检索结果-内蒙古大学图书馆

4th International Conference for Emerging technology, INCET 2023

作者： Nair, Keertana Gopikrishna, P.B. Rubell Marion Lincy, G. Indian Institute of Information Technology Kottayam Department of Computer Science and Engineering Kottayam Pala India

ISBN: (纸本)9798350335750

Brain-computer Interface (BCI) is a system which is used to interact with the computer system and can be used to control different assistive devices by utilizing the brain signals such as Electroencephalography (EEG). Motor Imagery (MI) is considered one of the prominent fields of BCI systems which are based on EEG signals. These systems have the capability to restore motor ability in humans. Though a good deal of Machine Learning (ML) approaches were investigated in recent years, studies that explore BCI with Deep Learning methods or Wavelet Scattering Transforms have not been extensively used. Also, conventional classification methods show longer computational time and they are incapable of processing non-linear and non-stationary EEG signals. The proposed system aims to explore the area of a calibration-free or a subject-independent model by integrating Deep Convolutional Neural Network (CNN) with Wavelet Scattering Network by utilizing feature maps learned from both CNN and Scattering networks to tackle the non-linearity and non-stationarity of the EEG signals and thereby to improve the classification accuracy of the model to build a more robust and generalized MI-based BCI system. The proposed model outperforms the state-of-the-art techniques, achieving an accuracy of 87% and 93% on BCIC IV 2a and SMR-BCI datasets respectively. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Enhancing Effective Spectrum Utilization in 6G Cellular Networks via Sharing Algorithms 5th

Enhancing Effective Spectrum Utilization in 6G Cellular Netw...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： kudari, Jayashree M. Garg, Aanchal Sridevi, S. Savita Department of Computer Science and Information Technology Jain University Karnataka Bangalore India Department of Electronic & Communication Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

The emerging 6G mobile network technology presents an opportunity to noticeably increase spectrum utilization in comparison to previous generations. This paper introduces a singular sharing algorithm to correctly utilize the spectrum in 6G mobile networks. This set of rules leverages device mastering techniques to dynamically calculate a charge primarily based at the average channel usage and bandwidth usage through distinct users. Moreover, it gives a dispensed mechanism to define the resource allocation method used in different communique situations. The proposed set of rules is powerful, reliable, and cozy, and it is able to efficaciously apply spectrum sharing amongst unique users to maximize spectral performance. Simulation results display that the proposed set of rules achieves giant improvements in spectral efficiency as compared to both a traditional unmarried-mobile method, and a present sharing algorithm proposed in the literature. Finally, experimental results are supplied, which demonstrate the effectiveness of the proposed set of rules in real-world check setups. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Traffic-Sign Detection and Recognition Using Deep Learning 10

Large-Scale Traffic-Sign Detection and Recognition Using Dee...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Eeswara Manikanta Reddy, P. Muramalla, Pranav Sri Vidhya, S.R. Cruz Antony, J. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350353068

Automated traffic sign detection and identification plays an important position in site visitors sign stock control. The site visitors sign affords an accurate and timely way to manage inventory with minimum human attempt. In the computer imaginative and prescient network, site visitors sign popularity and identity is a nicely-researched trouble. Most of the prevailing strategies paintings well on visitor's indicators required for self-sustaining and advanced motive force help structures. However, this represents a extraordinarily small number of all site visitors signs (approximately 50 kinds out of numerous hundreds) and the performance of the last site visitors symptoms is essential to cast off guide paintings in coping with the listing of visitors symptoms. There is an open query., in this text we talk the trouble to identifying and also identifying a big variety of traffic sign types suitable for automating site visitors signal stock management. We undertake a Convolutional Neural Network (CNN) technique, Mask R-CNN, to deal with the entire detection and identity method through give up-to cease gadget studying. We advise some of upgrades that are evaluated in detecting site visitor's signs and improve the over all performance. This approach is used to discover 200 sorts of visitors symptoms represented in our new dataset. Results are reported on extra tough site visitors signal sorts that have no longer been taken into consideration in previous paintings. We gift an in depth analysis of a deep studying technique to locate site visitors signs and symptoms with big variations in look inside a category and display error quotes below 3% with the proposed technique, which has capability for realistic applications in site visitors signal inventory management. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enhanced Security for LEO Satellite Firmware Updates in Beyond-5G NTN Networks 29

Blockchain-Enhanced Security for LEO Satellite Firmware Upda...

