检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xing, Haozhe Gao, Shuyong Tang, Hao Mok, Tsui Qin Kang, Yanlan Zhang, Wenqiang Information Technology and Electrical Engineering Eth Zurich Zurich Switzerland Fudan University Academy for Engineering & Technology Shanghai China Fudan University School of Computer Science Shanghai China

ISBN: (纸本)9781728163277

关键词： Camouflaged object detection edge features feature fusion image segmentation lightweight model

来源：评论

学校读者我要写书评

暂无评论

I-DLMI: Web Image Recommendation Using Deep Learning and Machine Intelligence 22nd

I-DLMI: Web Image Recommendation Using Deep Learning and Mac...

引用

22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022

作者： Kannan, Beulah Divya Deepak, Gerard Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9783031274084

Web Image Recommendation is the need of the hour because of the increasing exponential contents especially the multimedia content in the World Wide Web. The IDLMI framework has been proposed which is a query centric knowledge driven approach for Web Image recommendation. This model hybridizes Wiki Data and YAGO for entity enrichment and generation of Meta Data takes place which is further subjected to semantic similarity computation and mapped reduce algorithm for mapping and reducing the complexity within the Pearson’s correlation coefficient. LSTM (Deep Learning Intrinsic Classifier) is used for automatic classification of data set. The model also classifies the data for upper ontology which enhances auxiliary knowledge. Performance of the proposed I-DLMI framework approach is calculated by utilizing F-measure, Precision, Recall, Accuracy percentages and False Discovery Rate (FDR) as the potential metrics. The proposed model furnishes the largest average precision of 96.02%, largest average recall percentage of 98.19%, largest average accuracy percentage of 97.10% and the largest F-measure percentage of 97.09%, while the lowest FDR is 0.17. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Bi-CSem: A Semantically Inclined Bi-Classification Framework for Web Service Recommendation 13th

Bi-CSem: A Semantically Inclined Bi-Classification Framework...

引用

13th International Conference on Innovations in Bio-Inspired Computing and Applications, IBICA 2022, and 12th World Congress on Information and Communication Technologies, WICT 2022

作者： Surya, Deepak Palvannan, S. Deepak, Gerard Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9783031274985

Web services are products in the era of service-oriented computing and cloud computing. As the number of web services on the Internet grows, selecting and recommending them becomes more important. Consequently, in the realm of service computing, how to propose the finest Web services for researchers is now a popular research topic. To determine the proper recommendation, the BI-CSem model was proposed and tested with multiple baseline models using real-world Web Service datasets in this research. Aside from that, thesaurus is built using Web service keywords gathered from Web service repositories such as UDDI,WSDI, and from the World Wide Web Cloud. The extracted terms are then subjected to semantic similarity, which is determined using SemantoSim, Concept similarity, and KL divergence measure, and the terms from the user, such as query, user click, and previous historical data, are pre-processed the terms from the semantic alignment are then classified using XGBoost, while the Web service dataset is classified using XGBoost and GRU. Semantic similarity is determined using just SemantoSim, based on the classification intersection of the top 75 percent words from the extracted terms from the two classifiers and features from the created intermediate term tree generated using STM. Finally, terms are reranked and recommended to the user, and the precision, accuracy, recall, F-measure, and FDR for the Web service recommendation system are calculated, and the Bi-CSem model is found to have an excellent precision percentage of 94.37% and the lowest FDR of 0.06. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

An Extended Deep Learning and Feature Pyramid Based Network for Screening CT-Scans Images 6

An Extended Deep Learning and Feature Pyramid Based Network ...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Pandey, Dhiraj Pandey, Kavita JSS Academy of Technical Education Department of Information Technology Noida India Jaypee Institute of Information Technology Department of Computer Science Engineering & IT Noida India

ISBN: (纸本)9798350304480

Deep convolution neural Network is basically using a methodology to teach computer systems in the same way as humans learn by using examples and through experiences. It is a method of solving exhaustive image processing problems by using a heuristic-based approach. The objective of this research is to develop an extended deep learning-based hybrid method to detect abnormal symptoms using CT-scan Images. The detection of abnormal in any infected people is the most challenging issue due to less medical facility and time required to confirm its correctness based on the test conducted. Many AI-based approaches are suggested by researchers but most of the work is not integrated as a working model because of its correctness and accuracy level. The proposed work is implemented using Python and TensorFlow library. For experimentation, the CT-scan dataset is used with two different classes like normal or abnormal in nature. The proposed hybrid approach takes an input of CT-SCAN images from the selected data sets, converts it into grayscale, and then into. tiff format to get a more specific feature suitable for preprocessing step of the deep convolution network. Feature pyramid network has also been used on the selected images which provides better results in terms of low-level features in the deeper convolution networks. This hybrid methodology is helping us to get better results in comparison to state of art available. The implemented extended deep CNN network can accurately recognize varieties of real test cases CT-scans images. The learning accuracy of the hybrid method of RESNET101V2 with Feature pyramid network (FPN) and preprocessed dataset is up to 98.68 percent and it is maximizing the standard available state of art technique by a good margin in terms of result accuracy. © 2023 IEEE.

