检索结果-内蒙古大学图书馆

Small Object Detection via Precise Region-Based Fully Convolutional Networks

computers, Materials & Continua 2021年第11期69卷 1503-1517页

作者： Dengyong Zhang Jiawei Hu Feng Li Xiangling Ding Arun Kumar Sangaiah Victor SSheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India Department of Computer Science Texas Tech UniversityLubbock79409TXUSA

In the past several years,remarkable achievements have been made in the field of object *** performance is generally improving,the accuracy of small object detection remains low compared with that of large object *** addition,localization misalignment issues are common for small objects,as seen in GoogLeNets and residual networks(ResNets).To address this problem,we propose an improved region-based fully convolutional network(R-FCN).The presented technique improves detection accuracy and eliminates localization misalignment by replacing positionsensitive region of interest(PS-RoI)pooling with position-sensitive precise region of interest(PS-Pr-RoI)pooling,which avoids coordinate quantization and directly calculates two-order integrals for position-sensitive score maps,thus preventing a loss of spatial precision.A validation experiment was conducted in which the Microsoft common objects in context(MS COCO)training dataset was *** showed an accuracy improvement of 3.7%for object detection tasks and an increase of 6.0%for small objects.

关键词： Small object detection precise R-FCN PS-Pr-RoI pooling two-stage detector

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Detection and Classification Using NLP

Hate Speech Detection and Classification Using NLP

引用

International Conference on Advances in Information Technology (ICAIT)

作者： Syed Shahidh Ilhan Soubraylu Sivakumar Nagaraj J S. Ramesh N. Sreeram Ratnavel Rajalakshmi Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Computer Science & Engineering Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Detected hate speech instances are appropriately classified, rebuilding the intricate landscape of disparaging language in an increasingly digitized society. We present an exhaustive analysis of the techniques, gravitating towards their efficiency, precision, and capability to adapt to the evolving dynamics of language manifestation online. The study uncovers fascinating insights into the relative strengths, weaknesses, limitations, and potential areas of improvement of Bi-LSTM and the Bi-LSTM with GRU in the realm of hate speech detection and classification. The results of Bi-LSTM with GRU has obtained an accuracy of 95% with an improvement of 1% over Bi-LSTM model. Serving as a cornerstone in the burgeoning NLP research, our findings provide promising direction and robust groundwork for future improvements and attempts in the continuous drive towards safer, more respectful digital communication platforms.

关键词： Adaptation models Accuracy Hate speech Focusing Digital communication Information technology

来源：评论

学校读者我要写书评

暂无评论

A Heuristic-based Dynamic Scheduling and Routing Method for Industrial TSN Networks 10

A Heuristic-based Dynamic Scheduling and Routing Method for ...

引用

10th IEEE International Conference on Cyber Security and Cloud computing and 9th IEEE International Conference on Edge computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Chen, Honglong Liu, Mindong Huang, Jing Zheng, Zhiling Huang, Weihong Xiao, Yufeng Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan411201 China Hunan Industry Polytechnic Information Center Changsha410125 China

ISBN: (纸本)9798350312461

In the industrial environment, machines often need to reflect the anomaly detection results to the total control center in time, and the general industrial network can not achieve high real-time. In order to solve such challenges, a set of protocol standards developed by IEEE802.1 working group, namely Time-sensitive Networking (TSN), has been introduced into industrial networks. TSN can provide high real-time and reliability for data transmission, where the reliability is achieved by Frame duplication and Frame Elimination (FRER). In the realization process of FRER, it is necessary to determine the source node, destination node, and multiple disjoint paths to transmit redundant data. However, the transmission of these redundant traffic may result in the delay of other flows, and then affects the user experience. Therefore, it is very important to choose excellent redundant traffic paths to ensure reliability and reduce the impact on other flows. In the existing research, there are many dynamic scheduling and routing heuristics to determine the path, but they do not consider the influence of the location of the source node on the whole route scheduling. This paper proposes an improved dynamic scheduling and routing heuristic method, which takes the source node into account in the routing selection. In the flow test experiments of different magnitudes, it is found that the total delay of all flows is reduced by 1.4%-4.5% under the same magnitude of schedulability compared with Ant Colony Optimization. © 2023 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Verification of Educational and Professional Certificates

Blockchain Based Verification of Educational and Professiona...

