检索结果-内蒙古大学图书馆

FPGA Implementation of Textural Feature Extractor and Distance Based Classifier for Multi Modal Biometric Pattern Recognition System Using Multi Resolution Approach 3

FPGA Implementation of Textural Feature Extractor and Distan...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Hariprasath, S. Santhi, M. Prabakar, T.N. Koushick, V. Aravind, P. Gunasekaran, T. Saranathan College of Engineering Department of Ece Trichy India Sri Sairam College of Engineering Department of Ece Bangalore Anekal India Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Mattu University Department of Electrical and Computer Engineering Ethiopia Electrical and Electronics Engineering Section University of Technology and Applied Sciences Muscat Oman

ISBN: (纸本)9798350322842

The design of biometric pattern recognition with better accuracy, high robustness and good permanence is a significant design issue in pattern recognition system. A pattern recognition system in which the biological and physiological traits of the user are employed to authenticate the users is known as biometric pattern recognition system. Unimodal biometric systems do not have the required characteristics like solidity, circumvention and permanence. When noisy data acquired from the sensor is given as input, the uni modal biometrics system's accuracy may reduce. Besides the noisy input, less variation of parameters of input data belonging to same class may be a cause for decrease in accuracy of the system. Several such limitations may be removed by applying input data from multi biometric sources. In this work, the design of a textural feature extractor and the classifier for a bimodal biometric system is described. The bimodal biometric system is constructed by fusion of iris code vector and palmprint code vector at feature level. In iris pattern, using the gray level dependent matrix values obtained from wavelet packet decomposed sub-images, the features are extracted Using gabor kernel, features are extracted from the palmprint pattern. The feature vector is formed by the concatenation of both the features after normalization is employed. By binarisation, the binary feature vector is created Using Hamming Distance and its variant, the classifier produces the classification result. The RTL description of the Hamming Distance Classifier (HDC) is written using VHDL 2008 language, Verilog HDL, and the implementation is performed on Spartan 6 FPGA. With a speed grade of 4, the propagation delay of the critical path is 330.12 ns. The obtained delay is sufficient for implementing the classifier as an off-chip design for real-time implementation. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Optimizing Variable-Strength Combinatorial Test Suite Generation via Fuzzy Adaptive Sine Cosine Algorithm (FASCA) 1

Optimizing Variable-Strength Combinatorial Test Suite Genera...

引用

1st International Conference on Cyber Security and Computing, CyberComp 2024

作者： Zabidi, Nur Syabila Ibrahim, Noraini Rejab, Mazidah Mat Mamat, MasrulEhsan Nazir, Sumaira Mat Tuselim, Nurul Hawani Faculty of Computer Science and Information Technology Parit Raja Batu Pahat Malaysia National University of Modern Languages Department of Software Engineering Islamabad Pakistan Industrial Research Management Centre SIRIM Berhad Business Intelligence Section Shah Alam Malaysia

ISBN: (纸本)9798350387728

Combinatorial test suite generation is a critical aspect of software testing, particularly for systems with variable-strength interactions. Traditional optimization algorithms often struggle to efficiently generate minimal test suites while maintaining coverage. This research introduces the Fuzzy Adaptive Sine Cosine Algorithm (FASCA), a variant of the Sine Cosine Algorithm (SCA), tailored specifically for optimizing variable-strength combinatorial test suite generation. FASCA incorporates fuzzy adaptation mechanisms to dynamically balance exploration and exploitation, addressing the limitations of standard SCA in handling diverse interaction strengths. Experimental evaluations demonstrate that FASCA significantly reduces test suite size and execution time compared to the original SCA, offering a more efficient solution for combinatorial test optimization. These results highlight FASCA's potential as a robust tool for enhancing the efficiency of software testing processes. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

A Variational Autoencoder-Feed Forward Networks (VAE-FNN) Model for Classifying DNA Barcodes 1

A Variational Autoencoder-Feed Forward Networks (VAE-FNN) Mo...

