检索结果-内蒙古大学图书馆

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Ovi, Tareque Bashar Chowdhury, Md. Jawad-Ul Kabir Oyshee, Shaira Senjuti Rizu, Mubdiul Islam Department of Electrical Electronic and Communication Engineering Military Institute of Science and Technology Dhaka Bangladesh

ISBN: (纸本)9783031346187

The novel coronavirus illness (COVID-19) is a highly contagious virus that has swept around the world and has presented a serious threat to every country’s economy and public health. It has been demonstrated that COVID-19 can be accurately diagnosed with computed tomography (CT) scans that automatically partition infected areas. However, accurate segmentation continues to be a difficult task, due to the lack of pixel-level annotated medical images. For the automatic segmentation of distinct COVID-19 infection zones, a Convolutional Block Attention U-Net with additional dilated blocks is proposed in this study. The suggested architecture for the automatic segmentation of COVID-19 chest CT images with a dual attention mechanism and dilated block performs remarkably well in experiments, reaching an IoU score of 89.0% and a dice score of 90.2%. The proposal provides a novel, promising approach for quantitative COVID-19 detection utilizing CT scans of lung infection by overcoming the aforementioned issues. © 2023, ICST institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Time Series Models for Radiated Electromagnetic Energy of Lightning Strokes Detected by World Wide Lightning Location Network

Time Series Models for Radiated Electromagnetic Energy of Li...

引用

2022 International Conference on Recent Advances in Wireless communications and Emerging Technologies, RAWCET 2022

作者： Rafi, Mehdi Hasan Mostafa, Golam Department of Electrical Electronic and Communication Engineering Military Institute of Science and Technology Dhaka Bangladesh

Lightning is a significant atmospheric event and has a wide-ranging influence on the Earth's climate. Recently a sensor station of World Wide Lightning Location Network (WWLLN) is hosted at Dhaka (23.81°N, 90.41°E) and one year (Jan 2021 to Dec 2021) lightning strokes energy data is investigated. In an effort to switch the analysis from descriptive to predictive, WWLLN lightning strokes energy data is modeled using time series analysis. The autoregressive integrated moving average (ARIMA) model has been applied to predict the data. According to the process of model selection, the auto-correlation function (ACF) and partial auto-correlation function (PACF) are examined to determine the auto-regressive (AR) and moving-average (MA) terms. Standard diagnostic tests are performed to ensure the goodness of fit of the chosen model. After necessary diagnostic tests, ARIMA (3,1,0)×(2,1,0)12 is selected as the best fitted model. © Published under licence by IOP Publishing Ltd.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

An intrusion detection system using ranked feature bagging

引用

International Journal of Information Technology (Singapore) 2024年第2期16卷 1213-1219页

作者： Azhagiri, M. Rajesh, A. Karthik, S. Raja, K. Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering Jain University Bangalore India Department of IT College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

An Intrusion Detection System monitors the network for any malicious attacks. It is an ideal tool for protecting extensive business networks from any kind of attack. In this paper, an Intrusion Detection System using Bagging and ranked features has been proposed. The sample datasets for training the ensemble of classifiers in the bagging approach are obtained by generating subsets of the features ranked according to their importance in the classification process. OneR algorithm has been used to rank the features. The decision tree has been used as the base classifier in the bagging approach. The proposed system was able to predict attacks with an accuracy of 99.71% with a minimal number of features and outperformed other similar approaches discussed in the literature. © The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Bagging CIC-IDS 2017 dataset Decision tree Ensemble Feature selection Intrusion detection system OneR feature selection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Attendance Management with Deep Learning

An Efficient Attendance Management with Deep Learning

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and communications, COSMIC 2024

作者： Shivanna Hema, H.P. Janardhana, D.R. Srinivas, P.M. Sahyadri College of Engineering and Management Department of Computer Science and Engineering Mangaluru India D S Dinakar Polytechnic College Department of Electronics and Communication Engineering Shivamogga India Nitte Meenakshi Institute of Technology Department of Computer Scince and Engineering Bengaluru India

ISBN: (纸本)9798331517892

Accurate attendance recording is critical in educational institutions to ensure students' and teachers' consistency and discipline. Traditional manual attendance systems are frequently inefficient and prone to errors, such as proxy attendance and missed entries, which may impact the accuracy of attendance records. To address these challenges, an automatic attendance system that uses camera-based facial recognition technology is proposed. The latest technology records accurate attendance by taking visuals of students as soon as the class starts and comparing them to an already-existing database. Face recognition happens through human detection. The concept used here is deep learning. For students, this automated solution streamlines attendance management by ensuring that records are accurate and up to date without the need for manual entry. The system efficiently keeps track of the presence of teachers, notifying the Head of department (HOD) right away in the case of an excused absence, therefore preventing disruptions during scheduled lessons. This technology significantly increases the reliability and efficiency of attendance tracking by automating the process. Enhancing record accuracy and accountability leads to a more regulated and effective learning environment that benefits teachers and students alike. This technological method offers greater precision and oversight, leading to improved institutional administration and educational outcomes. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Advances in 3D bioprinting for environmental remediation and hazardous materials treatment

