检索结果-内蒙古大学图书馆

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Nandalal, V. Muruganandham, A. Karthikeyan, S. Iqbal, J L Mazher Manikandan, T. Sri Krishna College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Vtu Rajarajeswari College of Engineering Department of Electronics and Communication Engineering Belagavi India Velammal Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India R&d Institute of Science and Technology Vel Tech Rangarajan Dr. Sagunthala Department of Electronics and Communication Engineering Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

We present this article which is a research summary on the fault detection and diagnosis in the wireless sensor networks (WSN) by means of the transformer model. Our methodology puts the emphasis on an innovative approach that uses intense machine learning, domain-specific know-how to increase the performance and dependability of fault detection techniques in WSNs. In depth study has been done using of sensors "in vivo"data and comparison of transformer based methods with traditional machine learning algorithms, which includes CNNs, RNNs and SVMs. The experimental results indicate that Transformer we have used yields the best result concerning precision (0. 95), precision (0. 93), recall (0. The sequence accuracy (0. 93), overall accuracy (96), and F1-score (0. 94) prove this model is quite optimized in studying and finding out the spatial and temporal dependencies and patterns in WSN data. Furthermore, the fault detection system that is based on the transformer model is very reliable, robust, and precise since it performs its task of identification of different types of faults which occur due to failure of sensors, communication or impact of environment with accuracy. In compliance with this, our evaluation of resources consumption shows, that the transformer-based fault detection and diagnosis systems are moderately consuming the resources, as detected CPU usage gets 80%, and memory (RAM) consumption amounting 6 GB respectively, while GPU remains unused, thus showing the possibility of deploying such systems on standard hardware configurations. These results reflect the possibility of transforming the impact of the transformer technology in sophisticated techniques of both detection and diagnosis of WSNs as an affirmation of future improvement and inventions of another kind of approach. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

First-principles study of optical band gap modulation in CaTiO3-doped KNN lead-free ceramics

引用

Ceramics International 2025年第15期51卷 20863-20869页

作者： He, Jian Wang, Junjun Jiao, Yufang Wang, Bingsen Mu, Yan Liu, Meng Sun, Che Liu, Danqing Yang, Wenlong Wu, Fengmin School of Science Harbin University of Science and Technology Harbin150080 China School of Material Science and Chemical Engineering Harbin University of Science and Technology Harbin150080 China School of Measurement and Communication Engineering Harbin University of Science and Technology Harbin150080 China

In this study, the effects of CaTiO3 (CT) doped (K0.5Na0.5)NbO3 (KNN) (KNN-xCT. x = 0, 1/24, 1/12, and 1/8) on the structure, optical and ferroelectric properties were investigated through first-principles calculations and experimental analysis. The calculation results demonstrate that CT doping decreases the band gap of KNN-based materials, and the experimental results of optical band gap show excellent agreement with the theoretical calculations. The theoretically calculated band gap value is lower than the experimental value, which can be attributed to the inherent underestimation associated with the generalized gradient approximation (GGA). The reason of this is the formation of "traps" around the d orbitals of Ca atoms can significantly enhance the electrical performance of KNN-CT ceramics. The XRD results demonstrated the successful incorporation of CT into the KNN structure. The ferroelectric loop of KNN-1/24CT ceramics indicates that domains exhibit a more rapid response to the electric field than the undoped KNN ceramics near the coercive field due to narrowing of the band gap. Under the synergistic effect of Ca and Ti atoms, KNN-CT ceramics exhibit a denser band structure and a narrower band gap. This study provides theoretical insights and experimental analysis into improving the band structure, optical and electric properties of KNN ceramics. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Ferroelectricity

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture Farming Robot based on Bluetooth 5

Smart Agriculture Farming Robot based on Bluetooth

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Sarman, K.V.S.H. Gayatri Kumar, D. Vijendra Priyanka, Samsani N. V. D. Lakshmi Neelima, M. Raju, K. Satyanarayana Tirumani, Nalini Prasad Vishnu Institute of Technology Department of Electronics and Communication Engineering Bhimavaram India Godavari Institute of Engineering & Technology Department of Ece Rajahmundryr India B V C Engineering College Department of Electronics and Communication Engineering Odalarevu India Sri Vasavi Engineering College Department of Electronics and Communication Engineering Tadepalligudem India B V Raju College Department of Physics and Electronics Vishnupur Bhimavaram534202 India Srkr Engineering College Department of Electronics and Communication Engineering Bhimavaram India

ISBN: (纸本)9798350389609

Smart agriculture is rapidly gaining popularity as a means of improving farming operations and increasing productivity. In this aspect, the use of robot technology opens up promising potential for precision farming and automation. This study presents a design which can able to perform multiple tasks in the agriculture fields through Bluetooth. The robot can be controlled remotely via a Bluetooth-enabled interface or autonomously to perform various tasks such as crop inspection, irrigation control, and soil monitoring. The robot and user devices may readily connect thanks to Bluetooth technology, which enables real-time data sharing and control. The hardware and software components of the system architecture are thoroughly detailed, and practical results demonstrate how well they perform to improve agricultural operations such as plowing, water pumping, seed planting, and robot forward and backward movements. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An Efficient Attention Deficit Hyperactivity Disorder (ADHD) Diagnostic Technique Based on Multi-Regional Brain Magnetic Resonance Imaging

