检索结果-内蒙古大学图书馆

VireNet-SSD: object detection model for resource-constrained applications based on self-organized operational neural networks

引用

Neural Computing and Applications 2025年第14期37卷 8547-8569页

作者： Kamath, Vidya Renuka, A. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Discovering deep learning-based computer vision solutions for use with constrained devices is exceptionally hard, and the trade-offs are often too undermining. Deep learning models are enormous, which makes it challenging to deploy them on constrained platforms. The convolutional neural network is the fundamental framework for majority of the models that are currently in use. However, operational neural networks have recently shown to be a better option to the convolutional equivalents on a variety of tasks due to their heterogeneous nature and greater resemblance to the functioning of biological neurons. The question of whether heterogeneous models could function on constrained devices and be deployed in real time remains a major concern. To address this problem, an object detection model architecture based on a single-shot multi-box detector with self-organized operational neural networks as its backbone was developed, which can perform efficiently on constrained devices such as Raspberry Pi. The resultant backbone architecture was named as VireNet. In contrast to homogeneous conventional deep learning networks that use convolutions, heterogeneous networks were chosen to develop VireNet, which provides a more productive and effective solution. Furthermore, an in-depth explanation of the design space has been provided to aid any future research that is associated with this architectural search. This new approach might mark the very beginning of the use of heterogeneity to address issues on devices with constrained resources. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MLMO-HSM: Multi-label Multi-output Hybrid Sequential Model for multi-resident smart home activity recognition

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2313-2325页

作者： Ramanujam, E. Perumal, Thinagaran Department of Computer Science and Engineering National Institute of Technology Silchar Assam 788010 India Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang India

Smart home automation is protective and preventive measures that are taken to monitor elderly people in a non-intrusive manner using simple and pervasive sensors termed Ambient Assistive Living. The smart home produces a large volume of sensor activations to predict an elder’s health status to improve the quality of life and independent living. Machine learning techniques are very familiar and popular in recognizing single resident activities using such a sensor reading. However, multi-resident activities are more complex, and no correlation exists between sensor readings and activities. Recently deep learning and graphical models have been proposed to solve this problem, but it consumes more time to train the model. Moreover, models are primarily executed in parallel, or multi-resident activity recognition has been converted to single for classifying events. This paper proposes a Multi-label Multi-output Hybrid Sequential Model (MLMO-HSM), a feature engineering approach with a hybrid sequential model to recognize the multi-resident activities concurrently in the shortest time. Experimentation has been performed with various machine learning, graphical and deep learning models at the different sizes of the ARAS dataset to validate the efficiency of the proposed model in terms of activity recognition and computation time. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Effective IoT-based crop disease prediction using localise search traversing coupled with deep convolutional neural network classifier

引用

International Journal of Wireless and Mobile Computing 2024年第2期26卷 168-181页

作者： Vani, B.V. Guruprakash, C.D. Information Science and Engineering Sri Siddhartha Institute of Technology Karnataka Tumkur India Department Computer Science and Engineering Sri Siddhartha Institute of Technology Karnataka Tumkur India

Predicting crop disease on the image obtained from the affected crop has been a potential research topic. In this research, the Localise Search Optimisation Algorithm (LSOA) enabled deep Convolutional Neural Network (deep CNN) is used to predict the crop disease for which the dominant statistical and texture features are utilised and LSOA as a training algorithm. The experiments were done on an apple data set and a corn data set, and the results show that the LSOA-deep CNN model attains 98.474% of accuracy, 92.837% of sensitivity and 99.00% of specificity in k-fold training data and 94.683% of accuracy, 95.489% of specificity and 99.00% of specificity with 80% training data for the corn data set. With the apple data set, the developed method achieves 94.587% of accuracy, 99.00% sensitivity and 99.00% specificity under k-fold training, while for the 80% of training, 97.959% accuracy, 96.233% sensitivity and 99.005% specificity are attained. © 2024 Inderscience Enterprises Ltd.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

An Assessment Towards 2D and 3D Human Pose Estimation and its Applications to Activity Recognition: A Review

引用

SN computer Science 2025年第2期6卷 1-24页

作者： Verma, Pratishtha Srivastava, Rajeev Tripathy, Santosh Kumar Department of Computer Engineering National Institute of Technology Haryana Kurukshetra India Computer Science and Engineering IIT BHU Varanasi India Department of Computing Science and Engineering National Institute of Technology Patna Bihar Patna India

Human pose estimation (HPE) from images or video is not only a major issue of computer vision, but also it plays a vital role in many real-world applications. The most challenging problems of human pose estimation are the disparity of poses, disturbing background clutter, different camera views, changes in scene lighting conditions, and occlusion. To solve these issues, a significant amount of research effort has been considered in the past. In this paper, we explore various vision-based activity recognition using 2D and 3D human pose estimations. We explore the conventional system, which includes both statistical and deep learning-based approaches for HPE, and then explore the current progress of each one in comparison to existing ones. At last, we also present various current state-of-the-art human activity recognition (HAR) techniques that use HPE for recognition. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Human activity recognition (HAR) Human body model (HBM) Human pose estimation (HPE)