引用

Environmental Science and Pollution Research 2024年第44期31卷 55984-55995页

作者： Vellalapalayam Manoharan, Gobinath Munuswamy, Naresh Babu Johnpeter, Jasmine Hephzipah Veeramani, Sathya Balasubramanian, Hemalatha Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai600 124 India Department of Mechanical Engineering Easwari Engineering College Chennai600 089 India Department of Electronics and Communication Engineering R.M.K. Engineering College Chennai601 206 India Department of Computer Science Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Chennai600 062 India Department of Civil Engineering St. Peter’s Institute of Higher Education and Research Chennai600 054 India

The high-throughput method based on the micron-level structure that 3D bioprinting technology offers for various environmental microbiological engineering applications is made possible by its several printing paths and precision programming control. This versatility makes it an on-demand manufacturing technology. A novel 3D manufacturing technique called 3D bioprinting may be used to precisely uptake and disperse bacteria to create microbial active substances with a variety of intricate functionalities for environmental applications. The technological challenges that the current 3D bioprinting technology must face include the mechanical properties of materials, the creation of specific bioinks to adapt to different strains, and the exploration of 4D bioprinting for intelligent applications. Therefore, this analysis delves deeply into the core technological ideas of 3D bioprinting, bioink materials, and their environmental applications. It also offers recommendations about the challenges and opportunities associated with 3D bioprinting. Combined with the present advancements in microbe enhancement technology, 3D bioprinting will provide an enabling platform for multifunctional microorganisms and facilitate the management of in situ directional responses in the environmental domain. This review highlights the applications of 3D bioprinting in the environmental monitoring and bioremediation. 3D printing in solid waste management is also discussed in detail. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： 3D bioprinting Bioink Biomaterial Integrated biomaterials

来源：评论

学校读者我要写书评

暂无评论

Investigation of Normally-Off β-Ga2 O3 Power MOSFET Using Ferroelectric Gate 3rd

Investigation of Normally-Off β-Ga2 O3 Power MOSFET Using F...

引用

3rd International Conference on Micro and Nanoelectronics Devices, Circuits and Systems, MNDCS 2023

作者： Singh, Rajan Purnachandra Rao, G. Lenka, Trupti Ranjan Prasad, S.V.S. Dasari, Kiran Singh, Pulkit Nguyen, Hieu Pham Trung Department of Electronics and Communication Engineering MLR Institute of Technology Telangana Hyderabad500043 India Department of Electronics and Communication Engineering National Institute of Technology Assam Silchar788010 India Department of Electrical and Computer Engineering New Jersey Institute of Tech NewarkNJ07102 United States

ISBN: (纸本)9789819944941

In this paper, we present a normally-off beta-gallium oxide (β-Ga2O3) metal–oxide–semiconductor field-effect transistor (MOSFET) with ferroelectric gate (Fe-G). The enhancement-mode (E-Mode) operations are achieved by depleting the charge carriers from the channel using the gate charge trapped in the ferroelectric material at the ferroelectric–dielectric (Fe-De) interface. The enhancement-mode (E-mode) operation has a negligible degradation in saturation current as compared to depletion-mode (D-Mode) operation. Ohmic-contacts access region resistances are minimized in the E-mode using highly-doped ohmic-contacts access regions. Furthermore, device achieves a significant low specific on-resistance (RON,sp) of 48 mΩ-cm2 in E-mode compared to 103 mΩ-cm2 in the D-mode. Furthermore, a high breakdown voltage (VBR) of 2250 V in E-mode combined with RON,sp brings in a figure of merit (VBR2/RON,sp) of 49 MW/cm2, showing its potential for futuristic wide bandgap (WBG) power devices. In addition, the E-mode device shows a hysteresis-free subthreshold swing (SS) of 65 mV/dec, which indicates its suitability for fast switching applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ohmic contacts

来源：评论

学校读者我要写书评

暂无评论

Design of Approximate Multiplier using Highly Compressed 5_2 Counter 6

Design of Approximate Multiplier using Highly Compressed 5_2...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Nelmin, Bathlin N. Shaji, R.S. Hariprasad, S. Shettygari, Sudeshna Vasan, J.K. Vijayan, V. Department of Electronics and Communication Engineering University College of Engineering Nagercoil India Department of Computer Science and Engineering St. Xavier’s Catholic College of Engineering Nagercoil India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798331522667

