检索结果-内蒙古大学图书馆

Classifying Multi-Lingual Reviews Sentiment Analysis in Arabic and English Languages Using the Stochastic Gradient Descent Model

引用

computers, Materials & Continua 2025年第4期83卷 1275-1290页

作者： Yasser Alharbi Sarwar Shah Khan College of Computer Science and Engineering University of HailHail55436Saudi Arabia Department of Computer Science University of Engineering&TechnologyMardan23200Pakistan

Sentiment analysis plays an important role in distilling and clarifying content from movie reviews,aiding the audience in understanding universal views towards the ***,the abundance of reviews and the risk of encountering spoilers pose challenges for efcient sentiment analysis,particularly in Arabic *** study proposed a Stochastic Gradient Descent(SGD)machine learning(ML)model tailored for sentiment analysis in Arabic and English movie *** allows for fexible model complexity adjustments,which can adapt well to the Involvement of Arabic language *** adaptability ensures that the model can capture the nuances and specifc local patterns of Arabic text,leading to better *** distinct language datasets were utilized,and extensive pre-processing steps were employed to optimize the datasets for *** proposed SGD model,designed to accommodate the nuances of each language,aims to surpass existing models in terms of accuracy and *** SGD model achieves an accuracy of 84.89 on the Arabic dataset and 87.44 on the English dataset,making it the top-performing model in terms of accuracy on both *** indicates that the SGD model consistently demonstrates high accuracy levels across Arabic and English *** study helps deepen the understanding of sentiments across various linguistic *** many studies that focus solely on movie reviews,the Arabic dataset utilized here includes hotel reviews,ofering a broader perspective.

关键词： Sentiment analysis stochastic gradient descent reviews English IMDb dataset Arabic dataset

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Multi-Featured Movie Recommendation Using Knowledge Graph

Multi-Featured Movie Recommendation Using Knowledge Graph

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Nair, Lekshmi S. Cheriyan, Jo Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India Saintgits College of Engineering Department of Computer Science and Engineering Kerala India

ISBN: (纸本)9781665474511

Recommendation systems are crucial in offering items, particularly in streaming services. Recommendation algorithms are essential for streaming movie services like Netflix in aiding consumers in identifying new movies to watch. Provide a Technologically advanced strategy on autoencoders for constructing a movie filter system that anticipates users' ratings for movies through vast end-users rating data. Examine the application of deep learning to predict customers' assessments of new movies using the Movie-Lens dataset, providing movie recommendations. The movie recommendation system proposed here uses particle filtering embedded in a knowledge graph. The model enables the user to provide the best suitable recommendation of movies considering the user's favorite directors and genre. The experimental findings reveal that compared by error, our recommendation system beats a user-based model on projected ratings and even in the survey where people assess between concepts from both systems. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Texture and Deep Feature Extraction in Brain Tumor Segmentation Using Hybrid Ensemble Classifier 1st

Texture and Deep Feature Extraction in Brain Tumor Segmentat...

引用

1st International Conference on Computational Intelligence for engineering and Management Applications, CIEMA 2022

作者： Mohan, Divya Ulagamuthalvi, V. Joseph, Nisha Department of Computer Science and Engineering Sathyabama University Chennai India Computer Science and Engineering SAINTGITS College of Engineering Kerala Kottayam India

ISBN: (纸本)9789811984921

The abnormal cell development in the brain is referred to as a tumor. Brain tumors are treated by physicians using radiation and surgery. The brain tumor is categorized as benign or malignant. The benign tumor can be treated and cured using the appropriate medication suggested. A malignant tumor is an abnormal tissue that affects the nearby tissues, and it can be cured only through proper surgery by a physician. Manual identification process of malignant and benign tumors is very time taking and has a good chance of occurrence error in the process. To overcome this limitation, automatic brain tumor classification technique is proposed. An efficient methodology for the detection of brain tumors is done. Initially, the brain MRI image is smoothed and enhanced by a Gaussian filter. Then, deep and texture features are extracted. In the proposed work, an ensemble technique using three different classifiers based on majority voting method is used. The research work proposed in this paper is tested using BRATS 2017, 2018 datasets, and the obtained results are compared with recent methods and proved its efficacy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Improving fish image detection speed with hybrid VGG16 and darknet

引用

Multimedia Tools and Applications 2025年第12期84卷 10551-10566页

作者： Sirigineedi, Manikanta Jagan Mohan, R.N.V. Sahu, Bandita Department of Computer Science and Engineering GIET University Odisha Gunupur765022 India Department of Computer Science and Engineering SRKR Engineering College Andhra Pradesh Bhimavaram534201 India