引用

International Conference on Computational Systems and Communications (ICCSC)

作者： Anjali Singh SPS Chauhan Amit Kumar Goel Master of Technology in Computer Science and Engineering School of Computing Science and Engineering Galgotias University Greater Noida India School of Computing Science and Engineering Galgotias University Greater Noida India

Educational Documents and Certificates are a proof of professional achievements for anyone. Without these documents, it is not possible to start your career and hence play a very important role in everyone's professional life. Till date, Colleges, Universities and various educational institutes issue paper based degrees and certificates which are prone to get damaged or may be lost. The other drawback is that this process of issuing of degrees and manual process of verification of those documents by third parties is a time taking and cumbersome process. The employers take a lot of time for verifying these paper based degrees and certificates before they give the job offer. Forgery of paper based documents is also easier and has led to many educational scams. This paper aims to give the solution to the problems mentioned above through Blockchain Implementation. Block chain technology is not only limited to crypto currencies but is also of great applications in various fields like health, supply chain management, finance, etc. It has disrupted the traditional education system. This paper highlights as to how the educational certificates can be verified using the Ethereum platform and smart contracts. The traditional paper certificates would be converted to digital certificates on student's request, their hash value would be calculated using cryptographic hash functions and stored on Blockchain. A unique certificate ID and transaction hash value would be generated which would then be used to verify the certificates through a common platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Corn Leaf Diseases using Various Pre-trained Deep Learning Networks and Performance Comparison

Classification of Corn Leaf Diseases using Various Pre-train...

引用

2022 International Conference on Advances in computing, Communication and Materials, ICACCM 2022

作者： Srivastava, Prateek Singh, Shailendra Pratap Vishnoi, Ankit Sapra, Varun Graphic Era Hill University Department of Computer Science and Engineering Uttarakhand Dehradun India School of Computing Science and Engineering Galgotias University U.P. Greater Noida India

ISBN: (纸本)9781665474399

Corn is an important crop that feeds millions of hungry people. Many farmers rely on it for income. However, diseases that affect corn production are common, resulting in significant financial losses for farmers. Although high-quality pesticides are available to save plants from diseases, but complete safety cannot be guaranteed. As a result, plants are susceptible to a variety of diseases throughout their life cycle. As a result, if a timely cure is not taken, plants may be damaged, affecting production quality. Hence, correct diagnosis is essential for timely cure. Several researchers have shared their models for identifying corn diseases using deep learning and machine learning. The correct identification of disease aids in the timely implementation of safe measures. For feature extraction, various pre-trained networks such as LeNet-5, AlexNet, MobileNetV2, and VGG16 were considered in this work. This feature set is then passed on to the envisaged fully connected neural network. The classification using AlexNet has been reported to be the most accurate, with an accuracy of 99.40 percent. The Mendeley's dataset is employed for training, validation, and testing in this research. For a deeper understanding, various performance metrics have been compared and discussed. The F1-score measured for each class indicates the classification's strength of models. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MRI Breast Image Segmentation Using Artificial Bee Colony Optimization with Fuzzy Clustering and CNN Classifier

MRI Breast Image Segmentation Using Artificial Bee Colony Op...

引用

International Conference on Intelligent Systems and Sustainable computing, ICISSC 2021

作者： Sumathi, R. Vasudevan, V. Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Krishnankoil India School of Computing Kalasalingam Academy of Research and Education Krishnankoil India

ISBN: (纸本)9789811900105

Breast cancer is the most leading disease for women and many lost their lives without proper treatment and early diagnosis helps to reduce the death rate. In clinical procedure identifying the tumor take much processing time and extracting the abnormal part leads error at some time. To overcome this problem and helps the radiologist an automated framework with the integration of artificial bee colony and fuzzy C means clustering for extracting the cancerous part and classify the tumor as benign and malignant with CNN classification. Various objective measures like entropy, eccentricity, contrast, correlation, homogeneity, mean, variance, kurtosis, dice similarity index, hands-off distance and subjective measures like precision, recall, accuracy, MSE, PSNR were evaluated to ensure the efficiency and accuracy of segmentation and classification of MRI breast images with T1, T2—contrast enhanced images. Our hybrid approach yield 98% segmentation accuracy and 98.6% classification accuracy and it take average of 5 s for processing. We utilized public dataset like DDSM, MIAS and INbreast dataset for validation. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

An Optimized Deep Learning Approach To Identfiy the Alzheimer's Stages Identification Based on Biomarkers Extraction

An Optimized Deep Learning Approach To Identfiy the Alzheime...

