检索结果-内蒙古大学图书馆

6th International Hybrid Conference on Informatics and Applied Mathematics, IAM 2023

作者： Abdelhalim, Benoughidene Faiza, Titouna Department of Computer Science LaSTIC Laboratory University of Batna2 Algeria

With the exponential growth and availability of sports video data, the need for video analysis has become crucial. Sports video classification is one of the most challenging problems among computer vision researchers. This paper proposes a novel method for sports video classification based on a deep learning approach using the pre-trained model Inception V3 combined with long short-term memory (LSTM). The pre-trained model Inception V3 extracts the low, middle, and high spatial features. Additionally, we will get the temporal features by feeding LSTM with spatial features. Then, we trained our InceptionV3-LSTM model based on spatial-temporal features by feeding it to the LSTM to classify the video sports into specific categories. The experiments are conducted on the UCF sports dataset. The experiments performed showed that our proposed model has obtained much more encouraging experimental results than the others. © 2023 Copyright for this paper by its authors.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

PFed-NS: An Adaptive Personalized Federated Learning Scheme Through Neural Network Segmentation

引用

IEEE Transactions on computers 2025年第6期74卷 1936-1948页

作者： Liu, Yuchen He, Ligang Zhang, Zhigao Ren, Shenyuan University of Warwick Department of Computer Science CoventryCV4 7AL United Kingdom Wuhan University School of Computer Science Wuhan430072 China China Hubei Luojia Laboratory Wuhan430072 China Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing100044 China

Federated Learning (FL) is typically deployed in a client-server architecture, which makes the Edge-Cloud architecture an ideal backbone for FL. A significant challenge in this setup arises from the diverse data feature distributions across different edge locations (i.e., non-IID data). In response, Personalized Federated Learning (PFL) approaches have been developed. Network segmentation-based PFL is an important approach to achieving PFL, in which the training network is divided into a global segment for server aggregation and a local segment maintained client-side. Existing methods determine the segmentation before the training, and the segmentation remains fixed throughout the PFL training. However, our investigation reveals that model representations vary as PFL progresses and the fixed segmentation may not deliver best performance across various training settings. To address this, we propose PFed-NS, a PFL framework based on adaptive network segmentation. This adaptive segmentation technique is composed of two elements: a mechanism for assessing divergence of clients’ probability density functions constructed from network layers’ outputs, and a model for dynamically establishing divergence thresholds, beyond which server aggregation is deemed detrimental. Further optimization strategies are proposed to reduce the computation and communication costs incurred by divergence modeling. Moreover, we propose a divergence-based BN strategy to optimize BN performance for network segmentation-based PFL. Extensive experiments have been conducted to compare PFed-NS against recent PFL models. The results demonstrate its superiority in enhancing model accuracy and accelerating convergence. © 1968-2012 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Educational Dialogue Systems for Visually Impaired Students: Introducing a Task-Oriented User-Agent Corpus 30

Educational Dialogue Systems for Visually Impaired Students:...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Di Nuovo, Elisa Sanguinetti, Manuela Balestrucci, Pier Felice Anselma, Luca Bernareggi, Cristian Mazzei, Alessandro Computer Science Department University of Turin Italy Department of Mathematics and Computer Science University of Cagliari Italy Department of Mathematics Laboratory S. Polin University of Turin Italy

ISBN: (纸本)9782493814104

This paper describes a corpus consisting of real-world dialogues in English between users and a task-oriented conversational agent, with interactions revolving around the description of finite state automata. The creation of this corpus is part of a larger research project aimed at developing tools for an easier access to educational content, especially in STEM fields, for users with visual impairments. The development of this corpus was precisely motivated by the aim of providing a useful resource to support the design of such tools. The core feature of this corpus is that its creation involved both sighted and visually impaired participants, thus allowing for a greater diversity of perspectives and giving the opportunity to identify possible differences in the way the two groups of participants interacted with the agent. The paper introduces this corpus, giving an account of the process that led to its creation, i.e. the methodology followed to obtain the data, the annotation scheme adopted, and the analysis of the results. Finally, the paper reports the results of a classification experiment on the annotated corpus, and an additional experiment to assess the annotation capabilities of three large language models, in view of a further expansion of the corpus. The corpus is released under the Creative Commons Attribution Non Commercial 4.0 International license and available, only for research purposes, at: https://***/records/10822733. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