Approximate computing effectively impacts low-power VLSI circuits by reducing circuit overhead. It introduces minimal error in the output, which does not significantly affect the application. This paper proposes an approximate multiplier constructed using 5_3 and 5_2 counters. The proposed 5_2 counter delivers two outputs instead of three, thereby achieving 60% compression. The overhead of the 5_2 counter circuit is reduced, achieving a power delay product (PDP) improvement of 18%. This reduction comes with an addition of an 6% error rate. The newly designed multiplier has less delay, where the Mean error distance (MED) is kept as low as possible. The complexity of the 5_2 counter is also reduced since the counter uses only a full adder and three gates. This is achieved by applying various error optimization mechanisms. The error parameters, (i) Error Distance (ED), and (ii) Mean Error Distance (MED) are analyzed and compared with existing works. The proposed multipliers are involved in image contrast application with better Peak Signal to Noise Ratio (PSNR) value. © 2025 IEEE.

关键词： Delay circuits

来源：评论

学校读者我要写书评

暂无评论

An Improved Video Recommendation System for IoT Devices Using Federated Learning

An Improved Video Recommendation System for IoT Devices Usin...

引用

2023 IEEE International Conference on Device Intelligence, Computing and communication Technologies, DICCT 2023

作者： Kabir, Muqsetin Tasfia, Rifa Mostafa, Md. Golam Military Institute of Science and Technology Department of Electrical Electronic and Communication Engineering Dhaka Bangladesh

ISBN: (纸本)9781665474924

Video recommendation progressively adds new dimensions to the application of Internet of Things (IoT). JointRec, a video recommendation architecture for minority users, introduced federated learning in the JointCloud operation. In our work, the proposed design trains the edge end devices of the local clouds incorporating Federated Swapping (FedSwap) into Federated Averaging (FedAvg) operation during cloud weight aggregation. The implemented Convolutional Neural Network (CNN) model uses Dual Convolutional Probabilistic Matrix Factorization (Dual-CPMF) method in the parallel training of clouds. The communication cost of weighted file transmission is handled with a compression aggregator. After 10 training rounds, this model obtains RMSE = 0.8558 and aggregates 1.43 Gbits validating the prediction accuracy and communication efficiency of the proposed video recommendation system. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Contrastive Self-Supervised Speaker Embedding With Sequential Disentanglement

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 2704-2715页

作者： Tu, Youzhi Mak, Man-Wai Chien, Jen-Tzung Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Hong Kong SAR999077 Hong Kong National Yang Ming Chiao Tung University Institute of Electrical and Computer Engineering Hsinchu30010 Taiwan

Contrastive self-supervised learning has been widely used in speaker embedding to address the labeling challenge. Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker identity but also linguistic content. In this paper, we propose a contrastive learning framework with sequential disentanglement to remove linguistic content by incorporating a disentangled sequential variational autoencoder (DSVAE) into the conventional contrastive learning framework. The DSVAE aims to disentangle speaker factors from content factors in an embedding space so that the speaker factors become the main contributor to the contrastive loss. Because content factors have been removed from contrastive learning, the resulting speaker embeddings will be content-invariant. The learned embeddings are also robust to language mismatch. It is shown that the proposed method consistently outperforms the conventional contrastive speaker embedding on the VoxCeleb1 and CN-Celeb datasets. This finding suggests that applying sequential disentanglement is beneficial to learning speaker-discriminative embeddings. © 2014 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Statistical Characterization and Performance Analysis of Distributed Multi-RIS-Aided Wireless communication System 6

Statistical Characterization and Performance Analysis of Dis...

引用

6th International Conference on Electrical Information and communication Technology, EICT 2023

作者： Islam, Mohammad Shariful Mostafa, Md Golam Military Institute of Science and Technology Department of Electrical Electronic and Communication Engineering Dhaka Bangladesh

ISBN: (纸本)9798350370836

This study proposes two distributed multi-reconfigurable intelligent surface (MRIS)-aided systems and performs their statistical characterization and modeling. The mathematical framework is provided for both schemes to calculate the end-to-end (e2e) fading channel distribution. For both the Gamma and Log-Normal distributions, the approximate cumulative distribution functions (CDF) and probability density functions (PDF) show a remarkable alignment with their corresponding true CDFs and PDFs in both schemes. Subsequently, the performance of both schemes is evaluated in terms of outage probability (OP) and ergodic capacity (EC). It is observed that Scheme One achieves better performance than Scheme Two. Results for OP and EC are presented for both schemes, and it is evident that using multiple antennas in the transmission significantly improves the channel capacity. This research contributes valuable insights into optimizing distributed MRIS-aided wireless systems, highlighting the potential benefits of the proposed schemes for advancing wireless communication capabilities. © 2023 IEEE.

关键词： Probability density function

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：