引用

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Yadav, Abhivyakti Divya, S. Oviya, I.R. Raja, Kalpana Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Medicine Yale University Section for Biomedical Informatics and Data Science New HavenCT United States

ISBN: (纸本)9798350342796

DNA Barcodes, which are particular fragments derived from brief sections of DNA (such as mitochondrial, nuclear, and plastid sequences), can be used to identify organisms from the major life kingdoms. In addition to supporting conventional taxonomic techniques, DNA barcoding is a potent tool that advances our knowledge of species diversity and their ecological functions. On a variety of organisms, the use of this approach for species categorization has been successful. In this paper, we examine how DNA barcoding has been used to classify species based on DNA barcodes as well as other related research that has been done over the years on the subject. After experimenting with a number of deep learning models, we have propose a Variational Auto Encoder + Feed Forward Neural Network workflow for classifiying species using DNA barcodes. The models have been assessed on the basis of performance factors including accuracy, recall, and precision. COI, rbcL, matK, and ITS are the specific gene sections that have been identified as barcodes. For both simulated and real datasets, the model can attain an average accuracy of greater than 95 percent. This DNA barcoding approach has the ability to simplify DNA barcode-based species identification and serve as a tool for species categorization. © 2023 IEEE.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

An Investigation Through Stochastic Procedures for Solving the Fractional Order computer Virus Propagation Mathematical Model with Kill Signals

引用

Neural Processing Letters 2023年第2期55卷 1783-1797页

作者： Sabir, Zulqurnain Raja, Muhammad Asif Zahoor Mumtaz, Nadia Fathurrochman, Irwan Sadat, R. Ali, Mohamed R. Department of Mathematics and Statistics Hazara University Mansehra Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Computer Science Iqra University Islamabad Campus Islamabad Karachi Pakistan Department of Islamic Educational Management Institute Agama Islam Negeri Curup Rejang Lebong Indonesia Department of Mathematics Zagazig Faculty of Engineering Zagazig University Zagazig Egypt Faculty of Engineering and Technology Future University Cairo Egypt

In this study, the numerical investigations through the stochastic procedures for solving a class of fractional order (FO) computer virus propagation (CVP) mathematical model with kill signals (KS), i.e., CVP-KS is presented. The KS gets alert about those viruses, which can be infected through the computer system to decrease the virus propagation danger. The mathematical model of the CVP-KS is based on the SEIR-KS model. The focus of these investigations is to present the numerical solutions of the FO-SEIR-KS model using the sense of Levenberg–Marquardt backpropagation scheme (LMBS) together with the neural networks (NNs), i.e., LMBS-NNs. The use of the one dynamic of the other makes the model nonlinear. Three different FO values have been used to check the performances of the designed scheme for this FO-SEIR-KS nonlinear mathematical model. The statics used in this study is 80%, 10% and 10% for training, testing and certification for solving the FO-SEIR-KS nonlinear mathematical model. The numerical simulations are performed through the stochastic LMBS-NNs scheme for solving the FO-SEIR-KS nonlinear mathematical model. The obtained results will be compared with the design of database reference solutions based on the Adams–Bashforth–Moulton. In order to accomplish the validity, capability, consistency, competence and accuracy of the LMBS-NNs, the numerical results using the error histograms, regression, mean square error, state transitions and correlation have been provided. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Intelligent Network System based Covid 19 Health Care System 3

Machine Learning and Intelligent Network System based Covid ...

引用

3rd International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2022

作者： Basha, Amjath Ali Jakul Saravanan, K. Mangayarkarasi, T. Balarengadurai, C. University of Technology and Applied Sciences Ibra Sultanate of Oman RCC - ENGG Department Computer Engineering Electrical and Electronic Section Department of Engineering Oman R.M.D Engineering College Department of Information Technology Tamil Nadu Chennai India Sri Sairam Engineering College Department of Instrumentation and Control Engineering Tamil Nadu Chennai India Vidyavardhaka College of Engineering Department of Computer Science and Engineering Karnataka Mysuru India

