检索结果-内蒙古大学图书馆

A Neuromorphic Computational Model for Spintronics-based Hopfield Oscillatory Neural Network

IEEE Transactions on Magnetics 2025年

作者： Soni, Sandeep Rezaeiyan, Yasser Boehnert, Tim Ferreira, Ricardo Kaushik, Brajesh Kumar Moradi, Farshad Shreya, Sonal Aarhus University Department of Electrical and Computer Engineering Department Aarhus Denmark Indian Institute of Technology Department of Electronics and Communication Engineering Uttarakhand Roorkee India Braga Portugal

The human brain is competent in information processing and learning, largely due to the coordinated activity of neuronal populations. These populations exhibit rhythmic fluctuations in activity known as oscillatory dynamics, observed across different brain regions. These oscillations are crucial in various cognitive functions, such as memory consolidation, sensory processing, and motor control. This work proposes a novel neuromorphic computational (NC) model comprising analytical derivation for a spintronics-based Hopfield oscillatory neural network (HONN) employing frequency synchronization inspired by the brain's oscillatory mechanism of pattern recognition and associative memory. Kuramoto model, which represents the phase-based coupling of two oscillators, this work presents an extended mathematical analysis (modeling) of frequency and phase-based dual coupling mechanism. Further, this model is translated to the Theile equation which governs the dynamics of magnetic vortex core (such as core position and oscillation frequency) applicable to spintronic-based HONN. This approach uses spin-torque vortex nano-oscillators (SVNOs) as neurons connected via resistive synapses representing synaptic coupling strength. The model describes the analytical relation between the SVNOs and the synaptic element, and how it influences the synchronized frequency (fsync). Stronger coupling aligns fsync closer to the higher gyrotropic frequency of the magnetic vortex core within the network, while weaker coupling promotes fsync closer to the lower one. The synaptic connections transition between low resistance (LRS) and high resistance (HRS) states mimicking biological brain plasticity. This NC model is then utilized to design a spintronic-based HONN circuit to illustrate oscillatory properties, frequency-based synchronization, and resistive coupling to create an energy-efficient and scalable architecture. The proposed NC model represents a promising approach to advancing large-scale

关键词： Spintronics

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Touch Free Smart Home Controlling System Based on Virtual Reality (VR) technology

Design and Development of a Touch Free Smart Home Controllin...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Devi, S. Rukmani Raghi, K.R. Priya, S. Geetha Sathi, G. Kumar, Sarva Naveen Dinesh, M. Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Department of Computer Science Tamil Nadu Chennai India St.Joseph's College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India R.M.D. Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Tamil Nadu Chennai India Mlr Institute of Technology Department of Electronics and Communication Engineering Hyderabad India Saveetha University Department of Vlsi Microelectronics Tamil Nadu Chennai India

ISBN: (纸本)9798350375237

The Touch-Free Smart Home Controlling System based on Virtual Reality (VR) technology represents an innovative approach to home automation, leveraging the immersive capabilities of VR to provide users with seamless and intuitive control over their smart home environment without the need for physical touch. This system integrates VR headsets with motion sensors, depth cameras, and gesture recognition technology to enable users to navigate and interact with a virtual representation of their home environment. Smart home devices such as lights, thermostats, door locks, and entertainment systems are interconnected and controlled through the VR interface, offering users a compelling and immersive way to manage their living space. The central hub acts as the backbone of the system, facilitating communication between the VR interface, sensors, and smart home devices. Performance metrics such as response time, latency, throughput, and power consumption are monitored to ensure optimal system operation. Security measures including user authentication and data encryption are implemented to protect user privacy and prevent unauthorized access. The Touch-Free Smart Home Controlling System based on VR technology not only enhances convenience and accessibility but also represents a significant step forward in the evolution of smart home automation towards more intuitive and immersive user experiences.. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Network Model Based Analysis and Detection of RNA Enabling Convolutional Neural Network 4

A Heterogeneous Network Model Based Analysis and Detection o...