Fish classification and object detection are crucial tasks in the fishery industry. The use of computer vision and deep learning techniques can help automate these tasks and improve the efficiency of the fishery industry. In this paper, we propose a hybrid model of VGG16 and Darknet for fish classification and object detection. The VGG16 model is a popular deep learning model for image classification, and the Darknet model is a state-of-the-art object detection model. The hybrid model combines the strengths of both models to achieve better performance in fish classification and object detection. The proposed model is trained on a dataset of fish images, which is collected from various sources. The dataset includes images of different fish species, sizes, and orientations. The model is trained to classify fish species and detect fish objects in the images. The results of the experiments show that the proposed model outperforms the individual VGG16 and Darknet models in terms of accuracy and speed. The model achieves the training time for 500 sessions with all 951 images was only 1 h 12 min, which is very fast. Additionally, the size of the model weight file is 13 MB, which is relatively small. This suggests that the model is lightweight and efficient, which is desirable in many applications. In conclusion, the proposed hybrid model of VGG16 and Darknet is an effective solution for fish classification and object detection. The model can be applied in real-world fishery scenarios to improve the efficiency and accuracy of fishery tasks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

M-Bi-GRU-CNN: a hybrid deep learning model with optimized feature selection for enhanced crop yield prediction

引用

Multimedia Tools and Applications 2025年 1-25页

作者： J, Madhuri M, Indiramma N, Nagarathna Department of Computer Science and Engineering Bangalore Institute of Technology Karnataka Bengaluru560004 India Department of Computer Science and Engineering BMS College of Engineering Karnataka Bengaluru560019 India

Weather variability significantly impacts crop yield, posing challenges for large-scale agricultural operations. This study introduces a deep learning-based approach to enhance crop yield prediction accuracy. A Multi-Head Attention-based Bi-Directional Gated Recurrent Unit (M-Bi-GRU) integrated with a Convolutional Neural Network (CNN) is proposed. The publicly available Crop Recommendation dataset is pre-processed using data cleaning and Min–Max normalization to eliminate inconsistencies. Then, the Adaptive Reptile Search Optimization (ARSO) algorithm is used to identify the most relevant features for the prediction task. The M-Bi-GRU-CNN model uses these selected features to predict crop yields. The implementation is carried out in Python, and the performance is measured using a variety of metrics. Experimental results demonstrate that the proposed model outperforms existing methods, achieving a Mean Absolute Error (MAE) of 0.45, Mean Absolute Percentage Error (MAPE) of 0.07, and Root Mean Square Error (RMSE) of 0.28. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Drug–target interactions prediction based on similarity graph features extraction and deep learning

引用

Neural Computing and Applications 2025年第6期37卷 4303-4322页

作者： Torkey, Hanaa El-Behery, Heba Attia, Abdel-Fattah El-Fishawy, Nawal Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Computer Science and Engineering Faculty of Engineering Kafrelsheikh University Kafrelsheikh Egypt Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia

Identifying drug–target interactions (DTIs) is a critical step in both drug repositioning. The labor-intensive, time-consuming, and costly nature of classic DTI laboratory studies makes it imperative to create efficient computer algorithms to forecast possible DTIs. However, current computational approaches that predict potential drug–target interactions (DTIs) suffer from some limitations, like finding the best similarity measures or negative samples, and thus require substantial performance improvement. This study proposes an integrated approach based on feature representation and deep learning to predict DTIs. We extract the relevant features of drugs and proteins from heterogeneous networks using graph mining techniques. The proposed approach constructs a heterogeneous graph from the known drug–protein interactions, protein–protein, and drug–drug similarities. Then applying two feature extraction techniques to extract the features, then utilizing these features in training a deep learning model to predict the potential DTIs. Also, a novel algorithm is proposed to find the negative samples based on the drug and protein similarity matrices. Four Benchmark datasets are used to evaluate the proposed approach. Our approach achieves the highest AUC (area under the ROC curve) across all datasets (0.98) with around 2% increases over the existing methods. Experimental results demonstrate that our proposed approach outperforms the baseline methods in predicting DTI, and our negative sample-identifying algorithm could be established as a competitive solution. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Text-driven clothed human image synthesis with 3D human model estimation for assistance in shopping

引用

Multimedia Tools and Applications 2025年第1期84卷 167-200页

作者： Karkuzhali, S. Aasim, A. Syed StalinRaj, A. Department of Computer Science and Engineering Mepco Schlenk Engineering College Tamil Nadu Sivakasi India

