检索结果-内蒙古大学图书馆

Braille–Latin conversion using memristive bidirectional associative memory neural network

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12511-12534页

作者： Vaidyaraman, Jayasri Thyagarajan, Abitha K. Shruthi, S. Ravi, V. School of Electronics Engineering Vellore Institute of Technology Chennai India Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States

Artificial neural networks (ANNs) are finding increasing use as tools to model and solve problems in almost every discipline in today’s world. The successful implementation of ANNs in software—particularly in the fields of deep learning and machine learning—has spiked an interest in designing hardware architectures that are custom-made to implement ANNs. Several categories of ANNs exist. The two-layer bidirectional associative memory (BAM) is a particular class of hetero-associative memory networks that is extremely efficient and exhibits good performance for storing and retrieving pattern pairs. The memristor is a novel hardware element that is well-suited to modelling neural synapses because it exhibits tunable resistance. In this work, in order to create a device that can perform Braille–Latin conversion, we have implemented a circuit realization of a BAM neural network. The implemented hardware BAM uses a memristor crossbar array for modelling neural synapses and a neuron circuit comprising an I-to-V converter (resistor), voltage comparator, D flip-flop, and inverter. The efficiency of the implemented hardware BAM was tested initially using 2 × 2 and 3 × 3 patterns. Upon successfully verifying the ability of the implemented BAM to store and retrieve simple pattern pairs, it was trained for a pattern-recognition application, namely mapping Braille alphabets to their Latin counterparts and vice versa. The performance of the implemented BAM network is robust even on the introduction of noise. The application can recognize the input patterns with accuracies of 100% in either direction when tested with up to 30% noise. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Group Recommendation Method Based on Graph Neural Network

Group Recommendation Method Based on Graph Neural Network

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Lu, Mengye Zhu, Peng Miao, Chun Wang, Youjian Wang, Jiacun Nanjing University of Science and Technology School of Economics and Management Nanjing China Monmouth University Department of Computer Science and Software Engineering NJ United States

ISBN: (纸本)9798350376739

Group activities are becoming more and more common on the Internet in the big data environment. Which makes many scholars focus on how to recommend items or activities to a group. However, conventional recommendation systems grapple with issues like data sparsity and the cold start problem, which limits the relevance and accuracy of recommendation. Therefore, this paper conducts an in-depth exploration of group recommendation methods utilizing graph neural networks and introduces a novel recommendation framework aimed at enhancing the efficacy of group recommendations. Firstly, this paper discusses how to construct an effective graph structure to encode the social interaction and individual characteristics of users. Then, an improved graph neural network architecture is proposed. Finally, extensive experimental evaluation is carried out on actual datasets, and the findings demonstrate that our framework markedly enhances the accuracy of recommendations. © 2024 IEEE.

关键词： Graph neural network Group recommendation Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Ultrafast magneto-optical dynamics in nickel(111)single crystal studied by the integration of ultrafast reflectivity and polarimetry probes

引用

Chinese Physics B 2024年第3期33卷 65-69页

作者：匡皓余军潇陈洁 H.E.Elsayed-Ali 李润泽 Peter M.Rentzepis School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China Center for Transformative Science ShanghaiTech UniversityShanghai 201210China Center for Ultrafast Science and Technology Key Laboratory for Laser Plasmas (Ministry of Education)Collaborative Innovation Center of IFSA (CICIFSA)School of Physics and AstronomyShanghai Jiao Tong UniversityShanghai 200240China Department of Electrical and Computer Engineering Old Dominion UniversityNorfolkVirginia 23529USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege StationTexas 77843USA

With the integration of ultrafast reflectivity and polarimetry probes,we observed carrier relaxation and spin dynamics induced by ultrafast laser excitation of Ni(111)single *** carrier relaxation time within the linear excitation range reveals that electron-phonon coupling and dissipation of photon energy into the bulk of the crystal take tens of *** the other hand,the observed spin dynamics indicate a longer time of about 120 *** further understand how the lattice degree of freedom is coupled with these dynamics may require the integration of an ultrafast diffraction probe.

关键词： ultrafast spin dynamics non-equilibrium dynamics multi-probe

来源：评论

学校读者我要写书评

暂无评论

Local binary pattern-based reversible data hiding

引用

CAAI Transactions on Intelligence technology 2022年第4期7卷 695-709页

作者： Monalisa Sahu Neelamadhab Padhy Sasanko Sekhar Gantayat Aditya Kumar Sahu Department of Computer Science and Engineering School of Engineering and TechnologyGIET UniversityGunupurOdishaIndia Department of Computer Science and Engineering GMRITRajamAndhra PradeshIndia Department of CSE Vignan's Foundation for Science Technology and ResearchVadlamudiAndhra PradeshIndia

A novel local binary pattern-based reversible data hiding(LBP-RDH)technique has been suggested to maintain a fair symmetry between the perceptual transparency and hiding *** embedding,the image is divided into various 3×3 ***,using the LBP-based image descriptor,the LBP codes for each block are ***,the obtained LBP codes are XORed with the embedding bits and are concealed in the respective blocks using the proposed pixel readjustment ***,each cover image(CI)pixel produces two different stego-image ***,during extraction,the CI pixels are restored without the loss of a single bit of *** outcome of the proposed technique with respect to perceptual transparency measures,such as peak signal-to-noise ratio and structural similarity index,is found to be superior to that of some of the recent and state-of-the-art *** addition,the proposed technique has shown excellent resilience to various stego-attacks,such as pixel difference histogram as well as regular and singular ***,the out-off boundary pixel problem,which endures in most of the contemporary data hiding techniques,has been successfully addressed.