引用

29th IEEE International Workshop on computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2024

作者： Worku, Yonatan M. Tshakwanda, Petro M. Tsegaye, Henok B. Christodoulou, Christos Devetsikiotis, Michael Sacchi, Claudio University of New Mexico Department of Electrical and Computer Engineering United States University of Trento Department of Information Engineering and Computer Science Italy

ISBN: (纸本)9798350377644

The integration of terrestrial and Non-Terrestrial Networks (NTNs) represents a significant advancement in communication technology in the framework of the ongoing beyond-5G standardization process. This integration offers broader coverage, especially in remote and underserved areas, and improved reliability through diversified network paths. Additionally, it paves the way for new services and applications that benefit from ubiquitous connectivity. To achieve enhanced Quality of Service (QoS) and Service Level Agreements (SLAs), the end-to-end network should be open and visible to service providers and users. However, such a clear-mode approach introduces various security threats, making the network susceptible to unauthorized access and service disruption. To address these challenges, a blockchain-based satellite firmware update strategy across terrestrial 5G core and access networks is proposed. This study explores the tradeoff between throughput and QoS in the 5G NTN network when blockchain is implemented. Our experimental setup involved a network of Low Earth Orbit (LEO) satellites integrated with a 5G core, deploying a blockchain-based authentication mechanisms to secure satellite communications. The results show a tangible improvement in authentication efficiency, despite a throughput degradation of around 10 % and a latency increase of 17 % from the baseline values obtained without blockchain security. This tradeoff highlights the cost of enhanced security counter-measures in terms of network performance. Nonetheless, the security benefits, measured through successful authentication attempts, fully justify blockchain integration in scenarios where security is paramount. The proposed approach promises to secure communications in '5G and beyond' NTN hybrid environments by ensuring integrity and confidentiality to the traffic flows. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of Healthy and Unhealthy Food Items using Deep Learning 7

Prediction of Healthy and Unhealthy Food Items using Deep Le...

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Natesan, P. Thamil Selvan, R. Shrivarshini, M. Dhanya, B. Kalaiselvi, S. Department of Computer Science and Engineering Kongu Engineering College Erode India Department of Information Technology Kongu Engineering College Erode India Department of Computer Technology Kongu Engineering College Erode India

ISBN: (纸本)9781665464086

In recent times, people are mostly attracted to fast food. In this paper, a model for categorizing food products using convolutional neural networks has been built. Deep learning facts are being used in day-to-day life and recognizing objects through image processing. Convolutional neural networks are effective for classifying photographs of food because they exclude distracting characteristics from images. By implementing this model, the layers involved here to convert the three-dimensional input into an output volume and to filter input to a higher level of abstraction. This proposed model may help people to identify healthy and unhealthy food items and save us from causes of diseases. This study used image datasets we built, with the images coming from social media and already-existing image datasets (Kaggle) and (Google). The findings of this study demonstrate how much more effective the system is in classifying images when compared to other approaches. The suggested method includes more visual elements than other method and that it performs better at classifying food images. According to the experimental findings, the classification of foods as healthy or unhealthy is 90% accurate. © 2023 IEEE.

关键词： Food products

来源：评论

学校读者我要写书评

暂无评论

Enhanced UAV Pursuit-Evasion Using Boids Modelling:A Synergistic Integration of Bird Swarm Intelligence and DRL

引用

computers, Materials & Continua 2024年第9期80卷 3523-3553页

作者： Weiqiang Jin Xingwu Tian Bohang Shi Biao Zhao Haibin Duan Hao Wu School of Information and Communications Engineering Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an710049China China Academy of Electronics and Information Technology China Electronics Technology Group Corporation(CETC)Beijing100041China Department ofAutomatic Control School of Automation Science and Electrical EngineeringBeihangUniversityBeijing100191China

