检索结果-内蒙古大学图书馆

A Reconfigurable Frequency Selective Surface for Wi-Fi Application

学校读者我要写书评

暂无评论

Journal of Microwaves, Optoelectronics and Electromagnetic Applications 2023年第1期22卷 33-46页

作者： da Silva Evangelista, Thamyris Mamedes, Deisy Formiga Costa e Silva, Jefferson Serres, Alexandre Jean René Neto, Alfredo Gomes Federal University of Campina Grande UFCG Paraíba Brazil Department of Electrical and Computer Engineering University of Victoria UVic BC Canada Group of Telecommunications and Applied Electromagnetism GTEMA Federal Institute of Paraíba IFPB Paraíba Brazil

This work presents the development of a reconfigurable frequency selective surface (RFSS) for application in the 2400-2483.5 MHz band, standard IEEE 802.11b/g/n (Wi-Fi). The proposed RFSS is based on the four-arms star geometry and PIN diodes were used as switching elements. In the initial design, numerical and measured results, especially for y polarization, PIN diode on-state, shown a difference of 15% for the resonant frequency. To overcome this drawback, a scaling factor was adopted and RFSS was redesigned and characterized, achieving the desired frequency response. The RFSS reconfigurability is confirmed, with a variation of at least 15 dB, when switching the states of the PIN diode. Moreover, the signal strength was measured directly on a notebook, confirming the reconfiguration of the RFSS. Finally, for the γ polarization, it was found that for this polarization the frequency response remains virtually unchanged, even for angles of incidence up to 45°. In addition to the Wi-Fi signal control, the observed features make the developed RFSS especially attractive for reconfigurable antennas applications. © 2023 SBMO/SBMag.

关键词： Stars

Spiking representation learning for associative memories

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ravichandran, Naresh Lansner, Anders Herman, Pawel Computational Cognitive Brain Science Group Department of Computational Science and Technology School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Mathematics Stockholm University Stockholm Sweden Digital Futures KTH Royal Institute of Technology Stockholm Sweden

Networks of interconnected neurons communicating through spiking signals offer the bedrock of neural computations. Our brain’s spiking neural networks have the computational capacity to achieve complex pattern recognition and cognitive functions effortlessly. However, solving real-world problems with artificial spiking neural networks (SNNs) has proved to be difficult for a variety of reasons. Crucially, scaling SNNs to large networks and processing large-scale real-world datasets have been challenging, especially when compared to their non-spiking deep learning counterparts. The critical operation that is needed of SNNs is the ability to learn distributed representations from data and use these representations for perceptual, cognitive and memory operations. In this work, we introduce a novel SNN that performs unsupervised representation learning and associative memory operations leveraging Hebbian synaptic and activity-dependent structural plasticity coupled with neuron-units modelled as Poisson spike generators with sparse firing (~1 Hz mean and ~100 Hz maximum firing rate). Crucially, the architecture of our model derives from the neocortical columnar organization and combines feedforward projections for learning hidden representations and recurrent projections for forming associative memories. We evaluated the model on properties relevant for attractor-based associative memories such as pattern completion, perceptual rivalry, distortion resistance, and prototype extraction. © 2024, CC BY-SA.

关键词： Unsupervised learning

XAI for In-hospital Mortality Prediction via Multimodal ICU Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Xingqiao Gu, Jindong Wang, Zhiyong Yuan, Yancheng Du, Bo He, Fengxiang School of Computer Science Wuhan University China The Department of Engineering Science University of Oxford United Kingdom The School of Computer Science Faculty of Engineering The University of Sydney Australia The Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong The Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh United Kingdom

Predicting in-hospital mortality for intensive care unit (ICU) patients is key to final clinical outcomes. AI has shown advantaged accuracy but suffers from the lack of explainability. To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Furthermore, we introduce an explainable method, namely Layer-Wise Propagation to Transformer, as a proper extension of the LRP method to Transformers, producing explanations over multimodal inputs and revealing the salient features attributed to prediction. Moreover, the contribution of each modality to clinical outcomes can be visualized, assisting clinicians in understanding the reasoning behind decision-making. We construct a multimodal dataset based on MIMIC-III and MIMIC-III Waveform Database Matched Subset. Comprehensive experiments on benchmark datasets demonstrate that our proposed framework can achieve reasonable interpretation with competitive prediction accuracy. In particular, our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research. The code is available at https://***/lixingqiao/XAI-ICU. Copyright © 2023, The Authors. All rights reserved.

关键词： Intensive care units

Optimizing Urban Solid Waste-to-Energy Production Systems with Backpropagation Neural Network Model

学校读者我要写书评

暂无评论

Optimizing Urban Solid Waste-to-Energy Production Systems wi...