引用

2023 Intelligent computing and Control for engineering and Business Systems, ICCEBS 2023

作者： Sampath, R. Baskar, M. School of Computing Srm Institute of Science and Technology Department of Computer Science and Engineering Chengalpattu Tamilnadu Kattankulathur603203 India Sri Sai Ram Institute of Technology Department of Information Technology Tamilnadu Chennai600044 India

ISBN: (纸本)9798350394580

Alzheimer's is a progressive brain disorder. It affects human brain cell connections;as a result, it creates memory losses and other significant mental functional problems. The diagnosis of early stages of Alzheimer's and proper medication helps control the disease's progression since Alzheimer's is not a curable disease. The precise prediction of AD stages is an open challenge for researchers. Therefore, Researchers are developing lots of Alzheimer's disease (AD) detection techniques to predict the stages accurately. Most AD detection approaches contain several issues and can't reach the maximum accuracy rate. Therefore, this research introduces an efficient AD stages detection approach to solve the accuracy issues. This research customizes two aspects of the present systems to achieve the research objective. Initially, the appropriate adaptation of the AD stage's MRI brain image processing methodologies is enhancing the biomarker regions detection accuracy, and then the AD stage detection accuracy is improved by an optimized deep learning model. In this, the characteristics of the cuckoo search optimizer are incorporated in the Deep Belief Network (DBN) to optimize the AD stages detection functionalities of the AD detection algorithm, which helps to reduce the detection error. The AD detection approach's performance is evaluated using evaluation metrics such as accuracy, correlation coefficient, precision, Mean absolute error (MAE), Root Mean Square Error (RMSE), and Signal to Noise ratio SNR. The evaluation results prove that the accuracy of the AD stages detection approach is increased up to 0.66%, and the detection error is reduced up to 0.0345 % than the comparison approaches. © 2023 IEEE.

关键词： Alzheimer detection Alzheimer's disease deep learning MRI images optimizer

来源：评论

学校读者我要写书评

暂无评论

A computer Vision Model for Detecting Suspicious Behaviour from Multiple Cameras in Crime Hotspots Using Convolutional Neural Networks 20th

A Computer Vision Model for Detecting Suspicious Behaviour f...

引用

20th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2022

作者： Esan, Omobayo A. Osunmakinde, Isaac O. School of Computing College of Science Engineering and Technology University of South Africa Pretoria South Africa Computer Science Department College of Science Engineering and Technology Norfolk State University NorfolkVA United States

ISBN: (纸本)9783031186967

Conventional security surveillance systems detect suspicious behaviours by the active participation of human operators constantly watching monitors showing video streams of activities captured from different cameras. The datasets are manually retrieved and analyzed after the occurrence of the incidents. This often leads to misinterpretation and late detection in a real-life environment. Recent studies have investigated the current surveillance systems for the challenges of the detection of suspicious incidents. The research question here is: How can suspicious breaking into run be detected being a common red flag leading to most crimes? This research develops a computer vision framework based on feature engineering, convolutional neural network (CNN), and median filtering to address the lacuna faced by the surveillance systems. Experiments were conducted on real-life image frames captured from multiple camera datasets. The proposed model outperforms the conventional approaches in terms of the detection of suspicious behavioural patterns with an average F1-score of 0.9661, a false positive rate of 0.0734, and an accuracy of 94.81%. The deployment of this proposed model in a crowded environment can help to augment the work of security personnel in raising awareness regarding possible crime at hot spots. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation 39

RETIA: Relation-Entity Twin-Interact Aggregation for Tempora...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Liu, Kangzheng Zhao, Feng Xu, Guandong Wang, Xianzhi Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan China University of Technology Sydney Data Science and Machine Intelligence Lab Sydney Australia

ISBN: (纸本)9798350322279

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations;therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands"problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://***/CGCL-codes/RETIA. © 2023 IEEE.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning for Truth Inference

Graph Contrastive Learning for Truth Inference

引用

International Conference on Data engineering

作者： Hao Liu Jiacheng Liu Feilong Tang Peng Li Long Chen Jiadi Yu Yanmin Zhu Min Gao Yanqin Yang Xiaofeng Hou School of Data Science and Engineering East China Normal University Shanghai China Department of Computer Science and Engineering Chinese University of Hong Kong China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering University of Aizu Japan School of Computing Science Simon Fraser University Canada

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Crowdsourcing has become a popular paradigm for collecting large-scale labeled datasets by leveraging numerous annotators. However, these annotators often provide noisy labels due to varying expertise. Truth inference aims to infer accurate consensus labels from noisy crowdsourced annotations. Existing approaches rely heavily on hand-engineered assumptions or ground truth data, limiting their applicability. To address this, we propose GOVERN, a graph contrastive learning framework for truth inference without such external supervision. GOVERN employs a novel graph data augmentation strategy to generate views capturing worker coordination patterns. A contrastive objective then encourages invariant representations across views, enabling the discovery of features related to the hidden consensus. Further, a label correction method based on k-nearest neighbors refines noisy pseudo-labels to supervise model training. Comprehensive experiments on 9 real-world datasets demonstrate that GOVERN outperforms state-of-the-art truth inference techniques.

关键词： Training Crowdsourcing Limiting Accuracy Annotations Contrastive learning Nearest neighbor methods

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：