检索结果-内蒙古大学图书馆

International Conference on Computational and Characterization Techniques in engineering & sciences (CCTES)

作者： Komala C R J. Raja Sarange Shreepad Marotrao Nalla Neelima R. Sujatha K. Chidambarathanu Department of Information Science and Engineering East Point College of Engineering and Technology Bengaluru Karnataka India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Mechanical Engineering Ajeenkya D Y Patil School of Engineering Pune Maharashtra India Department of Information Technology R.V.R & J.C. College of Engineering Chowdavaram Andhra Pradesh India Department of Computer Science Subbalakshmi Lakshmipathy College of Science Madurai Tamil Nadu India Department of Computer Science and Business Systems R.M.K. Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

Robotic systems depend much on autonomous navigation since it allows them to operate on their own in environments constantly changing and lacking clarity. The most evolved artificial intelligence (AI) techniques applied in self-driving robot navigation are briefly reviewed in this work. These approaches call for classical methodologies, machine learning, and deep learning as well. We examine the advantages and drawbacks of numerous approaches applied in route planning, location finding, map creation, obstacle avoidance. We investigate how neural networks, sensor fusion, and reinforcement learning may be applied to provide increased dependability and flexibility for guiding systems. Case examples illustrating the advantages and drawbacks of applying artificial intelligence (AI) in practical contexts including service robots, drones, and self-driving cars abound. Combining modern AI algorithms with conventional approaches indicates that it is feasible to create self-driving robots more dependable and efficient based on the increased tracking performance.

关键词： Deep learning Navigation Service robots Neural networks Reinforcement learning Sensor fusion Robot sensing systems Planning Artificial intelligence Drones

来源：评论

学校读者我要写书评

暂无评论

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

arXiv

引用

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

arXiv

引用

arXiv 2023年

作者： Fu, Shenghao Yan, Junkai Gao, Yipeng Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy tradeoff. The code is available at https://***/iSEE-Laboratory/ASAG. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Efficient UAV Path Planning and Energy Optimization with Cooperative System Model for Vehicular Adhoc Networks

Efficient UAV Path Planning and Energy Optimization with Coo...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： A. Veeramuthu Shalini Mahalingam Ilakkia. T R. Sampathkumar T. D. Subha Department of Information Technology School of Computing Sathyabama Institute of Science and Technology Chennai Department of Computer Science and Engineering St.Joseph’s College of Engineering College Chennai Department of Electrical and Electronics Engineering Sona College of Technology Salem Tamilnadu India Department of Mechatronics Engineering KPR Institute of Engineering and Technology Coimbatore Department of Electronics and Communication Engineering R.M.K. Engineering College Chennai Tamilnadu

Vehicular Ad Hoc Networks (VANETs) is a highly trending technology which occupies lots of applications of intelligent communications in day to day life. Typically, vehicles in a vehicular network move at rapid speeds with unpredictable mobility, leading to frequent changes in the network’s structure. Consequently, this might cause some problems while transmitting data between vehicles. In addition, external activities might lead to data loss. In order to overcome certain drawbacks in recent times ground level to air level data connectivity is concentrated which includes the concept of Unmanned Aerial Networks (UAV). The primary obstacles in the construction of UAV is that its network formation and path finding process. For the purpose of overcoming these kinds of drawbacks in this article effective UAV path planning and the energy optimization (EUPEO) is concentrated in the vehicular communication. Through this process the communication is carried out in an effective manner with intelligent path planning of UAV and as well it reduces the delay and energy consumption. The idea is implemented in ns3 and from the final outcome it is obviously proven that the EUPEO method achieved superior results than previous methods concerned with efficiency and as well the delivery rate of the information transmitted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel hybrid classifier synergizing 3D_2D CNN with Support Vector Machine to enhance Hyperspectral image classification

Novel hybrid classifier synergizing 3D_2D CNN with Support V...