关键词： Abnormal computer Vision Deep Convolution Neural Network Feature pyramid network Image classification Residual Network

来源：评论

学校读者我要写书评

暂无评论

Automatic Liver Segmentation from Multiphase CT Using Modified SegNet and ASPP Module

引用

SN computer science 2024年第4期5卷 377页

作者： Nayantara, P. Vaidehi Kamath, Surekha Kadavigere, Rajagopal Manjunath, Kanabagatte Nanjundappa Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Radiodiagnosis and Imaging Kasturba Medical College Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India

Liver cancer is one of the dominant causes of cancer death worldwide. Computed Tomography (CT) is the commonly used imaging modality for diagnosing it. computer-based liver cancer diagnosis systems can assist radiologists in image interpretation and improve diagnosis speed and accuracy. Since liver segmentation is crucial to such systems, researchers are relentlessly pursuing various segmentation approaches. A clinically viable computer-aided system requires examining multiphase CT images. However, most of the research focuses only on the portal venous phase. In this work, we developed an automatic and efficient Deep Learning (DL) method using SegNet, atrous spatial pyramid pooling module and leaky ReLU layers for liver segmentation from quadriphasic abdominal CT volumes. The proposed method was validated on two datasets, an internal institutional dataset consisting of multiphase CT and a public dataset of portal venous phase CT volumes. The Dice Coefficients (DC) obtained were greater than 96% for the latter dataset and the portal venous phase of the former. For arterial, delayed and plain CT phases of the former dataset, the DC achieved were 94.61%, 95.01% and 93.23%, respectively. Experiments showed that our model performed better than the other state-of-the-art DL models. Ablation studies have revealed that the proposed model leverages the strengths of all the three components that make it up. The promising performance of the proposed method suggests that it is appropriate for incorporation in hepatic cancer diagnosis systems. © The Author(s) 2024.

关键词： Atrous spatial pyramid pooling Computed tomography computer-aided diagnosis Liver cancer Liver segmentation SegNet

来源：评论

学校读者我要写书评

暂无评论

A Review on Detection of Lung Cancer Using Ensemble of Classifiers with CNN 2

A Review on Detection of Lung Cancer Using Ensemble of Class...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Geethu Lakshmi, G. Nagaraj, P. Subhashini, S.J. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Viruthanagar Krishnankovil India Srm Madurai College of Engineering and Technology Department of Information Technology Madurai Sivagangai India

ISBN: (纸本)9798350347579

A thorough understanding of lung cancer and tumor development pathways has made significant advancements in lung cancer treatment. Lung cancer diagnosis and treatment in its early stages still require new techniques. Recent advancements in genetics, computational biology, and other technologies provide an opportunity to better understand the immunological landscape associated with early-stage lung carcinogenesis and the mechanism of lung cancer evolution. This review focuses on immunoediting and discusses new research on immunological alterations and biomarkers in pulmonary premalignancy and early-stage non-small cell lung cancer. By concentrating on developing innovative techniques for intercepting cancer before it advances to later stages, researchers have the potential to revolutionize lung cancer therapy and significantly improve clinical outcomes. The use of an Ensemble of Classifiers with a Convolution Neural Network could further enhance this approach. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Tomographic SAR imaging with large elevation aperture: a P-band small UAV demonstration

引用

science China(Information sciences) 2022年第3期65卷 211-224页

作者： Tao ZENG Minkun LIU Yan WANG Zegang DING Linghao LI Zhen WANG Yangkai WEI Jianping WANG Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Yangtze Delta Region Academy of Beijing Institute of Technology Faculty of Electrical Engineering Mathematics and Computer Science (EEMCS) Delft University of Technology

Elevation resolution is an important indicator in tomographic SAR imaging as it represents the ability to discriminate closed targets in elevation. In general, the elevation resolution is proportional to the length of the elevation aperture. However, as the elevation aperture increases, the geometric consistency of the image will undesirably deteriorate and hence fails the image coregistration approach required by the traditional super-resolution tomographic imaging. In this paper, a new super-resolution tomographic imaging method is proposed to overcome the inconsistency problem caused by the large elevation aperture. The core strategy is to get rid of two-dimensional image coregistration by applying a three-dimensional(3 D) back projection like imaging manner: the 3 D space is firstly divided into a 3 D imaging grid, each of which is individually imaged via compressive sensing for super-resolution. The effectiveness of the proposed approach is evaluated by both computer simulations and real P-band UAV SAR data.

