检索结果-内蒙古大学图书馆

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Gupta, Priti Tarafdar, Anirban Basu, Tanmay Shaikh, Azharuddin Bhattacharya, Paritosh Nit Agartala Dept. of Mathematics Agartala India Iiser Bhopal Dept. of Data Science and Engineering Bhopal India

ISBN: (纸本)9798331540821

Analyzing MRI scans is complex due to the often blurry boundaries and inconsistent sizes of tumors, leading to variability in results. This study underscores the critical role of hyperparameter tuning in optimizing 3D U-Net models for accurate brain MRI segmentation, using the BraTS 2020 dataset. Key parameters, including learning rate, optimizer, and batch size, were systematically adjusted to assess their impact on model performance. Identifying the optimal configuration proved challenging, addressed effectively using MARCOS and MAIRCA multicriteria decision methods. The optimal configuration, featuring a learning rate of 0.0001 and the Adam optimizer, achieved an accuracy of 0.966 and a precision of 0.978. This finely tuned 3D U-Net model demonstrated superior performance compared to other models like Hybrid DL and SLF-UNet, emphasizing the importance of meticulous hyperparameter tuning for improving model accuracy and robustness in brain MRI segmentation. © 2024 IEEE.

关键词： 3D U-Net Optimization Brain MRI Segmentation BraTS 2020 Hyperparameter Tuning

来源：评论

学校读者我要写书评

暂无评论

Exploring Chromatin Interaction Between Two Human Cell Types and Different Normalization Techniques for HI-C data 27

Exploring Chromatin Interaction Between Two Human Cell Types...

引用

27th International computer science and Engineering Conference, ICSEC 2023

作者： Rahman, Mafizur Chy, Md Showkat Hossain Rahman, Atikur Ahmed, Shuvo Sharmin, Tasnia Rahaman, Md. Shahidur Baylor University Dept. of Cse United States University of South Wales Dept. of Data Science United Kingdom University of New Haven Dept. of Data Science United States

ISBN: (纸本)9798350342109

In regulating gene expression and identifying relevant biomarkers for diseases like cancer, chromatin interaction plays a crucial role. Thus, the volume of HiC data is rapidly increasing as researchers strive to understand chromatin interaction. Most of the work focused on using a genome browser to visualize Hi-C data and genomic features for chromatin conformation. However, comparing chromatin connection and how much similarity exists between different cell types is still unexplored. As a result, this work used the Pearson and Spearman R correlation technique to investigate the similarities between Human ES and IMR90 Fibroblast cell types. By splitting Hi-C data into small subsets, we discovered that both cells have a significant degree of resemblance. Finally, we compared four different normalization methods based on their coefficient of variation results and running time on Hi-C data. Results demonstrate that min absolute scaling is better for Hi-C data as it has a low coefficient of variation than other methods and can perform fast for large Hi-C data. © 2023 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Acoustic data acquisition and integration for semantic organization of sentimental data and analysis in a PWSN

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Das, Sushovan Mondal, Uttam Kr. Dept. of CSE College of Engineering and Mgmt WB Kolaghat721171 India Dept. of Computer Science Vidyasagar University WB Midnapur721102 India

In an acoustic pervasive wireless sensor network (PWSN), the BASE station plays a vital role in gathering and integrating acoustic sensor data from various nodes, including end and router devices tracking time-driven events. The semantic BASE station is crucial in the IoT landscape as it consolidates data from these networks, enabling thorough sentiment analysis of acoustic signals and yielding insights across domains. A semantic processor at the BASE station is essential for an energy-efficient and intelligent PWSN, managing data collection, integration, signal feature extraction, and publication for model training and sentiment analysis. This paper introduces a novel approach to designing a semantic BASE station, focusing on ontology generation, evaluation, and updates to bolster pervasive wireless sensors in capturing and depicting events and time through an ontological framework. The study addresses challenges in efficiently gathering, integrating, and processing acoustic data from pervasive nodes, proposing a semantic processor at the BASE station to enhance feature extraction and metadata publication. The semantic organization of feature-extracted labeled metadata enables the analysis of comprehensive machine learning (ML) applications such as sentiment analysis, type detection, and environment detection by generating confusion matrix. Evaluation includes performance metrics (NEEN, LSNS, BDAS) as well as accuracy, precision, sensitivity, and specificity for sentimental data analysis to validate the proposed technique’s efficacy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Analyses the Predictive Power of Machine Learning Procedures over Multi Diseases datasets 3

Analyses the Predictive Power of Machine Learning Procedures...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Agarwal, Tarun Kumar Singh, Baldev Chaudhary, Nilam VGU Dept. of Computer Science & Engg. Rajasthan Jaipur India VGU Dept. of Computer Science Rajasthan Jaipur India SKIT Dept. of Computer Science & Engg. Rajasthan Jaipur India

