detecting pedestrian in the images. In the YOLOv9 model an additional backbone layer is added for achieving high efficiency and time bound detection. The primary aim of this research is to look for the possible technique by which detection accuracy can be improved. Additional added layer helps in detecting more complex features of pedestrian in the images. After careful observation findings are shows that proposed model has achieved better accuracy in comparison with another models. Experimental results also show that there is a chance for more reliability and responsiveness of object detection if model is trained on diverse dataset. Although this study demands high computational resources which may be a barrier in some sense.

关键词： Deep learning YOLO Training Pedestrians Accuracy Computational modeling Signal processing Feature extraction Autonomous vehicles Software development management

来源：评论

学校读者我要写书评

暂无评论

Research on Ornamental Fish Recognition Base on Improved Shufflenet V2 Network 4

Research on Ornamental Fish Recognition Base on Improved Shu...

引用

4th International Conference on Big Data and Artificial Intelligence and Software engineering, ICBASE 2023

作者： Zhang, Xingyun Chen, Hongming Zhang, Longqing Chen, Qian Zhejiang Ocean University Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhoushan316022 China Guangdong University of Science and Technology School of Computer Science Dongguan523083 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China

ISBN: (纸本)9798350329490

With the advancement of computer vision technology, fish recognition plays a crucial role in various fields such as aquaculture processing and disseminating fish knowledge. In this study, we propose an enhanced and lightweight fish recognition algorithm to accomplish fish classification recognition with limited data samples. Based on the ShuffleNet V2 network, we incorporate Transfer Learning and the SE attention mechanism. Additionally, we replace the ReLu activation function with the AM-Softmax activation function. Comparative evaluations are conducted against Resnet50, MobileNet V2, MobileNet V3, and the original ShuffleNet V2 network model. Our experimental findings demonstrate that the proposed algorithm outperforms the aforementioned models, resulting in recognition accuracy improvements of 16.01%, 19.05%, 15.04%, and 14.44% respectively. The final recognition accuracy achieved is 97.20%, successfully attaining the desired outcome. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Offline Natural Scene Character Recognition Using VGG16 Neural Networks 3

Offline Natural Scene Character Recognition Using VGG16 Neur...

引用

3rd International Conference on Inventive Research in Computing applications, ICIRCA 2021

作者： Dey, Raghunath Balabantaray, Rakesh Chandra Piri, Jayashree Singh, Debabrata Iiit Bhubaneswar Department of Computer Science and Engineering India Soa Bhubaneswar Department of Computer Application India

ISBN: (纸本)9780738146270

Recognizing printed characters is a little easier than when compared to handwritten characters by offline OCR machines. When the images of the characters are taken from the natural scene, they become hazy and in various angles. Then they are harder to recognize, even though they are printed. In this study, an attempt has been made to identify characters that are colored and in different orientations, using a deep convolutional neural network known as VGG16. The effect on classification accuracy with respect to epochs on the datasets is projected by conducting some experiments. Two Latin character datasets have been considered, such as Chars74kImg and Binary alphanumeric. The Chars74kImg dataset consists of RGB isolated character images taken from the real world, while the Binary alphanumeric dataset comprises binary versions of distinct characters in different orientations. With the Chars74kImg dataset, the suggested model obtains the highest accuracy of 78.04%, far better than the previous techniques found in the literature. Finally, along with quantitative analysis, a comparison of the suggested method to a few preexisting systems is presented. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Distill Vision Transformers to CNNs via Teacher Collaboration

Distill Vision Transformers to CNNs via Teacher Collaboratio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sunqi Lin Chong Wang Yujie Zheng Chenchen Tao Xinmiao Dai Yuqi Li Faculty of Electrical Engineering and Computer Science Ningbo University China Zhejiang Engineering Research Center of Advcanced Mass Spectrometry and Clinical Application China

The vision transformer (ViT) has recently emerged as a leading approach in various domains, outperforming other methods. Therefore, it is logical to explore the possibility of transferring the superior knowledge from ViT to more compact and cost-effective convolutional neural networks (CNNs). However, due to substantial architectural disparities in representation and logits between these models, conventional knowledge distillation methods have proven ineffective in this context. To address this issue, a novel cross-architecture knowledge distillation scheme based on teacher collaboration is proposed to alleviate the architecture gap. Two different teachers, i.e. one ViT and one CNN, are utilized to simultaneously distill the student by feature reaggregation and logit correction. The experiments show that the proposed scheme outperforms conventional methods on CIFAR-100 dataset. The code is available at https://***/SunkiLin/RCD.

关键词：

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：