关键词： UAV SAR tomography large elevation aperture super-resolution P-band

来源：评论

学校读者我要写书评

暂无评论

A novel stable feature selection algorithm for machine learning based intrusion detection system 4

A novel stable feature selection algorithm for machine learn...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Sowmya, T. Mary Anita, E.A. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal576104 India Bangalore India Karnataka Bengaluru560074 India

The advent of new technologies like artificial intelligence, and big data has influenced many cyber attackers to launch their attacks on the network. Hence researchers have already proposed Intrusion Detection Systems by incorporating machine learning as well. Building an effective IDS is still a challenging task because of low accuracy. Managing high dimensional data is another major problem that occurs in IDS. Hence in this paper, an efficient Machine Learning based Intrusion Detection System is developed by means of a novel stable feature selection strategy called IV-RFE. The proposed methodology aims to select only the relevant features that contribute to the attack, which is purely based on relative variance, and weight factor in combination with RFE. This methodology increases the performance in terms of accuracy and maintains a stable set of features. Previous studies only focussed on the feature selection strategy and their performance. The feature stability also has to be considered which is an equally important metric, especially in the field of Intrusion Detection Systems. Hence in the current study, an efficient ML based IDS is proposed which selects only the relevant and stable features. Experimental results also revealed that the proposed IV-RFE outperformed well for three attacks with respect to accuracy and stability metrics also. The results show that stability is also an important indicator in selecting the features in the field of Intrusion Detection Systems. © 2025 The Authors. Published by Elsevier B.V.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Ontology Integration for Cultural Landscape Management Using ML and Assistive Artificial Intelligence

Ontology Integration for Cultural Landscape Management Using...

引用

International Conference on Data science, Computation and Security, IDSCS 2023

作者： Gunasheelan, Akshith Deepak, Gerard Department of Electronics and Communication Engineering BMS College of Engineering Bull Temple Road Bengaluru India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9789819709748

This paper introduces an automatic ontology model for rare domains, with a focus on cultural landscape management, characterized by internationalization and inter-country relationships. The model fully automates ontology generation by extracting categories and informative terms from the dataset, applying topic modeling, and enriching metadata using generated topics. It strengthens knowledge by incorporating glossary indexes from e-books and leveraging Wikidata. Categorization is achieved through a deep-learning GRU classifier. Semantic relevance is computed using NPMI, PMI, and Petraitis index with differential thresholds, enhancing reasoning infrastructure. The model achieves a high precision of 95.06%, a low False Discovery Rate of 0.05, and an impressive F-measure of 96.06%. This research makes a significant contribution to automatic ontology conception, particularly in rare domains like cultural landscape management. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Protein Residue Contact Prediction Based on Deep Learning and Massive Statistical Features from Multi-Sequence Alignment

引用

Tsinghua science and technology 2022年第5期27卷 843-854页

作者： Huiling Zhang Min Hao Hao Wu Hing-Fung Ting Yihong Tang Wenhui Xi Yanjie Wei Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China College of Electronic and Information Engineering Southwest UniversityChongqing 400715China School of Software Engineering University of Science and Technology of ChinaHefei 230051China Department of Computer Science The University of Hong KongHong Kong 999077China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Sequence-based protein tertiary structure prediction is of fundamental importance because the function of a protein ultimately depends on its 3 D *** accurate residue-residue contact map is one of the essential elements for current ab initio prediction protocols of 3 D structure ***,with the combination of deep learning and direct coupling techniques,the performance of residue contact prediction has achieved significant ***,a considerable number of current Deep-Learning(DL)-based prediction methods are usually time-consuming,mainly because they rely on different categories of data types and third-party *** this research,we transformed the complex biological problem into a pure computational problem through statistics and artificial *** have accordingly proposed a feature extraction method to obtain various categories of statistical information from only the multi-sequence alignment,followed by training a DL model for residue-residue contact prediction based on the massive statistical *** proposed method is robust in terms of different test sets,showed high reliability on model confidence score,could obtain high computational efficiency and achieve comparable prediction precisions with DL methods that relying on multi-source inputs.

关键词： multi-sequence alignment residue-residue contact prediction feature extraction statistical information Deep Learning(DL) high computational efficiency

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：