检索结果-内蒙古大学图书馆

Innovative Video Classification Method based on Deep Learning Approach

Recent Patents on engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach for Alzheimer’s disease diagnosis: image segmentation and deep learning classification

引用

Neural Computing and Applications 2025年 1-19页

作者： Bhimavarapu, Usharani Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Alzheimer’s disease is a severe neurodegenerative disease that leads to cognitive decline and memory loss, and hence, the early diagnosis is essential for proper management and care. This study investigates the usage of the improved fuzzy C-means (FCM) algorithm for segmentation of MRI scan and five deep learning models, namely Densenet121, Inception-v3, VGG-19, Xception, and Resnet-50, for image classification. Enhanced fuzzy C-means algorithm helps segment MRI data, while the selected deep learning architectures classify these images for accurate classification. Rigorous processes, including five-fold cross-validation, early stopping, and optimization techniques, were employed to ensure model performance. The results indicated that combining the enhanced fuzzy C-means algorithm with deep learning architectures significantly improved MRI classification accuracy, where Densenet121 and Resnet-50 exhibited the best results. This approach holds promise for enhancing the diagnosis and treatment of Alzheimer’s disease because it increases detection accuracy and reliability, allowing for better patient care. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Secure speaker identification in open and closed environments modeled with symmetric comb filters

引用

Multimedia Tools and Applications 2025年第18期84卷 19147-19189页

作者： Shafik, Amira Monir, Mohamad El-Shafai, Walid Khalaf, Ashraf A. M. Nassar, M.M. El-Fishawy, Adel S. El-Din, M. A. Zein Dessouky, Moawad I. El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Minia University Minia61519 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Speech is a fundamental means of human interaction. Speaker Identification (SI) plays a crucial role in various applications, such as authentication systems, forensic investigation, and personal voice assistance. However, achieving robust and secure SI in both open and closed environments remains challenging. To address this issue, researchers have explored new techniques that enable computers to better understand and interact with humans. Smart systems leverage Artificial Neural Networks (ANNs) to mimic the human brain in identifying speakers. However, speech signals often suffer from interference, leading to signal degradation. The performance of a Speaker Identification System (SIS) is influenced by various environmental factors, such as noise and reverberation in open and closed environments, respectively. This research paper is concerned with the investigation of SI using Mel-Frequency Cepstral Coefficients (MFCCs) and polynomial coefficients, with an ANN serving as the classifier. To tackle the challenges posed by environmental interference, we propose a novel approach that depends on symmetric comb filters for modeling. In closed environments, we study the effect of reverberation on speech signals, as it occurs due to multiple reflections. To address this issue, we model the reverberation effect with comb filters. We explore different domains, including time, Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Discrete Sine Transform (DST) domains for feature extraction to determine the best combination for SI in case of reverberation environments. Simulation results reveal that DWT outperforms other transforms, leading to a recognition rate of 93.75% at a Signal-to-Noise Ratio (SNR) of 15 dB. Additionally, we investigate the concept of cancelable SI to ensure user privacy, while maintaining high recognition rates. Our simulation results show a recognition rate of 97.5% at 0 dB using features extracted from speech signals and their DCTs. Fo

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

An efficient approach for denoising EOG artifact through optimal wavelet selection

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 279-292页

作者： Prakash, Vinod Kumar, Dharmender Department of Computer Science and Engineering Guru Jambheshwar University of Science and Technology Haryana Hisar 125001 India

Electroencephalography (EEG) is a non-intrusive method used to capture electrical potential generated by brain neurons, which is crucial for diagnosing neurological disorders like epilepsy, sleep disorders, brain tumours, and dementia. However, EEG signals can sometimes be contaminated with undesired signals, known as artifacts. These artifacts are generated by retinal dipole movement and eyelid motion, resulting in spikes with significant amplitudes and distortions in EEG recordings. Researchers have explored wavelet-based techniques to remove EOG artifacts from EEG signals, with Haar, Symlet, and Daubechies being common wavelets. However, selecting the most suitable wavelet remains a challenge. The proposed study found that db7 is the optimal wavelet for removing EOG artifacts, with the lowest RMSE value of 54.97 and a calculation time of 0.5798 s. The proposed wavelet-independent component analysis approach outperforms the existing independent component analysis, specifically Fast-ICA, with a promising computation time (Δ C_t) of 6.27 s. The proposed approach aims to enhance the quality of EOG signals by effectively reducing noise through the selection of an appropriate mother wavelet function. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Discrete wavelet transform EOG artifact Independent component analysis Optimal mother wavelet Wavelet family

来源：评论

学校读者我要写书评

暂无评论

Offshore Software Maintenance Outsourcing Process Model Validation:A Case Study Approach

引用

computers, Materials & Continua 2023年第3期74卷 5035-5048页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Adel Sulaiman Muhammad Akram Ahmad Salman Khan Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala TerengganuMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan

The successful execution and management of Offshore Software Maintenance Outsourcing(OSMO)can be very beneficial for OSMO vendors and the OSMO *** a lot of research on software outsourcing is going on,most of the existing literature on offshore outsourcing deals with the outsourcing of software development *** frameworks have been developed focusing on guiding software systemmanagers concerning offshore software ***,none of these studies delivered comprehensive guidelines for managing the whole process of *** is a considerable lack of research working on managing OSMO from a vendor’s ***,to find the best practices for managing an OSMO process,it is necessary to further investigate such complex and multifaceted phenomena from the vendor’s *** study validated the preliminary OSMO process model via a case study research *** results showed that the OSMO process model is applicable in an industrial setting with few *** industrial data collected during the case study enabled this paper to extend the preliminary OSMO process *** refined version of the OSMO processmodel has four major phases including(i)Project Assessment,(ii)SLA(iii)Execution,and(iv)Risk.

关键词： Offshore outsourcing process model model validation vendor challenges case study

来源：评论

学校读者我要写书评

暂无评论

Intelligent predictions of Covid disease based on lung CT images using machine learning strategy

引用

Materials Today: Proceedings 2023年 80卷 3744-3750页

作者： Prabha, B. Kaur, Sandeep Singh, Jaspreet Nandankar, Praful Kumar Jain, Sanjiv Pallathadka, Harikumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram Guntur India Department of Computer Engineering and Technology Guru Nanak Dev University Amritsar India Department of Computer Science and Engineering Adesh Institute of Technology Chandigarh Campus India Department of Electrical Engineering Government College of Engineering Nagpur India Medi-Caps University India Manipur International University Manipur India

Covid or Corona Virus, a term ruling the world from past two years and causes a huge destruction in all countries. One of the most important Covid disease identification method is Lung based Computed Tomography (CT) image scanning, in which it provides an effective disease identification means in clear manner. However, this Lung CT image based disease detection principles are complex to health care representatives and doctors to predict the Covid disease accurately. Several manual errors and medical flaws are raised day-by-day, so that a new systematic methodology is required to identify the Covid disease effectively with respect to machine learning principles. The machine learning principles are most popular to identify the respective disease efficiently as well as classify the disease in accurate manner without any time consumption. The infected portions of the chest are identified accurately and report to the respective person without any delay. In this paper, a new machine learning strategy is introduced called Hybrid Disease Detection Principle (HDDP), in which it is derived from the two classical machine learning algorithms called Convolutional Neural Network (CNN) and the AdaBoost Classifier. Both these algorithms are integrated together to produce a new strategy called HDDP, in which it process the lung CT image based on the machine learning factors such as pre-processing, feature extraction and classification. Based on these effective image processing strategies the proposed algorithm handles the CT images to predict the Covid disease and report to the respective user with proper accuracy ratio. This paper intends to provide effcient disease predictions as well as provide a sufficient support to medical people and patients in fine manner to assist them with modern classification algorithms. © 2021

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Two-view attention-guided convolutional neural network for mammographic image classification

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 453-467页

作者： Lilei Sun Jie Wen Junqian Wang Yong Zhao Bob Zhang Jian Wu Yong Xu College of Computer Science and Technology Guizhou UniversityGuiyangChina Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Harbin Institute of Technology ShenzhenChina School of Electronic and Computer Engineering Shenzhen Graduate School of Peking UniversityShenzhenChina Department of Computer and Information Science University of MacaoTaipaChina Science for Life Laboratory KTH Royal Institute of TechnologyStockholmSweden

Deep learning has been widely used in the field of mammographic image classification owing to its superiority in automatic feature ***,general deep learning models cannot achieve very satisfactory classification results on mammographic images because these models are not specifically designed for mammographic images and do not take the specific traits of these images into *** exploit the essential discriminant information of mammographic images,we propose a novel classification method based on a convolutional neural ***,the proposed method designs two branches to extract the discriminative features from mammographic images from the mediolateral oblique and craniocaudal(CC)mammographic *** features extracted from the two-view mammographic images contain complementary information that enables breast cancer to be more easily ***,the attention block is introduced to capture the channel-wise information by adjusting the weight of each feature map,which is beneficial to emphasising the important features of mammographic ***,we add a penalty term based on the fuzzy cluster algorithm to the cross-entropy function,which improves the generalisation ability of the classification model by maximising the interclass distance and minimising the intraclass distance of the *** experimental results on The Digital database for Screening Mammography INbreast and MIAS mammography databases illustrate that the proposed method achieves the best classification performance and is more robust than the compared state-ofthe-art classification methods.