关键词： hiding capacity(HC) local binary pattern(LBP) peak signal-to-noise ratio(PSNR) reversible data hiding

来源：评论

学校读者我要写书评

暂无评论

Transformer Based Multi-view Learning for Interagting Static and Dynamic Complementarity of Brain Function

Transformer Based Multi-view Learning for Interagting Static...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shengbing Pei Yan Wang Zhao Lv Chao Zhang School of Computer Science and Technology Anhui University Anhui China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dynamic temporal information and static connectivity information derived from functional magnetic resonance imaging (fMRI) can assist in the diagnosis of neurological disorders. However, existing disease diagnosis methods primarily rely on information from a single view, neglecting the advantages of multi-view information fusion. In this work, we propose an end-to-end multi-view fusion method that pre-trains on one view of fMRI data and fine-tunes on another view for disease identification. First, the dynamic temporal information and static connectivity information are integrated during the pre-training stage based on the consistency between the two views, effectively combining complementary information from both data types to improve disease identification accuracy. Finally, in the fine-tuning stage, for different fine-tuning datasets, we combine the residual connections in the model with the self-attention mechanism through the hadamard product. This guides the learning process and can be seen as a form of regularization or inductive bias, enhancing the models ability to learn from the data. Experiments conducted on the ADHD-200 dataset demonstrate that: 1) our method effectively fuses temporal and connectivity information from fMRI, improving the accuracy of brain disorder identification; 2) analyzing the consistency between the two views validates the effectiveness of the pre-training strategy and its positive impact on accuracy; 3) the residual attention maps of the model fine-tuned with functional connectivity networks (FCN) capture distinct symmetrical connections, which align with the inherent symmetry of FCN, supporting the rationale for using the hadamard product.

关键词： Neurological diseases Accuracy Fuses Magnetic resonance Functional magnetic resonance imaging Signal processing Brain modeling Transformers Medical diagnosis Speech processing

来源：评论

学校读者我要写书评

暂无评论

MDCFS: few-shot object detection with multilevel decoupled classifiers

引用

Optoelectronics Letters 2025年

作者： LI Chuanhui ZHOU Mian FENG Zhikun SUI Zezhou GAO Zhan School of Computer Science and Engineering， Tianjin University of Technology

Few-shot object detection poses unique challenges as it requires effectively learning novel classes with limited labeled data. Current approaches often suffer from biases towards base classes during fine-tuning， leading to suboptimal performance on detecting novel classes. Additionally， in complex scenes， the confusion between foreground and background objects further affects the accuracy and robustness of the model. To address these issues， we propose the Multilevel Decoupling Classification Few-Shot Algorithm (MDCFS). we decouple the standard classifier into a parallel foreground classifier and a background classifier in the Few-Shot Object Detection (FSOD) setting. This decoupling enables the independent separation of positive samples from noisy negative samples， alleviating the foreground-background confusion problem commonly encountered in few-shot detectors. For Generalized Few-Shot Object Detection (G-FSOD)， where the few-shot dataset contains base classes， we further decouple the foreground classification head into a base class classification head and a novel class classification head. To ensure balance， we assign more weight to the novel class classification head， effectively addressing the bias towards base classes. Furthermore， we optimize the initial weights of the few-shot fine-tuning stage， significantly reducing training time and mitigating catastrophic forgetting in G-FSOD. Additionally， we incorporate metric learning into our model with minimal cost. Experimental results demonstrate the effectiveness of our approach. Compared to state-of-the-art few-shot object detection methods based on fine-tuning， MDCFS achieves performance improvements of up to 6.3% on the PASCAL VOC dataset and 1.5% on the COCO dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discriminative Deep Neural Network Model for In-air Handwritten Chinese Character Recognition 25

Discriminative Deep Neural Network Model for In-air Handwrit...

引用

Proceedings of the 2025 3rd International Conference on Communication Networks and Machine Learning

作者： Hu Deng Xiwen Qu School of Computer Science and Information Technology Anhui University of Technology Ma'anshan Anhui China School of Computer Science and Technology Anhui University of Technology Ma'anshan Anhui China

ISBN: (纸本)9798400713231

An end-to-end discriminative convolutional neural network (CNN) model is proposed to ex-tract discriminative features from the sequential coordinates of in-air handwritten Chinese characters, addressing the problem in existing CNN models that require data format conversion, thereby improving recognition speed. The Softmax cross-entropy loss function struggles to amplify inter-class differences. To address this, a discriminative loss function is introduced, which reduces the distance between a sample and the mean of its corresponding class while in-creasing the distance between the sample and the mean of its closest opposing class, thus enhancing the model's discriminative ability. Experimental results show that compared to the 1-dimensional CNN model, the proposed method achieves higher recognition accuracy and faster average recognition speed, with 96.90% accuracy and an average speed of 6 milliseconds.