引用

International Conference on computing and Networking technology (ICCNT)

作者： Sridevi S V V V Bhagya Sree Sudarshan R PrasannaKumar R Shanmugakumar M Balasubramanian E Surendar G Balachandran S Kanimozhi T Jae Sung Choi Rithani M SCOPE Vellore Institute of Technology Chennai Computer Science and Engg. Amrita School of Computing Chennai CSE Amrita School of Computing Chennai MATIC IIITDM Kancheepuram Mechanical Engineering NITTR Taramani Chennai Aeronautical Engg VelTech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Central Library Amrita School of Computing Chennai ECE VelTech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Department of CSE Sun Moon University Asan-si Korea

Hyperspectral imaging (HSI) is a potent tool that offers accurate identification and analysis of materials and objects in various domains ranging from remote sensing, agriculture, chemo-metric analysis for agricultural products and bio-medical applications, and much more. However, accurately categorizing HSI images remains challenging due to high dimensionality pertaining to spectral resolution in multiple bands, inadequate training samples, and pixel mixing. Deep learning Convolutional Neural Networks (CNN) have undergone development over time to process data of varied dimensions as 1D CNNs were developed to handle time series data, while 2D CNNs operate on spatial image data, and 3D CNNs evolved for processing 3D volumetric data. This paper proposes a synergistic hybrid classifier model that generalizes the 3D_2D CNN deep learning model to extract features from HSI images automatically and a robust Support Vector Machine (SVM) classifier to classify them accurately with less computational efficiency. The prominent intention of this proposed classifier is to be robust in terms of efficiency and less computationally complex. The proposed method involves HSI image dimensionality reduction using principal component analysis (PCA) and 3D_2D convolutional layers to extract significant spectral-spatial features. These feature maps are flattened, which is then used to train the SVM classifier. On the Kennedy Space Centre (KSC) HSI dataset, experimental results demonstrate that the proposed hybrid technique provides excellent accuracy and outperforms the modern techniques regarding classification precision and computational effectiveness. The proposed hybrid 3D 2D CNN synergized with the SVM approach achieved 99.8% accuracy, which is a 1.31% improvement compared to the existing Cube CNN with an SVM similar kind of hybrid classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pondering About Task Spatial Misalignment: Classification-Localization Equilibrated Object Detection

Pondering About Task Spatial Misalignment: Classification-Lo...

引用

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

作者： Yudong Zhang Wei Lu Xu Wang Pengkun Wang Yang Wang School of Data Science USTC Hefei China Suzhou Institute for Advanced Research USTC Suzhou China School of Software Engineering USTC Hefei China Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China (USTC) Hefei China School of Computer Science and Technology USTC Hefei China

Object detection is a fundamental task in computer vision, consisting of both classification and localization tasks. Previous works mostly perform classification and localization with shared feature extractor like Convolution Neural Network. However, the tasks of classification and localization exhibit different sensitivities with regard to the same feature, hence the "task spatial misalignment" issue. This issue can result in a hedge issue between the performances of localizer and classifier. To address these issues, we first propose a novel Dynamic Coefficient Loss to simultaneously consider and balance the performances of classification and localization tasks. To well address anchor label misjudgment issue in irregular- shaped object detection, we define a new classification-aware IoU metric to assign anchors intelligently. Finally, we further introduce the localization factor into NMS by proposing a Classification-Localization balanced NMS. Extensive experiments on MS COCO and PASCAL VOC demonstrate that our proposals can improve RetinaNet by around 1.5% AP with various backbones.

关键词： Location awareness Sensitivity Convolution Neural networks Signal processing algorithms Object detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Fake News Detection Model Using fakenewslingual dataset with Feature Selection

An Ensemble Fake News Detection Model Using fakenewslingual ...

引用

IEEE Conference on Systems, Process & Control (ICSPC)

作者： Hoi Chun Choong Hui Na Chua Muhammed Basheer Jasser Richard T.K. Wong Ghassan Saleh ALDharhani Department of Computing and Information Systems School of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Darul Ehsan Malaysia Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia Faculty of Information Science and Technology UKM University Bangi Selangor Malaysia