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： P. Loganathan Devika SV Lalit Mohan Trivedi S. Rukmani Devi Neeru Malik D. Jayakumar Department of Electrical and Electronics Engineering Vinayaka Mission's Research Foundation (Deemed to be University) Salem India Department of Electronics and Communication Engineering Hyderabad Institute of Technology and Management Hyderabad India Department of Ash Mathematics Moradabad Institute of Technology Moradabad India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai India School of Engineering and Technology Pimpri Chinchwad University Pune India Department of Electronics and Communication Engineering Kuppam Engineering College Kuppam India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Environmental concerns and global MSW generation have spurred waste-to-energy (WtE) research. These projects support the global bioeconomy and biorefineries to generate renewable energy and reduce fossil fuel use. Preprocessing, feature extraction, and model training comprise the approach. Outliers are removed and input values are normalized using zero-mean normalization. For feature extraction, GW was chosen because to its localization and frequency domain capabilities. Model training uses the Backpropagation Neural Network (BPNN). The proposed model outperformed SVMs and ANNs with 91.45% accuracy. Thus, the model's strength is waste-to-energy conversion. The results indicate that the suggested method optimizes MSW processing for renewable energy. This method is promising for WtE technology, which will help the globe switch to renewable energy.

关键词： Backpropagation Training Location awareness Solid modeling Accuracy Biological system modeling Frequency-domain analysis Neural networks Feature extraction Integrated circuit modeling

Intelligent IoT-Based Water Quality Monitoring System Using TD-CNN-LSTM Approach

学校读者我要写书评

暂无评论

Intelligent IoT-Based Water Quality Monitoring System Using ...

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： M. Velammal Vittam Rakesh K. Kartheeban Khalid Ali Qidwai G Shyamala Thulasimani T Department of Computer Science and Technology Karpagam College of Engineering Coimbatore Tamil Nadu India Electrical and Electronics Engineering Geethanjali College of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Anand Nagar Krishnankoil Tamilnadu India Computer Science College of Computer Science and Information Technology Jazan University Japan Saudi Arabia Civil Engineering School of Engineering SR University Warangal Telangana India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Tamilnadu India

Today, water contamination affects a large portion of the world's population. Manually collecting water samples from various sites and analyzing them in a lab as part of the routine monitoring technique. These approaches used to be effective, but they are now too slow and laborious to be practical. In addition, cutting-edge methods consider a wide range of physical and chemical elements. The standard method of quality monitoring and data sharing is time-consuming, unreliable, and costly. This emphasizes the need for constant, around-the-clock water quality monitoring. Basic Data Preprocessing, feature selection, and model training are the three main pillars of the proposed approach. The proposed method employs the preprocessing tools. The proposed system used the SOFM method (Structure-From-Function-Movement) to identify and eliminate unnecessary features selection. A model's accuracy can be measured with the help of prediction tools like utilizing CNN, LSTM, and TD-CNN-LSTM, models are trained. The proposed model outperforms two current top-tier contenders. The proposed method achieves higher accuracy (about 98.37%) when compared to other approaches like CNN and LSTM.

关键词：

Wideband Antenna Design for 5G mmWave Applications Using Enhanced Adaptive Differential Evolution

学校读者我要写书评

暂无评论

Wideband Antenna Design for 5G mmWave Applications Using Enh...

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Goudos, Sotirios K. Boursianis, Achilles Mohamed, Ali Wagdy Salucci, Marco Koulouridis, Stavros Christodoulou, Christos Aristotle University of Thessaloniki ELEDIA Research Center ELEDIA-AUTH Department of Physics Thessaloniki54124 Greece Cairo University Faculty of Graduate Studies for Statistical Research Operations Research Department Giza Egypt The American University in Cairo School of Sciences & Engineering Department of Mathematics and Actuarial Science Cairo Egypt University of Trento ELEDIA Research Center ELEDIA-UniTN DICAM Trento Italy University of Patras Electrical and Computer Engineering Department Patras Greece The University of New Mexico Department of Engineering and Computing United States

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

Antenna design for 5G mmwave applications is a challenging task. Moreover, if the design specifications require wideband behavior the problem becomes more complex. In this paper, we address the above presented design problem by introducing a new modified E-shaped patch antenna that has an additional third slot. We present a design procedure based on Enhanced Adaptive Differential Evolution. The numerical results show that the obtained best design presents wideband behavior that covers the whole frequency range 2 (FR2) zone and expands up to 60GHz. © 2022 IEEE.