来源：评论

学校读者我要写书评

暂无评论

Classification of suspected objects and severity assessment of COVID-19 from chest X-ray images using deep transfer learning

引用

Research on Biomedical engineering 2023年第3期39卷 705-718页

作者： Verma, Karan Kumar, Ashok Swaraj, Aman Sagar, Aditi Department of Computer Science and Engineering National Institute of Technology Delhi Delhi India Department of Electronics and Communication Engineering Government Mahila Engineering College Rajasthan Ajmer India Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

Purpose: Coronavirus disease 2019 (COVID-19) has infected about 418 million people across the globe. So, the analysis of biomedical imaging accompanied with artificial intelligence (AI) approaches has transpired a vital role in diagnosing COVID-19. Until now, numerous classification approaches have been demonstrated for the detection of COVID-19. The assessment of COVID-19 patients according to severity level is not so far investigated. For this motivation, the classification of COVID-19 chest X-ray (CXR) images according to severity of the infection is presented in this work. Methods: Primarily, the 1527 CXR images are pre-processed to reshape images into unique size, denoised, and enhanced images through median filter and histogram equalization (HE) techniques, respectively. Afterward, reshaped, denoised, and enhanced CXR images are augmented using synthetic minority oversampling technique (SMOTE) to achieve the balanced dataset of 1752 CXR images. After augmentation, a pre-trained VGG16 and residual network 50 (Resnet50) deep transfer learning models with random forest (RF) and support vector machine (SVM) classifiers are utilized for feature extraction and classification of 1752 CXR images into diverse class labels such as normal, severe COVID-19, and non-severe COVID-19. Results: Our proposed ResNet50 model with SVM classifier provides the highest accuracy of about 95% for severity assessment and classification of COVID-19 CXR images as compared to other permutations. For the ResNet50 model with SVM classifier model, the average value of precision, recall, and F1-score are 91%, 94%, and 92%, respectively. Conclusion: The multi-class classification deep transfer learning models are presented to determine the severity assessment and classification of COVID-19 by using CXR images. Out of these proposed models, the ResNet50 model with SVM classifier will be highly favorable for doctors to classify patients according to their severity assessment and detection of COV

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Autism spectrum disorder based on squeezenet with fractional tasmanian rat swarm optimization

引用

Multimedia Tools and Applications 2024年第41期83卷 89029-89054页

作者： Muppidi, Satish Anuradha, G. Valarmathi, K. Department of Computer Science and Engineering GMR Institute of Technology Andhra Pradesh Rajam India Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada Kanuru India Department of Computer Science and Engineering Panimalar Engineering College Bangalore Trunk Road Chennai Pooñamallee600123 India

A complicated neuro-developmental disorder called Autism Spectrum Disorder (ASD) is abnormal activities related to brain development. ASD generally affects the physical impression of the face as well as the growth of the brain in children. An early and proper medical diagnosis is essential for ASD affected children to enhance their quality of life. However, the clinical detection of ASD is a difficult task and time-consuming, hence it is essential to design an ASD detection approach for precise diagnosis of ASD children. In this research, an algorithmic approach called Fractional Tasmanian Rat Swarm Optimization driven SqueezeNet (FTRSO-SqueezeNet) is designed for the detection of ASD. The median filter and Region of Interest (RoI) extraction are used to de-noise the input image initially and extract a particular region from the filtered image. Later, the nub regions are extracted by choosing the optimal grid from the pre-processed image and using different feature extractors the features from the input images are determined. Finally, the detection of ASD is done by using SqueezeNet, which is trained using the FTRSO approach. The performance of the method is estimated, where the designed model achieved higher performance with an accuracy of 94.55%, sensitivity of 92.53%, and specificity of 95.22% than other prevailing approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Augmented Array based Efficient Fill Ratio Estimation in a Bloom Filter 2

Augmented Array based Efficient Fill Ratio Estimation in a B...

引用

2nd International Conference on Computational Intelligence and Network Systems, CINS 2024

作者： Singh, Amritpal Singh, Amrinderpreet Batra, Shalini Department of Computer Science and Engineering National Institute of Technology Jalandhar Jalandhar India Department of Computer Science and Engineering Thapar Institute of Engineering & Technology Patiala India