ISBN: (纸本)9781665462754

COVID-19 has lately infected a big number of people worldwide. Medical service frameworks are strained as a result of the infection. The emergency unit, which is part of the medical services area, has experienced several challenges as a result of the low data quality offered by existing ICU clinical equipment. The Internet of Things has enhanced the capability for essential information mobility in medical services in the twenty-first century. Nonetheless, many of today's ideal models use IoT innovation to assess patients' well-being. As a result, executives lack understanding regarding the most effective method to apply such innovation to ICU clinical equipment. The IoT Based Paradigm for Medical Equipment Management Systems, a breakthrough IoT-based paradigm for successfully administering clinical hardware in ICUs, is introduced in this study. During the COVID-19 episode, IoT technology is used to boost the data stream between clinical hardware, executive frameworks, and ICUs, enabling the maximum level of openness and reasonableness in clinical equipment redistribution. IoT MEMS conceptual and functional features were painstakingly drawn. Using IoT MEMS expands the capacity and limits of emergency clinics, effectively easing COVID-19. It will also have a substantial impact on the nature of the data and will improve the partners' trust and transparency. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A new model based on Dynamic Naive Bayes classifier for retweet behavior prediction 10

A new model based on Dynamic Naive Bayes classifier for retw...

引用

10th International Conference on Artificial Intelligence and Robotics, QICAR 2024

作者： Safari, Rahebeh Mojtahedi Rahmani, Amir Masoud Alizaeh, Sasan H. Department of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan Tehran Iran

ISBN: (纸本)9798350348873

At present, the prediction of user retweeting behavior plays a significant role in perceiving the underlying mechanism of information diffusion in the microblogging network. The problem of retweeting behavior prediction is usually considered as a classification task hence, the effort for the classification of the time-series data in the microblogging network has gained spacious attention. It is challenging to improve the classification accuracy of retweeting behavior prediction models, because the applied classifications still lack a tailored method. To address this, we present a retweeting behavior prediction model based on Dynamic Naïve Bayes classifier that is an appropriate classifier dealing with time-series data classification. In fact, we apply a time discretization approach and incorporate user individual, social and temporal features into our proposed prediction model to estimate accurately user retweeting behavior in the microblogging network over time. The real Twitter(X) microblogging dataset is used to evaluate the performance of the proposed model in the user retweeting prediction. The experimental results show that our proposed classifier due to its simple structure can avoid overfitting problem, and outperforms in compared to other baseline methods. ©2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

MPI Allgather Utilizing CXL Shared Memory Pool in Multi-Node Computing Systems

MPI Allgather Utilizing CXL Shared Memory Pool in Multi-Node...

引用

IEEE International Conference on Big Data

作者： Hooyoung Ahn Seonyoung Kim Yoomi Park Woojong Han Shinyoung Ahn Tu Tran Bharath Ramesh Hari Subramoni Dhabaleswar K. Panda Supercomputing System Research Section Electronics and Telecommunications Research Institute Department of Computer Science and Engineering The Ohio State University

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

In Artificial Intelligence (AI) and high-performance computing (HPC), growing data and model sizes require distributed processing across multiple nodes due to single-node limitations, increasing inter-node communication. To address these challenges, we propose a novel MPI allgather method leveraging CXL technology, which supports composable architectures and dynamic resource allocation in data centers and HPC systems. Notably, CXL 3.1 facilitates cache coherence among nodes. The proposed allgather method uses the CXL shared memory pool as a communication buffer, outperforming existing algorithms for two reasons: First, CXL provides lower latency than Ethernet and IB, and second, by using the CXL shared memory pool as a shared communication buffer across multiple nodes, it significantly reduces the number of communications. To the best of our knowledge, this work is the first to explore combining MPI collective communication with CXL technology to optimize MPI allgather. Our proposed allgather method significantly reduces communication latency compared to traditional allgather methods by up to 42.14x, with a minimum improvement of 2.91x, as measured using the OSU Micro-Benchmark (OMB), a standard MPI benchmarking suite.

关键词： High performance computing Heuristic algorithms Memory management Ethernet Dynamic scheduling Hardware Topology Resource management Artificial intelligence Standards

来源：评论

学校读者我要写书评

暂无评论

A K-Band CMOS Power Amplifier using an Analog Predistortion Linearizer with 22.1 dBm Psat and 0.9° AM-PM Distortion

A K-Band CMOS Power Amplifier using an Analog Predistortion ...