Online shopping has become an integral part of modern consumer culture. Yet, it is plagued by challenges in visualizing clothing items based on textual descriptions and estimating their fit on individual body types. In this work, we present an innovative solution to address these challenges through text-driven clothed human image synthesis with 3D human model estimation, leveraging the power of Vector Quantized Variational AutoEncoder (VQ-VAE). Creating diverse and high-quality human images is a crucial yet difficult undertaking in vision and graphics. With the wide variety of clothing designs and textures, existing generative models are often not sufficient for the end user. In this proposed work, we introduce a solution that is provided by various datasets passed through several models so the optimized solution can be provided along with high-quality images with a range of postures. We use two distinct procedures to create full-body 2D human photographs starting from a predetermined human posture. 1) The provided human pose is first converted to a human parsing map with some sentences that describe the shapes of clothing. 2) The model developed is then given further information about the textures of clothing as an input to produce the final human image. The model is split into two different sections the first one being a codebook at a coarse level that deals with overall results and a fine-level codebook that deals with minute detailing. As mentioned previously at fine level concentrates on the minutiae of textures, whereas the codebook at the coarse level covers the depictions of textures in structures. The decoder trained together with hierarchical codebooks converts the anticipated indices at various levels to human images. The created image can be dependent on the fine-grained text input thanks to the utilization of a blend of experts. The quality of clothing textures is refined by the forecast for finer-level indexes. Implementing these strategies can result

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Cyber-attack detection based on a deep chaotic invasive weed kernel optimized machine learning classifier in cloud computing

引用

Soft Computing 2025年第4期29卷 2015-2030页

作者： Indrasena Reddy, M. Siva Kumar, A.P. Subba Reddy, K. Department of Computer Science and Engineering BVRIT Hyderabad College of Engineering for Women Hyderabad500090 India Department of Computer Science and Engineering Jawaharlal Nehru Technological University Ananthapuramu Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Rajeev Gandhi Memorial College of Engineering and Technology Andhra Pradesh Nandyala India

Nowadays, Cloud Computing has attracted a lot of interest from both individual users and organization. However, cloud computing applications face certain security issues, such as data integrity, user privacy, and service availability. The only better solution to such issues is to identify and prevent cyber threats before they can cause seriously harm the cloud computing system. Several methods have been suggested so far to detect the attack in cloud computing (CC), but no one method attains satisfactory results. To overwhelm these drawbacks, a Cyber Security Attack Detection using Deep Kernel Machine Learning optimized with Chaotic Invasive Weed Optimization algorithm is proposed in this paper for Cloud Computing. Here, the data is amassed from CSE-CIC-IDS2018 and Bot-IoT datasets. Subsequently, a pre-processing step involving redundancy reduction and missing value replacement for uncertainty removal is achieved through the Developed Random Forest with Local Least Squares (DRFLLS) method. By utilizing Entropy-Kurtosis based feature selection approach, the pre-processing data is given to the feature selection to identify the optimal features. The selected features are supplied to the Deep Kernel Machine Learning classifier (DK-ML), which is optimized using the Chaotic Invasive Weed Optimization algorithm (Chaotic-IWOA) for classification. This classification process classifies the data as normal or anomalous categories with anomalies encompassing, like DoS, DDoS, Theft attacks, and normal attacks. The proposed technique is activated in MATLAB. The proposed technique achieves 24.88%, 17.98%, 45.65%, 35.95% better accuracy for CSE-CIC-IDS2018 dataset, and 23.93%, 13.94%, 32.94%, and 29.04% better accuracy for Bot-IoT dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Preemptive Min Max Optimal Cost Based Scheduling for Improving the Load Balancing in Virtualized Cloud Environment

引用

SN computer science 2024年第6期5卷 754页

作者： Ravikumar, K. Saravanakumar, K. Viswanathan, Anand Department of Computer Science and Engineering RRASE College of Engineering Department of Computer Science and Engineering Sri Eshwar College of Engineering Department of Information Technology Ponjesly College of Engineering

Load balancing and scheduling are essential components of cloud computing that aim to optimize resource allocation and utilization. In a cloud environment, multiple virtual machines and applications compete for shared resources, and efficient load balancing and scheduling mechanisms are crucial for ensuring optimal performance and resource utilization. The prior methodologies attains higher utilization to allocate task due to makspan problem leads more deadlock occurrence and request failures with higher energy consideration. Furthermore, the paper examines the challenges and considerations in load balancing and scheduling, such as dynamic workload variations, heterogeneity of resources, and QoS requirements. To handle this issues, to propose an Efficient Load Balancing Based Predictive Priority-based Preemptive Min max priority Load balancer (PMin-Max LB) to improve the service optimality in Decentralized cloud server. Initially the user request accessibility and task progress is evaluated through Service level Workload Impact score (SLWIS). Then introducing Workload Scaling Job vector estimation is carried by Particle Swarm Optimization (PSO). By evaluating the Makespan Instance Scaling Changeover Virtualization (MISCV) task weights are assigned to virtual machine by applying Preemptive Min max priority Load balancer (PMin-Max LB) to reduce the workload to improve the performance. The proposed system improves the impact of load balancing and scheduling on cloud performance, scalability, and cost-effectiveness. Finally proposed system attains the potential advancements in load balancing and scheduling techniques improves the computing approach in virtualization process to reduce the workload burned to optimize the heterogeneity and Quality of service. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cloud computing Load balancer Particle swarm optimization Priority scheduling Task allocation Virtual machine

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：