引用

Journal of Computing Science and engineering 2023年第3期17卷 135-143页

作者： Sachnev, Vasily Mahanand, B.S. School of Information Communication and Electronics Engineering Catholic University of Korea Bucheon Korea Republic of Department of Information Science and Engineering Sri Jayachamarajendra College of Engineering JSS Science and Technology University Mysuru India

In this paper, an efficient technique for the diagnosis of attention deficit hyperactivity disorder (ADHD) was proposed. The proposed method used features/voxels extracted from structural magnetic resonance imaging (MRI) scans of seven brain regions and efficiently classified three subtypes of ADHD: ADHD-C, ADHD-H, and ADHD-I, as well as the typically developing control (TDC). Training and testing data for experiments were obtained from ADHD-200 database, and 41,721 features/voxels were extracted from sMRI by using region-of-interest (ROI). The proposed ADHD diagnostic technique built an efficient ADHD classifier in two steps. In the first step, a proposed regional voxels selection method (rVSM) selected an optimal set of features/voxels from seven brain regions available in ADHD-200, i.e., the Amygdala, Caudate, Cerebellar Vermis, Corpus Callosum, Hippocampus, Striatum, and Thalamus. In the second step, voxels/features selected by rVSM were used together to form a unified set of voxels. The unified set of voxels was used by a multiregion voxels selection method to train an efficient classifier using the extreme learning machine (ELM). Finally, the proposed method selected a unique set of voxels from the seven brain regions and built a final ELM classifier with maximum accuracy. Experiments clearly indicated that the proposed method produced better results than existing methods. © 2023. The Korean Institute of Information Scientists and Engineers

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Recaptured Image Forensics Using Transfer Learning 7

Recaptured Image Forensics Using Transfer Learning

引用

2023 7th International Conference On Computing, communication, Control And Automation, ICCUBEA 2023

作者： Singh, Medha Singh Singha, Nitin Muniraj, Manigandan National Institute of Technology Electronics and Communication Engineering Delhi Delhi India School of Electronics Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350304268

Recaptured Image detection is a field of security forensics that deals with detecting the originally captured image from its reimaged counterpart. The different algorithms that have been proposed to differentiate the original and recaptured images work with great accuracy on a large dataset and high-definition images. But the challenge remains for small-scale and small- size images as the existing algorithms required customized hand engineering whilst dealing with different datasets. Our proposed system is a dual learning model, which takes into account the enormous research for computer vision and applies concept of transfer learning for recaptured images detection. The ensemble of 6 pre-trained networks, namely AlexNet, Res Net, InceptionNet, GoogleNet, SqueezeNet, and MobileNet, has been compared on same dataset. It will allow institutional level detection of image spoofing and the recaptured image forgery for small-scale images with considerable accuracy without requiring specialized preprocessing on their end. We have achieved the highest accuracy of 90 percent through our model containing Transfer Learned MobileNet and SVM classifier. As per the latest resources, this is the first instance of applying transfer learning for recaptured image detection. © 2023 IEEE.

关键词： Pre-trained networks Recaptured image forensics SVM Classifier Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of area and energy efficiency in Fruit-v2, Fruit-80 and Grain128AEAD for resource-constrained devices

引用

International Journal of High Performance Systems Architecture 2023年第4期11卷 179-190页

作者： Sharma, Dheeraj Kumar Department of Electronics and Communication Engineering National Institute of Technology Kurkshetra Haryana Kurukshetra136119 India

There is a lot of increase in technology. As there are restrictions on the resources available, there is a need to implement lightweight stream ciphers. The ciphers are used for the encryption of data. So, the security of data is also an important factor. As handheld devices are increasing, the need for energy-efficient devices becomes more vital. Keeping all these requirements in mind, researchers have done much research on ciphers. The unrolling of stream ciphers showed the energy-efficient way to implement ciphers. In this paper, the unrolling of Fruit-v2, Fruit-80 and Grain128AEAD stream ciphers is discussed. Using Xilinx ISE Design Suite and Verilog HDL, simulation is performed for different unrolling factors. Using the Synopsys DC compiler, power and energy are calculated. The unrolling rounds for which the energy is optimised for Fruit-v2, Fruit-80 and Grain128AEAD are 16, 16, and 64, respectively. This paper discusses area, power and energy consumption. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Techniques for Improved Localization of Brain Lesions in Neuroimaging 2

Image Fusion Techniques for Improved Localization of Brain L...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Beenarani, B.B. Nirmala, P. Kumaresan, S. Joshua Senthilkumar, C. Kongkham, Dinokumar Computer Science and Engineering Saveetha School of Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350384277

This research explores the application of advanced image fusion techniques to enhance the precision and accuracy of brain lesion localization in neuroimaging studies. Neuroimaging plays a crucial role in diagnosing and understanding various neurological disorders, and precise localization of brain lesions is imperative for effective treatment planning. Traditional imaging modalities may provide limited information, and their fusion with complementary modalities, such as functional or molecular imaging, holds promise for improved localization. The study investigates and compares different image fusion methods, aiming to optimize the integration of diverse imaging data to achieve a more comprehensive and accurate representation of brain lesions. The outcomes of this research have the potential to significantly enhance diagnostic capabilities, ultimately contributing to better-informed clinical decisions and improved patient outcomes in the field of neurology. © 2024 IEEE.