关键词： Design

A Comparative Study of K-means and NMF Clustering Algorithms

学校读者我要写书评

暂无评论

A Comparative Study of K-means and NMF Clustering Algorithms

electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Fahimeh Basiri Ayman Amer Mohammad Javad Ranjbar Naserabadi Mohammad Mahdi Moghimi Applied Mathematics Department Tarbiat Modares University Tehran Iran Faculty of Engineering Zarqa university Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia Technical Inspection Department Petroleum University of Technology Abadan Iran Department of Electrical Engineering Yazd Branch Islamic Azad University Yazd Iran

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

Cluster analysis, also known as clustering, is a multivariate data mining technique whose goal is to classify objects based on a set of selective features. Nonnegative matrix factorization (NMF), and K-means are the most used clustering methods. NMF is a method that breaks down a high-dimensional data matrix into two lower-dimensional matrices with positive elements; while K-means is an algorithm that assigns each data point to a cluster that has a centroid. The main objective of this algorithm is to minimize the total distance between the data points and their respective clusters. In this paper, four datasets, consist of data collected from newswires, radio programs, and television programs are prepared for assessing. Then, they are clustered via NMF and K-means techniques. Furthermore, the results are compared with Purity and Entropy criteria. It can be concluded that both algorithms work better in small dimension datasets rather than high-dimensional ones. Furthermore, NMF has generally a better accuracy.

关键词： TV Data analysis Clustering methods Clustering algorithms Energy measurement Size measurement Entropy

Characterization of n-Dimensional Toric and Burst-Error-Correcting Quantum Codes from Lattice Codes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Trinca, Cibele Cristina Palazzo, Reginaldo Interlando, J. Carmelo Watanabe, Ricardo Augusto de Albuquerque, Clarice Dias de Carvalho, Edson Donizete de Andrade, Antonio Aparecido The Department of Biotechnology and Bioprocess Engineering Federal University of Tocantins TO Gurupi Brazil The School of Electrical and Computer Engineering State University of Campinas Brazil The Department of Mathematics and Statistics San Diego State University San DiegoCA United States The School of Mathematics Statistics and Scientific Computing State University of Campinas Brazil Brazil The Science and Technology Center Federal University of Cariri Juazeiro do Norte Brazil The Department of Mathematics São Paulo State University SP Ilha Solteira Brazil The Department of Mathematics São Paulo State University Brazil

Quantum error correction is essential for the development of any scalable quantum computer. In this work we introduce a generalization of a quantum interleaving method for combating clusters of errors in toric quantum error-correcting codes. We present new n-dimensional toric quantum codes, where n ≥ 5, which are featured by lattice codes and apply the proposed quantum interleaving method to such new n-dimensional toric quantum codes. Through the application of this method to these novel n-dimensional toric quantum codes we derive new n-dimensional quantum burst-error-correcting codes. Consequently, n-dimensional toric quantum codes and burst-error-correcting quantum codes are provided offering both a good code rate and a significant coding gain when it comes to toric quantum codes. Another important consequence from the presented n-dimensional toric quantum codes is that if the Golomb and Welch conjecture in [1] regarding the Lee sphere in n dimensions for the respective close packings holds true, then it follows that these n-dimensional toric quantum codes are the only possible ones to be obtained from lattice codes. Moreover, such a methodology can be applied for burst error correction in cases involving localized errors, quantum data storage and quantum channels with memory. © 2024, CC BY.

关键词： Quantum channel

Displacement Current in Classical and Quantum Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ferry, David K. Oriols, Xavier Eisenberg, Robert School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Departament d’Enginyeria Electrònica Universitat Autònoma de Barcelona Barcelona08193 Spain Department of Physiology and Biophysics Rush University Medical Center ChicagoIL United States Department of Applied Mathematics Illinois Institute of Technology ChicagoIL United States Department of Biomedical Engineering University of Illinois Chicago ChicagoIL United States

It is certain that electrical properties—whether slow (sec) or fast (nsec), even optical (fsec)—are described by Maxwell’s equations, and there are terms that depend on the rate of change of the electric and magnetic fields. In particular, Maxwell's equation for the curl of the magnetic field contains both the steady current and a term depending upon the temporal derivative of the electric displacement field. The latter is referred to as displacement current, and is generally believed to have been included originally by Maxwell himself, although there is evidence it was earlier considered by Kirchhoff. Maxwell's equations and Kirchoff's circuit laws both are important over the wide range of frequencies with which electronics traditionally deals. And, displacement current is an important contribution to these in both classical and quantum mechanics. Here, the development of displacement current, its importance in both classical and quantum mechanics, and some applications are provided to illustrate the fundamental role that it plays in the dynamics of a wide range of systems. © 2024, CC BY.

关键词： Maxwell equations