ISBN: (纸本)9798331504106

Analysing patterns/trends and associations from heterogeneous data coming at varied speeds and formats require data structures which can handle large and dynamic data efficiently. Bloom Filter (BF), a probabilistic data structure, can be considered as one of the alternatives as it is space efficient and handles membership query effectively. To accommodate the dynamic data sets in the BF when ever the Fill Ratio (FR) exceeds the defined limits, two major approaches have been discussed in the literature: increasing the number of BFs as the data increases and refreshing the existing BF by deleting the staled data. In this paper, a novel approach motivated from Double probing named (DH-FRP) has been proposed to compute FR using augmented array to sample bit locations from parent BF. The augmented array keeps track of the sampled bit values at any given time and stores at contiguous locations for effcient bit counting and FR calculation. Markov Bound has been used to determine whether to recompute the step size or not. Since the rate of dynamic data coming from various sources may be uniform or non uniform, both cases have been considered and FR has been calculated for standard BF and Counting BF. It has been experimentally proved that the proposed scheme outperforms the given state-of-art techniques in terms of FR calculation time and accuracy. ©2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Enhanced text-independent speaker recognition using MFCC, Bi-LSTM, and CNN-based noise removal techniques

引用

International Journal of Speech technology 2024年第4期27卷 1013-1026页

作者： Tiwari, Manish Verma, Deepak Kumar Department of Computer Science and Engineering University Institute of Engineering and Technology Chhatrapati Shahu Ji Maharaj University UP Kanpur India

This research article introduces a novel approach to text-independent speaker recognition by integrating Mel-Frequency Cepstral Coefficients (MFCC) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks, with noise removal facilitated by Convolutional Neural Networks (CNNs). The primary objective is to upgrade the robustness and precision of speaker recognition systems in real-world environments where background noise is prevalent. The proposed method begins with the extraction of MFCC features, which effectively capture the timbral characteristics of the speech signal. To enhance these features, we employ a CNN-based noise removal mechanism that reduces background interference, thereby improving the quality of the input signal. The denoised MFCC features are then fed into a Bi-LSTM network, which excels in modeling temporal dependencies and capturing long-range contextual information inherent in speech data. Extensive experiments were conducted on publicly available datasets, demonstrating significant improvements in speaker recognition accuracy under various noise conditions compared to traditional approaches. The integration of CNN for noise removal and Bi-LSTM for temporal feature modeling showcases a synergistic effect, leading to a more robust and reliable speaker recognition system. Our results underscore the effectiveness of combining advanced feature extraction, noise reduction, and deep learning techniques for enhanced speaker recognition in challenging acoustic environments. The accuracy of the proposed method is found to be 98.17% at the Signal to Noise Ratio (SNR) level of 30 dB. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Insights into research on blockchain for smart contracts: a bibliometric analysis

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Singh, Renu Gupta, Ashlesha Mittal, Poonam Faculty of Informatics and Computing J.C. Bose University of Science and Technology YMCA Faridabad India Department of Computer Science & amp Engineering Indraprastha Institute of Information Technology IIIT New Delhi India

Over the past few years, blockchain technology has gained significant attention. This surge in popularity can be attributed to the emergence of cryptocurrencies and the development of smart contracts. Cryptocurrency is a digital currency that eliminates the problem of double spending. Cryptocurrencies like Bitcoin, Ethereum, Litecoin, Stellar, Zcash, Maker, Aave, etc. become popular and are preferred for money transfers. Smart contracts are the next popular technology on the blockchain after cryptocurrency. It can be considered a piece of code that can execute automatically when the predefined conditions are fulfilled. Researchers believe that the potential of blockchain with smart contracts is only in its initial stages and that its true potential has yet to be fully discovered. Hence, an extensive bibliometric analysis is conducted to understand blockchain trends for smart contracts and to give future directions in this field. For this analysis, various steps are followed, starting with formulating the research question, defining the scope of our research, extracting and analyzing data, answering the research question, and finally, drawing a conclusion. This research paper will be fruitful for scholars and researchers, providing an extensive statistical and network analysis of extracted smart contracts publications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Bibliometric analysis Blockchain Crypto contract Scientometrics Scopus Smart contracts VOSViewer

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cancer Subclassification Using Multi-Omics Clustering and Quantum Cat Swarm Optimization

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer Science and Mathematics 2024年第3期5卷 552-582页

作者： Ali, Ali Mahmoud Mohammed, Mazin Abed Informatics Institute for Postgraduate Studies Iraqi Commission for Computers & Informatics Baghdad Iraq Department of Artificial Intelligence College of Computer Science and Information Technology University of Anbar Anbar31001 Iraq

Integrating multiple omics data can significantly improve the accuracy of cancer subclassification, a challenging task due to the high dimensionality and limited sample sizes. The integration of these data sets can enhance model performance. This study addresses these challenges by employing Quantum Cat Swarm Optimization (QCSO) for feature selection, along with K-means clustering and Support Vector Machine (SVM) for classification. Using QCSO, the most significant features were identified, resulting in an increase in accuracy from 81% to 100%. Performance was evaluated using accuracy, F1-score, precision, recall, ROC, and the silhouette metric, all of which confirmed the effectiveness of the feature selection approach. Additionally, this method enhances the classification of samples while making the models more interpretable, providing better insights into the molecular mechanisms of cancer. This work contributes to advancing knowledge in the field of cancer research and biology in general. © 2024 College of Education, Al-Iraqia University. All rights reserved.

关键词： Support vector machines

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：