引用

4th International Conference on Smart electronics and Communication, ICOSEC 2023

作者： Priyatharsini, G. Soniya Aruna, M. Myneni, Madhu Bala Kumar, P. Kiran Anil Kumar, D.B. Singh, Vijay Dr. M.G.R. Educational and Research Institute Department of Computer Science and Engineering Tamil Nadu Chennai600095 India Nitte Meenakshi Institute of Technology Department of Electrical and Electronics Engineering Bangalore India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Cvr College of Engineering Department of Computer Science and Engineering Telangana Ibrahimpatnam India School of Electrical and Electronic Engineering Reva University Karnataka Bengaluru India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350300888

RNA is an important target in the research of genetic diseases and disorders since it is essential for the process of gene expression and control. Convolutional neural networks (CNNs) and other machine learning-based methods for analyzing RNA sequences have recently attracted more attention. But reliable analysis and detection are significantly hampered by the enormous variability of RNA sequences. In this research, a brand-new heterogeneous network model for CNN-based RNA analysis and detection is provided. This model accounts for the wide range of RNA sequence properties, such as length fluctuation, secondary structure, and chemical changes. A unified model that incorporates these features is created by combining 1D and 2D convolutional layers. Multiple datasets, including synthetic and real-world datasets, were used to assess proposed model's performance. The outcomes show that the model performs better in terms of accuracy, sensitivity, and specificity than current state-of-the-art approaches. Furthermore, the model's performance is greatly enhanced with the addition of 2D convolutional layers and attention processes, according to rigorous studies to assess the contributions of each component of the model. Overall, the heterogeneous network model offers a reliable and precise method for analyzing and identifying RNA sequences, which has significant ramifications for comprehending hereditary illnesses and creating targeted therapies. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Machinery Fault Diagnoses in High-Voltage Circuit Breakers Using Empirical Mode Decomposition-Support Vector Machine Model 3

Machinery Fault Diagnoses in High-Voltage Circuit Breakers U...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and electronics, ICDCECE 2024

作者： Al-Farouni, Mohammed Sudhakar, A.V.V. Divya, G. Bala Dhandayuthapani, V. Shivakanth, Gandla Department Of Computers Techniques Engineering College Of Technical Engineering The Islamic University Najaf Iraq Department Of Electrical And Electronics Engineering Sr University Warangal India Department Of Ece Nitte Meenakshi Institute Of Technology Bengaluru India Department Of It College Of Computing And Information Sciences University Of Technology And Applied Sciences Shinas campus Shinas Oman Department Of Computer Science And Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad India

ISBN: (纸本)9798350318609

The circuit breakers have a flaw in their trip mechanism. Early mechanical faults like coil-plunger jam are hard to report using traditional fault diagnosis based on the coil current. However, users still have difficulty understanding and trusting the diagnosis results since the standard EMD is opaque in terms of interpretability. In this work, an Empirical Mode Decomposition with Support Vector Machine (EMP-SVM) proposed for machinery fault diagnosis. This work uses the vibration signal recovered from the trip process as an intrinsic time series of the data. At first, The Improved EMD is a data-adaptive multiresolution approach that breaks down signals into physically relevant components based on vibration and coil current signals. Lastly, utilizing the characteristics that were retrieved, the SVM is used to diagnose the defect. The implemented improved EMP-SVM model demonstrates superior performance, achieving Precision of (98.37%), recall of (91.03%) and F1-Score of (96.34%). When compared to previous models like Improved Dempster-Shafer Evidence Theory-Echo State Neural Network (IDSET-ESNN) and Phase Space Reconstruction with Support Vector Machine (PSR-SVM). © 2024 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A Review on Precoding Techniques for Massive MIMO-Based Wireless Communication 2

A Review on Precoding Techniques for Massive MIMO-Based Wire...

引用

2nd International Conference on Microwave, Antenna and Communication, MAC 2024

作者： Kumar, Aman Kumar, Suman Singh, Indrasen Kaur, Jatinder Kaur, Sumanpreet Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Vellore632014 India Chandigarh Group of Colleges Jhanjeri Division of Research & Innovation Chandigarh Engineering College Department of ECE Punjab Mohali140307 India Chandigarh Group of Colleges Jhanjeri Chandigarh Engineering College Department of Computer Science Engineering Punjab Mohali140307 India

ISBN: (纸本)9798350350104

To enhance the performance of fifth-generation (5G) or beyond 5G communication, Massive Multiple Input Multiple Output (mMIMO) technology plays a crucial role. The precoding technique is essential in optimizing the transmission process by mitigating interference and improving the overall spectral efficiency. The paper discusses various precoding strategies, including zero-forcing, minimum mean square error, maximum ratio transmission, and other advanced techniques tailored for maMIMO environments. Furthermore, the impact of channel state information (CSI) on precoding design is explored, considering both idealistic scenarios and practical channel estimation challenges. The objective is to provide researchers, engineers, and practitioners with a comprehensive understanding of the state-of-The-Art precoding techniques in mMIMO, their advantages, limitations, and potential applications in future communication systems. Through this exploration, the paper gives a thorough study of precoding techniques and mMIMO technology for next-generation communication. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Review on Collision Avoidance Application in Automotive Ad Hoc Networks Employing a Novel Source-Based Ant Colony Optimization Routing Protocol Using a Cross-Layer Approach

A Review on Collision Avoidance Application in Automotive Ad...