关键词： Molecular imaging

来源：评论

学校读者我要写书评

暂无评论

DAMNet: lightweight dual attention mixed network for efficient image deraining

引用

Neural Computing and Applications 2025年第17期37卷 10557-10575页

作者： Thatikonda, Ragini Cheruku, Ramalingaswamy Kodali, Prakash Department of Electronics and Communication Engineering National Institute of Technology Warangal Telangana Hanamkonda Warangal506004 India Department of Computers Science and Engineering National Institute of Technology Warangal Telangana Hanamkonda Warangal506004 India

A long-standing problem in computer vision (CV) is image deraining. Current deraining networks frequently fail to achieve a good balance between low system complexity and great image quality, particularly when considering spatial features and contextual feature map information. We propose the Dual Attention Mixed Network (DAMNet) as a solution, which achieves a balance between these conflicting objectives. Encoder-Decoder, Dual Attention Network (DANet), and Channel Attention Sub-Module Network (CASMNet) are the three sub-networks which jointly make up DAMNet. It has two hierarchical levels. The Encoder-Decoder and DANet operate at the first level, while CASMNet operates at the second hierarchical level. An enhanced U-Net serves as the base for the Encoder-Decoder architecture, which effectively learns contextual feature map information. The main objective of CASMNet is to preserve local information. In order to reduce network complexity, a window multi-head self-attention network is used in place of the Middle Block (MB) and multiplication is applied in place of the nonlinear activation function in the U-Net encoder-decoder. DAMNet can gradually retrieve contextual information and spatial details from degraded images through this approach. Our network performs better than many current networks on the Rain100H dataset, reaching at least 0.55 dB greater PSNR, although only using 16.3 million parameters. In comparison with state-of-the-art (SOTA) networks, extensive testing on synthetic, real-world, and raindrop datasets show that DAMNet yields promising results. Moreover, the implementation of DAMNet on a low-end edge device such as the Jetson Nano demonstrates its effectiveness in practical world environment. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Customized Graph-Cut Segmentation with Superpixels for Snowfall Detection on Solar Panels 4

Customized Graph-Cut Segmentation with Superpixels for Snowf...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Pavithra, V. Danisha, B.R. Divyadharshini, V. Koresh, H. James Deva Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331523923

Snow accumulation on solar panels reduces their performance in energy generation regions. Hence certain image processing methods were developed for segmenting snow from the normal areas of solar panels. Graph Cut and Flood Fill are the popular semi-automatic method used for this application where it relies on detecting an efficient region for marking the segmentation process. Similarly, the manual intervention fails to provide consistent results in such methods. Therefore, a customized graph cut methodology is proposed in this work by combining super pixel-based feature extraction and k-means clustering. At first, the input images are preprocessed by dividing the pixels to form super pixels as a group to reduce the computational complexity without losing the meaningful information. Features like intensity, edge density, texture, and color are extracted from these super pixel groups for segmenting the snow-covered regions on a solar panel. Further, the extracted features are normalized by a k-means clustering algorithm for identifying the highest intensity regions to observe the snow-covered regions. A graph cut-based segmentation technique is applied at the end to ensure the precise boundary delineation. The work is also incorporated with several post-processing techniques for improving the segmentation mask quality. This proposed method is evaluated against Graph cut and flood fill and satisfied with an average dice similarity coefficient of 93.09% and 95.11%. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Model for Real Time Hand Gestures Recognition

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 1105-1119页

作者： S.Gnanapriya K.Rahimunnisa Department of Information Technology Easwari Engineering CollegeChennai600089India Department of Electronics and Communication Engineering Easwari Engineering CollegeChennai600089India

The performance of Hand Gesture Recognition(HGR)depends on the hand *** helps in the recognition of hand gestures for more accuracy and improves the overall performance compared to other existing deep neural *** crucial segmentation task is extremely complicated because of the background complexity,variation in illumination *** proposed mod-iﬁed UNET and ensemble model of Convolutional Neural Networks(CNN)undergoes a two stage process and results in proper hand gesture ***ﬁrst stage is segmenting the regions of the hand and the second stage is ges-ture identiﬁ*** modiﬁed UNET segmentation model is trained using resized images to generate a cost effective semantic segmentation *** Central Processing Unit(CPU)utilization and training time taken by these models with respect to three public benchmark datasets are also *** is carried out with the ensemble learning model consisting of EfﬁcientNet B0,Efﬁ-cientNet B4 and ResNet *** on NUS hand posture dataset-II,OUHANDS and HGRI benchmark datasets show that our architecture achieves a maximum recognition rate of 99.07%through semantic segmentation and the Ensemble learning model.

关键词： Convolutional neural networks EfﬁcientNet ensemble learning ResNet semantic segmentation UNet

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：