TheUAV pursuit-evasion problem focuses on the efficient tracking and capture of evading targets using unmanned aerial vehicles(UAVs),which is pivotal in public safety applications,particularly in scenarios involving intrusion monitoring and *** address the challenges of data acquisition,real-world deployment,and the limited intelligence of existing algorithms in UAV pursuit-evasion tasks,we propose an innovative swarm intelligencebased UAV pursuit-evasion control framework,namely“Boids Model-based DRL Approach for Pursuit and Escape”(Boids-PE),which synergizes the strengths of swarm intelligence from bio-inspired algorithms and deep reinforcement learning(DRL).The Boids model,which simulates collective behavior through three fundamental rules,separation,alignment,and cohesion,is adopted in our *** integrating Boids model with the Apollonian Circles algorithm,significant improvements are achieved in capturing UAVs against simple evasion *** further enhance decision-making precision,we incorporate a DRL algorithm to facilitate more accurate strategic *** also leverage self-play training to continuously optimize the performance of pursuit *** experimental evaluation,we meticulously designed both one-on-one and multi-to-one pursuit-evasion scenarios,customizing the state space,action space,and reward function models for each *** simulations,supported by the PyBullet physics engine,validate the effectiveness of our proposed *** overall results demonstrate that Boids-PE significantly enhance the efficiency and reliability of UAV pursuit-evasion tasks,providing a practical and robust solution for the real-world application of UAV pursuit-evasion missions.

关键词： UAV pursuit-evasion swarm intelligence algorithm Boids model deep reinforcement learning self-play training

来源：评论

学校读者我要写书评

暂无评论

A coherent approach-based fine-tuning of segment anything model plus watershed algorithm for instance segmentation of mitochondria in electron microscopy images

引用

IEEE Access 2025年 13卷 98088-98105页

作者： Faska, Zahra Khrissi, Lahbib Mountasser, Imadeddine Haddouch, Khalid Akkad, Nabil El Alshathri, Samah El-Shafai, Walid Sidi Mohamed Ben Abdellah University Laboratory of Engineering Systems and Applications ENSA Fez Morocco Princess Nourah Bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt

Increasingly available ultrastructural data from a continuously growing diversity of experimental conditions are driving new opportunities for fruitful neuroscientific hypotheses tested in intracellular compartments such as the nanoscale roles of, e.g., the mitochondria. Reliable morphological statistics are based on achieving highly accurate semantic segmentations of EM images. The state-of-the-art deep CNNs can be somewhat brittle;they tend to provide coarse and high-frequency-oscillatory solutions with discontinuities and false positives even for simple mitochondria segmentation. Historically, the current state-of-the-art in medical image segmentation would involve some variant of the encoder-decoder architecture, such as the U-Net architecture. The SAM does not perform as well, since it has not been explicitly trained for the task and does not demonstrate user-interactive, over one billion annotations mostly for natural images. However, the SAM may be applied to segment anything, including medical image segmentation challenging new datasets. This work is aimed at the difficult task of implementing domain adaptation in mitochondria segmentation within EM images obtained from various tissues and species, using deep learning. We do a systematic study to assess SAM's ability to perform segmentation in medical images, measure its performance on volumetric EM datasets, and show that it is powerful at segmenting instances even under challenging imaging conditions. We provide a fine-tuning SAM which can be naturally trained by SAM at an exemplary scale, benefiting from a diverse and large dataset over one million image masks in 11 modalities. This model would be able to perform precise segmentation for a wide range of targets under various imaging conditions, at the level of performance of specialized U-Net models, or even better. A visual comparison is shown between our fine-tuning SAM model and U-Net, along with an examination of different watershed post-processing st

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

PRF: deep neural network compression by systematic pruning of redundant filters

引用

Neural Computing and Applications 2024年第33期36卷 20607-20616页

作者： Sarvani, C.H. Ghorai, Mrinmoy Basha, S. H. Shabbeer Computer Vision Group Indian Institute of Information Technology Andhra Pradesh Sri City Chittoor517646 India School of Computer Science and Engineering RV University Karnataka Bengaluru560059 India

In deep neural networks, the filters of convolutional layers play an important role in extracting the features from the input. Redundant filters often extract similar features, leading to increased computational overhead and larger model size. To address this issue, a two-step approach is proposed in this paper. First, the clusters of redundant filters are identified based on the cosine distance between them using hierarchical agglomerative clustering (HAC). Next, instead of pruning all the redundant filters from every cluster in single-shot, we propose to prune the filters in a systematic manner. To prune the filters, the cluster importance among all clusters and filter importance within each cluster are identified using the 1-norm based criterion. Then, based on the pruning ratio filters from the least important cluster to the most important ones are pruned systematically. The proposed method showed better results compared to other clustering-based works. The benchmark datasets CIFAR-10 and ImageNet are used in the experiments. After pruning 83.92% parameters from VGG-16 architecture, an improvement over the baseline is observed. After pruning 54.59% and 49.33% of the FLOPs from ResNet-56 and ResNet-110, respectively, both showed an improvement in accuracy. After pruning 52.97% of the FLOPs, the top-5 accuracy of ResNet-50 drops by only 0.56 over ImageNet. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Framework for Situational Aspects-Based Annotation and Classification of International Student’s Tweets during COVID-19

