检索结果-内蒙古大学图书馆

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

An Adaptive Deep Learning Framework for Human Activity Recognition using Video Data 5

An Adaptive Deep Learning Framework for Human Activity Recog...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Chejarla Raja, S. Arivazhagan, D. Lavanya, S. Rajeswari, C. Banu, S. Rahmaan, K. Anna University Faculty of Information and Communication Engineering Tamil Nadu Chennai India Academy of Maritime Education and Training Deemed to be University Amet Business School Kanathur Chennai India Kcg College of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331522100

This research presents a dual-pathway SlowFast network in order to provide a novel approach for the recognition of human actions. The method has the ability to capture low-intensity as well as high-intensity activities efficiently. The model is trained on two different datasets: one on the routine activities, such as sitting and walking, and the other on complex sports and leisure activities. The SlowFast network increases the accuracy in a wide variety of scenarios by incorporating high-level spatial context along with fast motion characteristics using a dual-path architecture. The proposed model outperforms the conventional HAR methods on different grounds such as adaptability and accuracy, and thus aptly useful for applications such as security surveillance, healthcare, and sports analysis. This approach brings forth a robust system able to identify a range of human actions in static as well as dynamic environments by removing some of the limitations from existing HAR models. © 2025 IEEE.

关键词： Deep learning

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

Conformal Graph-level Out-of-distribution Detection with Adaptive Data Augmentation 25

Conformal Graph-level Out-of-distribution Detection with Ada...

引用

34th ACM Web Conference, WWW 2025

作者： Lin, Xixun Cao, Yanan Sun, Nan Zou, Lixin Zhou, Chuan Zhang, Peng Zhang, Shuai Zhang, Ge Wu, Jia Institute of Information Engineering Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Cyber Science and Engineering Wuhan University Wuhan China Academy of Mathematics and Systems Science CAS School of Cyber Security University of Chinese Academy of Sciences Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Academy of Mathematics and Systems Science CAS Beijing China School of Computer Science and Technology Donghua University Shanghai China Department of Computing Macquarie University Sydney Australia

ISBN: (纸本)9798400712746

Graph-level out-of-distribution (OOD) detection, which attempts to identify OOD graphs originated from an unknown distribution, is a vital building block for safety-critical applications in Web and society. Current approaches concentrate on how to learn better graph representations, but fail to provide any statistically guarantee on detection results, therefore impeding their deployments in the scenario where detection errors would result in serious consequences. To overcome this critical issue, we propose the Conformal Graph-level Out-of-distribution Detection (CGOD), extending the theory of conformal prediction to graph-level OOD detection with a rigorous control over the false positive rate. In CGOD, we develop a new aggregated non-conformity score function based on the proposed adaptive data augmentation. Through the guidance from two designed metrics, i.e., score consistency and representation diversity, our augmentation strategy can generate multiple non-conformity scores, and aggregating these generated non-conformity scores together is robust to the misleading information. Meanwhile, our score function can perceive the subsequent process of conformal inference, enabling the aggregated non-conformity score to be adaptive to different input graphs and deriving a more accurate score estimation. We conduct experiments on multiple real-world datasets with different empirical settings. Extensive results and model analyses demonstrate the superior performance of our approach over several competitive baselines. © 2025 Copyright held by the owner/author(s).

关键词： Network theory (graphs)

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

Comparative Evaluation of Pose Estimation Models for Underwater Hydrotherapy Gait Analysis 5

Comparative Evaluation of Pose Estimation Models for Underwa...

引用

5th International Conference on Smart Sensors and Application, ICSSA 2024

作者： Mekki, Amr Emad Dawood, Aly Khaled Khairuddin, Uswah Eissa, Noureldin S. Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia Department of Computer Engineering Arab Academy for Science Technology and Maritime Transport Cairo2033 Egypt

ISBN: (纸本)9798350354294

Hydrotherapy provides health advantages, such as reducing pain, enhancing blood circulation and easing symptoms. Making use of cutting edge motion capture technology, the detection of poses without markers has emerged as a tool for examining exercise patterns for hydrotherapy patients. This research assesses the effectiveness of four pose estimation models—OpenPose, MediaPipe Pose, AlphaPose and YOLOv7—in extracting and analyzing human gait pose specifically under challenging underwater conditions (i.e: camera positioning, complex backgrounds, underwater imaging issues, and the absence of head connections). A dedicated dataset of hydrotherapy movements was developed to evaluate model accuracy. Findings revealed that YOLOv7 and AlphaPose outperformed the other techniques. YOLOv7 achieved the highest accuracy in scenarios involving multiple participants, delivering near-perfect results for single-person exercises both on land and underwater. For four-person exercises underwater, AlphaPose had an average accuracy of 90.6%, while YOLOv7 slightly outperformed it with an accuracy of 93%. © 2024 IEEE.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing students' learning achievements, self-efficacy, and motivation using mobile augmented reality

引用

Journal of computer Assisted Learning 2024年第4期40卷 1823-1837页

作者： Aldeeb, Fatimah H. Sallabi, Omar M. Elaish, Monther M. Hwang, Gwo-Jen Computer Network College of Computer Technology Benghazi Libya Computer Science The Libyan Academy Benghazi Libya Software Engineering Information Technology Faculty University of Benghazi Benghazi Libya Computer Science Information Technology Faculty University of Benghazi Benghazi Libya Graduate Institute of Educational Information and Measurement National Taichung University of Education Taichung City Taiwan Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei City Taiwan Yuan Ze University Taoyuan City Taiwan

Background: This paper examines the use of augmented reality (AR) as a concept-association tool in schools, with the aim of enhancing primary school students' learning outcomes and engagement. Conflicting findings exist in previous studies regarding the cognitive load of AR-enriched learning, with some reporting reduced load and others indicating increased demand and poorer performance. Understanding these implications is essential for effectively leveraging AR in education. The study offers a fresh perspective on the potential of AR technology in improving educational experiences. Objectives: The primary goal of this research was to evaluate the effectiveness of an AR-assisted concept-association strategy for improving essential knowledge acquisition and skills outcomes, increasing cognitive load, and increasing self-efficacy and learning motivation among primary school students. Methods: A quasi-experimental design with a control group was employed to investigate the effectiveness of the intervention. Results and Conclusions: The results demonstrate that the implementation of the AR-assisted concept-association strategy effectively enhanced essential knowledge acquisition and skills outcomes, increased cognitive load, and increased self-efficacy and learning motivation among primary school students. These findings highlight the potential of AR technology to improve the learning experience and engagement of primary school students. The study contributes to the existing literature on the effectiveness of AR technology in education, suggesting future research directions. Ultimately, it offers a practical solution for improving the learning experience by presenting a new approach for teaching using AR technology. © 2024 John Wiley & Sons Ltd.

关键词： augmented reality biology education cognitive load learning motivation mobile learning self-efficacy

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：