关键词： convolutional neural network deep learning medical image processing mammographic image

来源：评论

学校读者我要写书评

暂无评论

Dynamic Quantum Federated Learning for UAV-Based Autonomous Surveillance

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8158-8170页

作者： Park, Soohyun Son, Seok Bin Jung, Soyi Kim, Joongheon Sookmyung Women's University Division of Computer Science Seoul04310 Korea Republic of Korea University School of Electrical Engineering Seoul02841 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

In recent years, unmanned aerial vehicles (UAVs) have proven their effectiveness in surveillance due to their superior mobility. By utilizing multiple UAVs with collaborated learning, surveillance of a huge area while consuming minimum resources is possible. However, the performance of UAV collaborative learning systems is still severely limited because the number of parameters in a classical NN is generally very large, which is unsuitable for unstable wireless communication. To address this issue, this paper uses a quantum neural network (QNN), which has large computational capabilities and uses fewer parameters to overcome the problems caused by many parameters. However, it is still difficult to send all the parameters of the QNN to the server under poor channel conditions. Therefore, this paper proposes dynamic quantum federated learning (DQFL), a novel framework designed for UAVs employing quantum computing (QC) and federated learning (FL). The proposed DQFL uses a dynamic quantum neural network (DQNN) with a multi-depth circuit and employs dynamic control of the circuit layer to improve the efficiency of local parameter transmission between UAVs in unstable wireless communication environments. Extensive simulations conducted under real-world autonomous surveillance conditions demonstrate the robustness of DQFL to non-iidness, varying signal-to-noise ratios (SNRs), and poor communication channel conditions in the UAV environment. © 1967-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Performance Based Scheduling in Distributed Mixed Criticality Systems

引用

IEEE Access 2025年 13卷 95321-95340页

作者： Ali, Amjad Wasly, Saud Khattak, Asad Masood Ali, Ihsan Iqbal, Shahid Hayat, Bashir University of Swat Department of Computer and Software Technology Khyber Pakhtunkhwa Swat Pakistan King Abdul Aziz University Electrical and Computer Engineering Department Jaddah Saudi Arabia Zayed University College of Technological Innovation United Arab Emirates Institute of Management Sciences School of Computer Science and IT Peshawar Pakistan

With a focus on computationally intensive, distributed, and parallel workloads, scheduling in mixed-criticality distributed systems presents significant challenges due to shared memory and resources, as well as the diverse demands of tasks. The system’s efficiency is heavily dependent on the overall scheduling duration (make span), while individual task deadlines impose strict timing constraints. When the tasks need to simultaneously access the shared memory, then these tasks interfere the execution of one another. For managing the scheduling of interfering tasks in distributed mixed-criticality systems, a novel Interference-Aware Partitioning Fixed Priority (IAP-FP) approach is proposed, which effectively handles task partitioning among cores while considering interference, ensuring better performance and adherence to critical deadlines. This method reduces task waiting times, which minimizes the scheduling duration and improving the schedulability of the task set. The novel proposed approach is compared with Mixed-Criticality Multicore Compositional Earliest Deadline First (MMC-EDF), Global and Mixed Criticality Partitioning (MC-Partitioning) approaches to show the efficiency. The proposed approach schedules 75% tasks while the MMC-EDF, Global and MC-Partitioning approaches schedules 65%, 0% and 18% tasks respectively for target utilization U=0.8. As the utilization of mixed criticality (MC) workload increases, the schedulability of MC task sets decreases, but still the proposed approach performs better than the MMC-EDF, Global and MC-partitioning approaches. © 2013 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

A systematic review on recent methods on deep learning for automatic detection of Alzheimer's disease

引用

Medicine in Novel Technology and Devices 2025年第1期25卷 1-12页

作者： Radhakrishna Chamakuri Hyma Janapana Department of Computer Science Engineering GITAM School of TechnologyVisakhapatnamAndhra Pradesh530045India

Alzheimer's disease(AD)is the most frequent cause of dementia,however,and it is caused by a number of different *** regard to the elderly population all over the world,Alzheimer's disease is the seventh largest cause of mortality,disability,and ***,social isolation,inactivity,alcohol,smoking,obesity,diabetes,high blood pressure,and age are all variables that can increase the likelihood of getting *** risk factors include social isolation,depression,and smoking.A diagnosis of Alzheimer's disease at an earlier stage may improve the odds of receiving care and *** professionals often diagnose AD based on a limited number of *** the other hand,it is now possible to identify and categorize Alzheimer's disease(AD)because of technological advancements such as artificial intelligence(AI).However,to identify the current AI-enabled approaches,we must conduct an investigation into the state of the *** breakthrough in diagnosis methodologies will enable the development of the Clinical Decision Support System(CDSS),capable of automatically diagnosing Alzheimer's disease(AD)without human *** this publication,we conduct a systematic review of sixty research articles previously reviewed by other *** systematic review sheds light on the synthesis of new knowledge and *** study discusses the current approaches for machine learning,deep learning methods,ensemble models,transfer learning,and methods used for early Alzheimer's disease *** paper provides answers to a large number of research issues and synthesizes fresh information that is helpful to the reader on many elements of AI-enabled approaches for Alzheimer's disease *** addition,it has the potential to stimulate additional research into more effective methods of computer-based intelligent identification of Alzheimer's disease.

关键词： Alzheimer disease diagnosis Artificial intelligence Deep learning Ensemble learning Machine learning

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：