关键词： Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Optimized Sensor Network Design for Real-Time Environmental Monitoring

Optimized Sensor Network Design for Real-Time Environmental ...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Harron, Syed Shukla, Gaurav Kaushik, Harshita Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350383348

A sensor community is a set of interconnected sensors that can degree, monitor, and report phenomena within the environment. Sensor networks have many packages consisting of actual-time environmental tracking. A good way to effectively use these networks for monitoring, an optimized network layout needs to be employed to ensure that the network can meet the necessities of its operational demands. This paper proposes a fashionable-motive sensor network design framework for real-time environmental tracking. The proposed framework gives a step-by-step technique to optimize a sensor network design for the project at hand. It begins with a version of the surroundings that the sensor community will screen, which is used to generate sensor node configurations and topologies. These configurations and topologies are then used to lay out the sensor community such that its deployment is optimized for the surroundings. The design framework makes use of a community optimization set of rules to attain a configuration that maximizes the network's performance and is capable of meeting its operational requirements. The set of rules operates with the aid of looking through the distance of all feasible sensor community topologies, looking for those that have the first-rate value-benefit ratio. The algorithm can be further progressed by way of the usage of the device, gaining knowledge of strategies, which makes it capable of managing extra complex eventualities. © 2024 IEEE.

关键词： Algorithm Community Eventualities Interconnected Requirements Sensor Strategies Value-Benefit

来源：评论

学校读者我要写书评

暂无评论

Exploiting Convolutional Neural Networks for Automated Pathology Image Classification

Exploiting Convolutional Neural Networks for Automated Patho...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Sharma, Sunil Menaka, C. Singh, Akhilendra Pratap Vivekananda Global University Department of Computer Science & Application Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

Convolutional neural networks (CNNs) are a deep mastering method for the computerized pathology photograph category. With the improvement of superior imaging techniques, the quantity of virtual and representable pathology pix has increased notably. Automatic picture evaluation has become increasingly crucial to exploit those photographs for clinical selections. CNNs have attracted huge interest and were established to be very powerful for automated photograph classification and object detection. The improvement of deep getting-to-know based on Convolutional Neural Networks (CNNs) for computerized pathology photo classes has been a focal point of research in current years. This paper critiques the recent advances in CNNs in automatic pathology image type. The key architectures and algorithms for CNNs are summarized, and their capability applicability in pathology picture classification is discussed. This overview also introduces the maximum hit CNN methods that have been proposed and have proven promising consequences in pathology photograph category duties. The paper concludes with a dialogue of future research directions in this area. Convolutional neural networks (CNNs) are a deep mastering method for the computerized pathology photograph category. With the improvement of superior imaging techniques, the quantity of virtual and representable pathology pix has increased notably. To exploit those photographs for clinical selections, automatic picture evaluation has grown to be an increasingly number of crucial. CNNs have attracted huge interest and were established to be very powerful for automated photograph classification and object detection. The improvement of deep getting-to-know based on Convolutional Neural Networks (CNNs) for computerized pathology photo classes has been a focal point of research in current years. This paper critiques the recent advances in CNNs in automatic pathology image type. The key architectures and algorithms for CNNs are summarized,

关键词： classification Convolutional development discussion pathology

来源：评论

学校读者我要写书评

暂无评论

State of health estimation of lithium-ion batteries based on TiDE

State of health estimation of lithium-ion batteries based on...

引用

2024 China Automation Congress, CAC 2024

作者： Li, Hui Cui, Fangshu Shi, Yuanhao Wang, Bohui School of Electrical and Control Engineering North University of China Taiyuan China School of Computer Science and Technology North University of China Taiyuan China School of Cyber Science and Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798350368604

Given the widespread use of lithium-ion batteries, accurately forecasting their State of Health (SOH) is crucial for ensuring the secure and reliable operation of equipment. The local capacity regeneration during battery degradation can undermine prediction accuracy. This research introduces an MDT-FOA+TiDE approach for predicting SOH in lithium-ion batteries using multidimensional time series data. Initially, capacity and various feature data from the degradation process were collected and health indicators were derived. Features with high correlation to capacity were integrated into multidimensional time series. Subsequently, the Time-series Dense Encoder (TiDE) model was employed for training and prediction, while the Fox Optimization Algorithm (FOA) was used for model optimization. Experimental results using the NASA dataset demonstrate that the proposed approach outperforms SVR and LSTM models that utilize univariate data and MDT-TiDE model without FOA optimization. © 2024 IEEE.

关键词： lithium-ion batteries local capacity regeneration multidimensional time series state of health

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：