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Lekshmi, V. Pramila, R Suji Symon, Tibbie Pon Noorul Islam Centre for Higher Education Department of Computer Applications Tamil Nadu Thackalay India Mar Baselios Institute of Technology and Science Department of Computer Science and Engineering Kerala India Noorul Islam Centre for Higher Education Department of Electrical and Electronics Engineering Tamil Nadu Thackalay India

ISBN: (纸本)9798350333244

The term 'Vehicle Ad hoc Network' (VANET) refers to a system in which a collection of non-stationary or stationary vehicles share a wireless connection. Until recently, VANETs were primarily used to improve the safety and convenience of driving. Both the AntHocNet method and the Ant based Routing Algorithm (ARA) rely on ACO. It is a combinational method that combines proactive route maintenance with a reactive setup process for route finding. Its objective is to preserve information about current routes and identify new ones. The term 'Ant Colony Optimization' (ACO) refers to a population-based mathematical heuristic that's capable of providing approximate solutions to difficult optimization problems. The aim of ACO is to solve an optimization problem by sending out a colony of virtual ants to find an optimal solution. Ant colony optimization is a probabilistic technique for finding optimum paths. In this paper a detailed literature review for VANET for collision avoidance application based on Ant colony optimization is surveyed. © 2023 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Energy Efficient Dynamic Particle Swarm Optimisation in Heterogeneous Wireless Communication Networks

Resource Allocation and Energy Efficient Dynamic Particle Sw...

引用

Innovation in technology (ASIANCON), Asian Conference on

作者： Anuradha Bhalerao Pawar G. Kannan T. Anuradha Vignesh V R. Kesavan Jose Anand A Department of Electronics Engineering MIT Academy of Engineering Alandi Pune Maharastra Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Tamil Nadu Department of Electrical and Electronics Engineering KCG College of Technology Tamil Nadu India Department of Computer Science and Engineering Karpagam College of Engineering Tamil Nadu India Institute of Computer Science and Engineering Saveetha School of Engineering SIMTS Tamil Nadu India Department of Electronics and Communication Engineering KCG College of Technology Tamil Nadu India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

This paper investigates the difficult of beam policy in a multi-user peer-to-peer web linkage setting as part of our research. Using a network simulator, the dynamic particle swarm optimization is suggested for this. The challenge is to limit the maximum power consumption per relay, according to minimal Signal to Noise Ratio (SNR) guarantees, after a complete Channel State Information (CSI) is established. It has been established that the non-convex problem satisfies a potent duality. The twofold problem with the highest polynomial complexity was given as Semi Definite Programming (SDP). On the basis of the standards of the optimal dual variables, we looked at the best beam forming vectors for the initial problems in 3 different scenarios. This demonstrated whether the minimum Signal-to-Noise Ratio (SNR) prerequisite for each S-D pair has been met as well as whether a relay's electricity consumption varies among relays.

关键词： Technological innovation Quality of service Throughput Energy efficiency Vectors Peer-to-peer computing Particle swarm optimization Optimization Signal to noise ratio Testing

来源：评论

学校读者我要写书评

暂无评论

Marine Robot for Underwater Surveillance

Marine Robot for Underwater Surveillance

引用

IEEE Students' Conference on Electrical, electronics and computer Science (SCEECS)

作者： Vishnu Gowda H P Deepa N Reddy Tejas B Gowda Shrikala R Yogitha H N Student of Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bengaluru India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bengaluru India Student of Department of Computer Science Engineering BMS Institute of Technology and Management Bengaluru India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

Underwater surveillance has become a crucial area of research, particularly for marine exploration and environmental monitoring, with marine robots playing a vital role. These robots, equipped with sensors and cameras, capture real-time data and images from underwater environments, reducing the need for human intervention in hazardous areas. However, a major challenge in this field is developing reliable communication networks, as underwater environments face limitations in bandwidth, range, and signal attenuation, hindering real-time data transmission. This paper presents a simple marine robot prototype based on the Raspberry Pi Model 4B, utilizing Electronic Speed Controllers (ESCs) and brushless motors for efficient movement. The robot's body is manually designed using 3D printing technology, with PETG (polyethylene terephthalate glycol) material chosen for its water resistance, durability, and buoyancy. The design ensures the robot’s stability and functionality underwater, offering a cost-effective solution for marine robotics while underscoring the need for improved underwater communication technologies.