ISBN: (纸本)9798350303360

In today's age of technology, people do not prioritize their health or well-being. Due to frequent circumstances, regular visits to the hospital for check-ups are uncommon, this has led to an increase in illness among people. Nowadays, the majority of people suffer from various health issues like heart, diabetes, kidney disease. The World Health Organization (WHO) considers such chronic diseases are the leading causes of premature death, responsible for half of all deaths in most countries. Early identification of patients can prevent the disease from progressing. Various distributed investigations strongly illustrated that traditional diagnosis methods of chronic diseases are susceptible to bias and variation among medical professionals, making it challenging to timely identify issues accurately. However, huge published efforts denoting that ML based methodology can significantly improve the timely estimation of various health issues and despite the availability of up-to-date information and various machine learning-based tools, accurate diagnosis of such diseases is remaining as a challenge. To address this issue, this paper investigates the chronic diseases forecasting act of dissimilar machine learning techniques, recital evaluation of different ML procedures using the UCI machine learning disease dataset. Results are corroborated using accurateness & confusion matrix. This paper also deliberates the benefits and drawbacks of an accessible diseases prediction schemes for assisting novice researchers in understanding the disease prediction function of machine learning-based methodologies and determining the scope of future research. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Learning for HAR Using 3D Siamese Network 15

A Few-Shot Learning for HAR Using 3D Siamese Network

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Guanghui, Hua Kumar, G. Hemantha Aradhya, V.N. Manjunath Punithavalli University of Mysore Dept. of studies in Computer Science Mysuru India Jss Science and Technology University Dept. of Computer Applications Mysuru India Bharathiar University Department of Computer Applications Coimbatore India

ISBN: (纸本)9798350370249

In artificial intelligence, deep learning techniques were applied in a wide field due to their ability to automatically learn complex patterns from raw data, such as image classification, object detection, image generation, and video analysis in computer vision. These applications are just the tip of a substantial iceberg. With the development of deep techniques to achieve state-of-art accuracy, learn precisely relevant features from raw data, and improve the robustness of models to make them versatile solutions. The traditional deep learning techniques require vast computational resources, including high-performance computer GPUs or TPUs, and can be expensive in terms of hardware. In Human Activity Recognition Systems (HARs). The video needs more computational resources than image processing. In this paper, we proposed a few-shot learning approach based on a 3D Siamese Network with dept. video sequences to address the action video similarity or dissimilar problem. Convolutional Neural Networks (CNNs) are well-suited for images and spatial data processing. The 3DCNN is an extension of CNNs to incorporate an additional temporal dimension to capture the temporal pattern. From the 3D Siamese network, we extract more effective features with spatial-temporal action information from raw data. We employed the 3DCNNs Siamese Network (3DCNNs+SN) with shared weight to recognize or classify a new class of data without new sample data only based on learning training existing sample constructed model. In addition, we divided the benchmark dataset MSR Action 3D dataset into sub-dataset1 (SD-1), sub-dataset2 (SD-2) and sub-dataset3(SD-3) to train and validate our proposed method. For dissimilar sub-dataset 2 we got a 98.1% accuracy, 33% on high-similar sub-dataset 3 and 63.5% on merged sub-dataset SD-4 from sub-dataset2 (SD-2) and sub-dataset3(SD-3). © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Analysis of Skin Lesion Classification using Computational Models

Analysis of Skin Lesion Classification using Computational M...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Arun, Chalana B Anusha, M. Rao, Trupthi Kodipalli, Ashwini Global Academy of Technology Dept. of Artificial Intelligence and Data Science Bangalore India Global Academy of Technology Dept. of Artificial Intelligence and Data Bangalore India

ISBN: (纸本)9798350361537

A common and sometimes lethal condition skin cancer requires early identification and precise categorization in order to be effectively treated. This study investigates the use of machine learning techniques, that includes Random Forest, K- Nearest Neighbors (KNN) and Support Vector Machine (SVM) in the classification of different types of skin cancer. The HAM10000 dataset used, which represents the major seven types of skin diseases, is initially processed and balanced with the help of Synthetic Minority Over-Sampling Technique (SMOTE) and SMOTE-ENN approaches. After data sampling, the findings show an important rise in accuracy, with Random Forest and SVM polynomial kernel utilizing the SMOTE-ENN approach, achieving the highest accuracies of 90.65% and 91.43% respectively. Evaluation criteria like as F1-score, precision, and recall provides additional evidence for the effectiveness of these models. The work emphasizes how crucial it is to correct dataset imbalances related to skin cancer and how conventional machine learning methods can be used to reliably and quickly classify skin cancer. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection Using Deep Learning and Anomaly Detection Techniques

Cybersecurity Threat Detection Using Deep Learning and Anoma...