ISBN: (数字)9798350391398

ISBN: (纸本)9798350391404

The rapid dissemination of information on social media acts as a double-edged sword, promoting the spread of accurate information and fake news, which can disrupt social cohesion and undermine trust in media and institutions. Existing fake news detection methods often lack feature comprehensiveness and struggle to generalize across different fake news types and sources. This study aims to enhance feature comprehensiveness by incorporating headline features into existing models and improve model generalization through ensemble techniques and hyperparameter tuning. The study expanded an existing dataset with headline, sentiment, and readability features. We assessed the impact of these additional features on model performance and explored various ensemble learning techniques (Bagging, AdaBoost, Gradient Boost) with tailored hyperparameters. An optimal model was then used to build a prototype for real and fake news classification. Integrating headline features showed marginally improved accuracy from 98.63% to 98.66%. While using ensemble learning models and hyperparameter tuning, accuracy increased significantly to 99.34%. This research enriched the dataset with headline features, enhancing the detection model’s accuracy and generalization. The enhanced dataset, which we named fakenewslingual, has been made publicly available for further research. The study underscores the effectiveness of headline features and ensemble models in fake news detection.

关键词： Accuracy Social networking (online) Prototypes Feature extraction Robustness Ensemble learning Fake news Tuning Bagging

来源：评论

学校读者我要写书评

暂无评论

Detection of Covid Disease using Computed Tomography Images

Detection of Covid Disease using Computed Tomography Images

引用

International Conference on computing and Networking technology (ICCNT)

作者： Amrita Tripathi Tripty Singh Bhanu Prakash Kn Kumar Rajamani Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Principal Investigator - Bioinformatics Institute A*Star Bioinformatic Institute Singapore Faculty of Engineering and Technology Marwadi Education Foundation’s Group of Institutions Gujarat India

After emerging in Wuhan, China, in December 2019, the coronavirus 2019 (COVID-2019) quickly spread throughout the world and sparked a pandemic. Covid-19 The pandemic affected human health globally. In a few cases of Covid19 humans faced death situations also. The Respiratory system of the human body gets affected by Covid-19 and the severity of Covid-19 leads to death so there is urgent need of fast and efficient automatic diagnosis system of Covid-19 to help medical experts to diagnose this disease quickly and efficiently. This paper’s main objective is to provide a Binary Classification of Covid-19 disease using a dataset obtained from computed tomography. Four Deep Learning existing models ResNet50, Inception V3, DenseNet121 and Efficient Net B0 are employed here. Compared to ResNet50, InceptionV3, and Efficient Net B0, DenseNet121 performs better. DenseNet121 model showed 96.83% as training accuracy and 92% as validation accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The stratified K-folds cross-validation and class-balancing methods with high-performance ensemble classifiers for breast cancer classification

引用

Healthcare Analytics 2023年 4卷 100247-100247页

作者： T R, Mahesh V, Vinoth Kumar V, Dhilip Kumar Geman, Oana Margala, Martin Guduri, Manisha Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore 562112 India School of Computer Science Engineering & Information Systems (SCORE) Vellore Institute of Technology (VIT) 632014 India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai 600062 India Department of Computers Electronics and Automation Faculty of Electrical Engineering and Computer Science Stefan cel Mare University of Suceava Suceava 720229 Romania School of Computing and Informatics University of Louisiana at Lafayette United States

Breast cancer is one of the most common causes of death among women, and early diagnosis is vital for reducing the fatality rate. This study evaluates the most widely used machine-learning breast cancer prediction and diagnosis methods. We use synthetic minority over-sampling to handle imbalanced data in the breast cancer diagnosis dataset obtained from the Wisconsin Machine Learning Repository. We use a variety of machine learning algorithms, including Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Classification and Regression Tree (CART), Naive Bayes (NB), and well-known ensembles methods like Majority-Voting, eXtreme Gradient Boosting algorithm (XGBoost), and Random Forest (RF) for the breast cancer classification. The findings show that the Majority-Voting ensemble method, built on the top three classifiers (LR, SVM, and CART), outperforms all other individual classifiers and offers the highest accuracy of 99.3%. © 2023 The Author(s)

关键词： Breast cancer Class-balancing Cross-validation Diagnostic analytics Ensemble method Machine learning

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via...

引用

International Conference on computer Vision (ICCV)

作者： Shenghao Fu Junkai Yan Yipeng Gao Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy trade-off. The code is available at https://***/iSEE-Laboratory/ASAG.

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：