关键词： Underwater communication Robot vision systems Video surveillance Three-dimensional printing Real-time systems Stability analysis Sensors Robots Marine robots Testing

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Deep Learning Framework for Breast Cancer Prediction

A Novel Ensemble Deep Learning Framework for Breast Cancer P...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Shaker Reddy, Pundru Chandra Nithyapriya, S. Sharma, Nipun Maheswari, S. Jayaram, B. Katale, Tejaswini SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Anna University Artificial Intelligence and Data Science Bannari Amman Institute of Technology Tamil Nadu Chennai India Presidency University Bangalore Electronics and Communication Engineering Karnataka India Sathyabama Institute of Science and Technology Department of Mathematics Tamil Nadu Chennai India Computer Science and Business System RMK Engineering College Tamil Nadu Kavaraipettai India Vishwakarma Institute of Technology Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798350319200

Because of its high incidence and high mortality rate, breast cancer requires reliable means of early detection and diagnosis to improve survival rates for its patients. With advantages including increased accuracy and efficiency, deep learning (DL) and machine learning (ML) methods are quickly becoming indispensable in the fight against breast cancer. However, there is a need for additional study because existing approaches have scalability and performance constraints. Utilizing a pre-trained ResNet50V2 and ensemble-based ML approaches, we offer a hybrid approach to reliable breast cancer diagnosis in this study. Learning and extracting latent trends from complex breast-cancer(BC) images is made possible by DL's incorporation, with ML strategies contributing interpretability and generalizability. We performed wide experiments utilizing a openly accessible Invasive-Ductal-Carcinoma(IDC) dataset based on breast histopathology images of varying sample sizes. The resilience and great performance of our hybrid model are supported by the results of our extensive experiments. When compared to state-of-the-art models, our 95% accuracy rate, 94.5 precision, 94.2 recall, and 94.6 F1 score are all improvements. We also found that the best ML model to use with the ResNet50V2 architecture is the Light Boosting Classifier (LGB). This study's findings provide substantial contributions to the field of breast cancer diagnosis thanks to its novel approach, in-depth performance analysis, and trustworthy evaluation. In addition, it may help doctors make better decisions, provide better care, and boost results for people with breast cancer. © 2023 IEEE.

关键词： breast histopathology-image Breast-cancer DL ML transfer-learning

来源：评论

学校读者我要写书评

暂无评论

Time-domain constraints for passive materials: The Brendel-Bormann model revisited

引用

Physical Review B 2024年第2期110卷 024307-024307页

作者： Sven Nordebo Martin Štumpf Department of Physics and Electrical Engineering Linnæus University Lerch Laboratory of em Research Department of Radio Electronics FEEC Brno University of Technology Department of Computer Science Electrical and Space Engineering EISLAB Luleå University of Technology

This paper presents a systematic approach to derive physical bounds for passive systems, or equivalently for positive real (PR) functions, directly in the time-domain (TD). As a generic, canonical example we explore the TD dielectric response of a passive material. We will furthermore revisit the theoretical foundation regarding the Brendel-Bormann (BB) oscillator model which is reportedly very suitable for the modeling of thin metallic films in high-speed optoelectronic devices. To this end, an important result here is to re-establish the physical realizability of the BB model by showing that it represents a passive and causal system. The theory is based on Cauer's representation of an arbitrary PR function together with associated sum rules (moments of the measure) and exploits the unilateral Laplace transform to derive rigorous bounds on the TD response of a passive system. Similar bounds have recently been reported for more general casual systems with other a priori assumptions. To this end, it is important to note here that the existence of useful sum rules and related physical bounds rely heavily on an assumption about the PR functions having a low- or high-frequency asymptotic expansion at least of odd order 1. As a particular numerical example, we consider here the electric susceptibility of gold (Au) which is commonly modeled by well established Drude or BB models. Explicit physical bounds are given as well as an efficient fast-Fourier transform -based numerical procedure to compute the TD impulse response associated with the nonrational BB model.

关键词： Capacitance Dielectric properties Permittivity Mathematical physics methods

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：