引用

IEEE Symposium on Radio Frequency Integrated Circuits (RFIC)

作者： Junhan Lim Wonseob Lee Seong-Mo Moon Euijin Oh Seunghun Wang Dongpil Chang Jinseok Park Satellite Payload Research Section ETRI Korea Department of Intelligent Electronics and Computer Engineering Chonnam National University Korea

ISBN: (数字)9798350359473

ISBN: (纸本)9798350359480

This paper presents a K-band CMOS power amplifier (PA) using the 65-nm CMOS process. To improve linearity, an analog predistortion linearizer using a cold-FET and a variable inductor is proposed. Unlike conventional cold-FET linearizers, which face limitations in improving amplitude-to-phase (AM-PM) distortion at high output power, the proposed linearizer compensates both AM-PM distortion and amplitude-to-amplitude (AM-AM) distortion of the PA. Especially, the linearizer has a phase-lag characteristic at medium output power and phase-lead characteristic at high output power, which compensates for AM-PM distortion of the PA up to high output power. The implemented PA achieved a peak power-added efficiency (PAE) of 34.4%, saturation output power (P sat ) of 22.1 dBm, and P 1dB of 19.44 dBm at 27 GHz. Also, AM-PM distortion of only 0.9° was achieved through the proposed linearization technique. Linear output power satisfying error vector magnitudes (EVMs) of -25 dB and -30 dB were measured at 16.5 dBm and 14.9 dBm, respectively.

关键词： Power measurement K-band Measurement uncertainty Linearization techniques Predistortion Radiofrequency integrated circuits Vectors

来源：评论

学校读者我要写书评

暂无评论

Energy and cost benefits of advanced lighting technology applications in traffic light systems

Energy and cost benefits of advanced lighting technology app...

引用

14th Mediterranean Conference on Power Generation Transmission, Distribution and Energy Conversion (MEDPOWER 2024)

作者： Alexis Polycarpou Marios S. Georgiou Department of Electrical Computer Engineering and Informatics Frederick University Nicosia Cyprus Electromechanical Section Nicosia Municipality Nicosia Cyprus

ISBN: (数字)9781837242689

Following a pilot project, which concluded in 2016, the replacement of old energy consuming Traffic Light Systems (TLS) of Nicosia Municipality were the subject of an investigation with regards to the energy saving potential and most importantly the payback period of the investment, through presumptions. This paper presents the results obtained of the new efficient technology implementation, with regards to the energy saving that materialised in the Nicosia Municipality. Investigation is presented in an attempt to determine whether the proposed solution and calculated capital employed had the expected energy usage reduction, return on investment, and payback period. The estimated cost benefit of the installed systems compared to the actual benefits varies significantly, after factors such as maintenance and electricity costs are considered.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Refining Pseudo Labels With a Teacher-Student Paradigm for Accurate Brain Lesion Segmentation

引用

IEEE Access 2025年 13卷 84474-84487页

作者： Chatterjee, Pubali Das Sharma, Kaushik Chakrabarti, Amlan Department of Computer Science and Engineering Bhubaneswar751030 India University of Calcutta Electrical Engineering Section Department of Applied Physics Kolkata700073 India University of Calcutta A. K. Choudhury School of Information Technology Kolkata700073 India

In medical image segmentation, obtaining large volume of high quality labeled data is a persistent challenge, especially for intricate tasks like brain lesion segmentation, where annotations are time-consuming, costly, and require expert knowledge. This work introduces a novel learning framework where the abundance of labeled data is scarce, and the model learns from both limited number of annotated data as well as from unlabeled data. The framework initially leverages superpixel segmentation to group pixels with similar properties into compact, perceptually coherent regions while preserving critical structural details, and produce coarse segmentation mask on unlabeled data. In the next phase, a teacher-student model is employed, where the teacher module generates pseudo-labels for unlabeled data, and the student model learns from both of these pseudo-labels and minimal amount of annotated data. In addition, a feature refinement module is introduced to further strengthen the teacher-student framework, where the student module also learns from the mutual agreement between superpixel prediction and the pseudo label generated by the teacher module. The overall framework helps in efficiently using the unlabeled data with the help of handful amount of labeled data. Experimental results across multiple datasets demonstrate the effectiveness of the proposed framework in achieving precise, computationally efficient brain lesion segmentation. The integration of superpixel-based grouping and the student-teacher architecture not only improves segmentation accuracy but also offers a scalable solution for scenarios with limited annotated data. This method provides a promising pathway for advancing medical imaging applications, enabling accurate and efficient segmentation while addressing the challenges of data scarcity and annotation constraints. © 2013 IEEE.

关键词： Image segmentation

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：