引用

computers, Materials & Continua 2023年第6期75卷 5355-5377页

作者： Shabir Hussain Muhammad Ayoub Yang Yu Junaid Abdul Wahid Akmal Khan Dietmar P.F.Moller Hou Weiyan School of Information Engineering Zhengzhou UniversityZhengzhouChina School of Computer Science and Engineering Central South UniversityChangshaChina Department of Data Science The Islamia University of BahawalpurBahawalpurPakistan Clausthal University of Technology Clausthal-ZellerfeldGermany

As the COVID-19 pandemic swept the globe,social media plat-forms became an essential source of information and communication for *** students,particularly,turned to Twitter to express their struggles and hardships during this difficult *** better understand the sentiments and experiences of these international students,we developed the Situational Aspect-Based Annotation and Classification(SABAC)text mining *** framework uses a three-layer approach,combining baseline Deep Learning(DL)models with Machine Learning(ML)models as meta-classifiers to accurately predict the sentiments and aspects expressed in tweets from our collected Student-COVID-19 *** the pro-posed aspect2class annotation algorithm,we labeled bulk unlabeled tweets according to their contained aspect ***,we also recognized the challenges of reducing data’s high dimensionality and sparsity to improve performance and annotation on unlabeled *** address this issue,we proposed the Volatile Stopwords Filtering(VSF)technique to reduce sparsity and enhance classifier *** resulting Student-COVID Twitter dataset achieved a sophisticated accuracy of 93.21%when using the random forest as a *** testing on three benchmark datasets,we found that the SABAC ensemble framework performed exceptionally *** findings showed that international students during the pandemic faced various issues,including stress,uncertainty,health concerns,financial stress,and difficulties with online classes and returning to *** analyzing and summarizing these annotated tweets,decision-makers can better understand and address the real-time problems international students face during the ongoing pandemic.

关键词： COVID-19 pandemic situational awareness ensemble learning aspect-based text classification deep learning models international students topic modeling

来源：评论

学校读者我要写书评

暂无评论

Visual Lip-Reading for Quranic Arabic Alphabets and Words Using Deep Learning

引用

computer Systems science & engineering 2023年第9期46卷 3037-3058页

作者： Nada Faisal Aljohani Emad Sami Jaha Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia

The continuing advances in deep learning have paved the way for several challenging *** such idea is visual lip-reading,which has recently drawn many research ***-reading,often referred to as visual speech recognition,is the ability to understand and predict spoken speech based solely on lip movements without using *** to the lack of research studies on visual speech recognition for the Arabic language in general,and its absence in the Quranic research,this research aims to fill this *** paper introduces a new publicly available Arabic lip-reading dataset containing 10490 videos captured from multiple viewpoints and comprising data samples at the letter level(i.e.,single letters(single alphabets)and Quranic disjoined letters)and in the word level based on the content and context of the book Al-Qaida *** research uses visual speech recognition to recognize spoken Arabic letters(Arabic alphabets),Quranic disjoined letters,and Quranic words,mainly phonetic as they are recited in the Holy Quran according to Quranic study aid entitled Al-Qaida *** study could further validate the correctness of pronunciation and,subsequently,assist people in correctly reciting ***,a detailed description of the created dataset and its construction methodology is *** new dataset is used to train an effective pre-trained deep learning CNN model throughout transfer learning for lip-reading,achieving the accuracies of 83.3%,80.5%,and 77.5%on words,disjoined letters,and single letters,respectively,where an extended analysis of the results is ***,the experimental outcomes,different research aspects,and dataset collection consistency and challenges are discussed and concluded with several new promising trends for future work.

关键词： Visual speech recognition lip-reading deep learning quranic Arabic dataset Tajwid

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：