引用

2024 International Conference on Knowledge Engineering and Communication Systems, ICKECS 2024

作者： Rajendran, T. Mohamed Imtiaz, N. Jagadeesh, K. Sampathkumar, Balaji Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Nagarjuna College of Engineering and Technology Dept. of Information Science and Engineering Bangalore India Sri Venkateswaraa College of Technology Dept. of Computer Science and Engineering Chennai India Akshaya College of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359688

Through the use of combined deep learning and anomaly detection approaches, this research investigates the area of cybersecurity threat detection. The study proves the framework's extraordinary success in recognizing as well as mitigating diverse cyber dangers, including insider threats and zero-day attacks, through practical testing and case studies. The framework establishes itself as a proactive cybersecurity solution adaptive to the changing threat landscape due to its high accuracy of 95%, low amount of false positives 5%, and quick reaction times. The recommendations cover user training, scalability, regulatory compliance, including cross-disciplinary collaboration. Behavioral analysis, AI explainability, IoT security, and countering quantum computing concerns should be the main areas of future research. These revelations help the cybersecurity industry become more resilient and well-prepared. In this research investigation, experiments on threat detection were conducted using deep learning algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The findings of the study reveal that a detection accuracy of 93% was achieved by CNN, while a higher accuracy of 96% in threat detection was exhibited by RNN. © 2024 IEEE.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Mask Region-Based Convolutional Neural Network for Disease Detection in Rice Leaf 3

Mask Region-Based Convolutional Neural Network for Disease D...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Putta, Narsaiah Kumari, T. Suvarna Naik, K Jairam Vasavi College of Engineering Dept. of Computer Science & Engg. Telangana Hyderabad India Chaitanya Bharathi Institute of Technology Dept. of Computer Science & Engg. Telangana Hyderabad India National Institute of Technology Raipur Dept. of Computer Science & Engg. Chhattisgarh India

ISBN: (纸本)9798350354171

Many approaches have been proposed for the problems, like manual diagnosis of crops and soil by experts. But this one is actually a very time-consuming activity. With the advancement of technology, many approaches have been made using machine learning, like image processing techniques, deep convolutional neural networks, segmentation techniques based on neutrosophic logic, etc. However, most of these methods were slow or had implemented complex algorithms that made them unsuitable for being used as an Android app. So, in this paper, a rice leaf disease detection and classification model using region-based convolutional neural networks and deep learning has been proposed. Using this approach, we have successfully developed a model to detect and classify diseases with an accuracy of 94.4%. Determining the type of disease in crops may help the farmers take timely measures and, therefore, avoid the loss. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing Intrusion Detection Process Using ML Techniques: Issues, Options, and Potential Future Directions 3

Assessing Intrusion Detection Process Using ML Techniques: I...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Gupta, Ankesh Singh, Baldev Chaudhary, Nilam VGU Dept. of Computer Science & Engg. Rajasthan Jaipur India VGU Dept. of Computer Science Rajasthan Jaipur India SKIT Dept. of Computer Science & Engg. Rajasthan Jaipur India

ISBN: (纸本)9798350303360

In today's society, the world of computer networks is rapidly expanding and has emerged as an essential means of information sharing. However, given the widespread use of networks for information sharing, data security has become even more critical. In spite of the fact that a variety of methods have been developed to safeguard data, intruders continue to develop novel strategies for breaching network security as new technologies emerge. R2L and U2R are two types of attacks that are considered to be uncommon due to their rarity in networks. However, because they allow intruders to gain access, these attacks can be very dangerous for the hosts they target. The current security system is limited in its ability to accurately, precisely, and without false alarms detect and prevent such attacks. A ton of examination is being finished to upgrade network security. This article discusses various measurable outcomes and itemized correlation with various strategies. Furthermore, with and without the use of feature selection techniques, we compare and contrast the attack detection capabilities of a number of existing approaches in this paper. New researchers may take benefit from these evaluative efforts to determine the most effective strategy for detecting rare class attacks and the significance of incorporating feature selection schemes. NSL-KDD datasets are used to test and investigate an assessment. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Quantum Convolutional Neural Networks for Student Facial Expression Identifcation and Mode Assessments 4

Leveraging Deep Quantum Convolutional Neural Networks for St...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Hossain, Javed Alam, Md. Nur Akib, Mohammad Yasin Nur Kogoya, Krisdahim Nanjing University of Information Science and Technology Dept. of Artificial Intelligence Nanjing China Nanjing University of Information Science and Technology Dept. of Computer Science and Technology Nanjing China

ISBN: (纸本)9798331529635

The incorporation of modern technologies into education has transformed how learning is seen and assessed, with a rising emphasis on understanding student behavior using facial expression recognition (FER). Recognizing students' emotional and cognitive states can provide vital insights into their engagement and learning styles, allowing teachers to adjust their teaching tactics in real time. Traditional machine learning algorithms have been used to solve this problem, but they frequently struggle with the complexity of facial expressions and big datasets, resulting in limitations in accuracy and processing efficiency. This study explores the potential of quantum computing in addressing these challenges through the development of a Deep Quantum Convolutional Neural Network (QCNN) architecture. By combining the advanced image processing capabilities of convolutional neural networks (CNNs) with the computational power of quantum features such as superposition and entanglement, we aim to enhance the detection of facial expressions that reflect students' engagement, concentration, frustration, and satisfaction. Finally, the result demonstrates a classification accuracy of 91.58 © 2024 IEEE.

关键词： Convolutional neural networks

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：