LegoDroid: flexible Android app decomposition and instant installation

引用

science China(Information sciences) 2023年第4期66卷 155-173页

作者： Yi LIU Yun MA Xusheng XIAO Tao XIE Xuanzhe LIU School of Computer Science Peking University Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of Education Institute for Artificial Intelligence Peking University Department of Computer and Data Sciences Case Western Reserve University

Current mobile applications(apps) have become increasingly complicated with increasing features that are represented on the graphical user interface associated with application programming interfaces(APIs) to access backend functionality and data. Meanwhile, apps suffer from the “software bloat” in volume. Some app features may be redundant, with respect to those features(from other apps) that the users already desirably and frequently use. However, the current app release model forces users to download and install a full-size installation package rather than optionally choosing only their desired features. Large-size apps can not only increase the local resource consumption, such as CPU, memory, and energy, but also inevitably compromise the user experience, such as the slow load time in the app. In this article, we first conduct an empirical study to characterize the app feature usage when users interact with Android apps,and surprisingly find that users access only a very small subset of app features. Based on these findings,we design a new approach named Lego Droid, which automatically decomposes an Android app for flexible loading and installation, while preserving the expected functionality with a fast and instant app load. With such a method, a slimmer bundle will be downloaded and host the target APIs inside the original app to satisfy users' requirements. We implement a system for Lego Droid and evaluate it with 1000 real-world Android apps. Compared to the original full-size apps, apps optimized by Lego Droid can substantially improve the load time by reducing the base bundle and feature bundles by 13.06% and 10.93%, respectively,along with the app-package installation size by 44.17%. In addition, we also demonstrate that Lego Droid is quite practical with evolving versions, as it can produce substantial reusable code to alleviate the developers' efforts when releasing new app versions.

关键词： performance software bloat instant installation mobile applications program analysis

来源：评论

学校读者我要写书评

暂无评论

An Effective Face Recognition System Based on Transfer Learning 6

An Effective Face Recognition System Based on Transfer Learn...

引用

6th International Hybrid Conference on Informatics and Applied Mathematics, IAM 2023

作者： Hattab, Abdessalam Behloul, Ali LaSTIC Laboratory Department of Computer Science Batna-2 University Batna Algeria

Face recognition is a widely studied field in biometrics that has achieved notable success in controlled environments. However, challenges arise when faced with uncontrolled conditions such as facial expressions, occlusions, and illumination variation. This paper proposed an effective face recognition system that addresses these challenges based on fine-tuned Xception Model. The system utilized a newly proposed deep CNN model inspired by the pre-trained Xception model. We employ the Transfer Learning technique to effectively train our proposed Deep CNN model and mitigate overfitting. Our proposed system successfully addresses the challenges associated with unconstrained conditions and training Deep Learning models using limited datasets. Experimental results demonstrate the superiority of our face recognition system over state-of-the-art methods in uncontrolled environments. Impressively, the system achieved a perfect accuracy rate of 100% on the ORL database using a two-fold cross-validation protocol. On the AR database, the system achieved a significant accuracy rate of 95.17% by training only on the fully visible faces and testing on occluded faces. Additionally, the system achieved an accuracy rate of 99.93% on an AR dataset containing illumination variation using a two-fold cross-validation protocol. © 2023 Copyright for this paper by its authors.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Prediction of Vehicle Lane Departure During Night-Times: A Synthetic Over-Sampling Framework with Enhanced Dimensionality Reduction 2nd

Deep Learning Prediction of Vehicle Lane Departure During Ni...

引用

2nd International Conference on Connected Objects and Artificial Intelligence, COCIA 2024

作者： Elamrani Abou Elassad, Dauha Elamrani Abou Elassad, Zouhair El Meslouhi, Othmane Ameksa, Mohammed Kardouchi, Mustapha Akhloufi, Moulay SARS Research Team Computer Science Department ENSAS Cadi Ayyad University Marrakesh Morocco LAMIGEP Laboratory EMSI Marrakesh Morocco LISI Laboratory Computer Science Department Faculty of Sciences Semlalia Cadi Ayyad University Marrakesh Morocco PRIME Laboratory Computer Science Department Moncton University Moncton Canada

ISBN: (纸本)9783031704109

The inevitability and imminent widespread adoption of autonomous vehicles are acknowledged, yet human supervision in driving remains crucial for the foreseeable future. Assessing a driver's capacity to take control during critical situations involves monitoring lane departure events during night-times through the incorporation of various features. In response to this challenge, this study endeavors to develop a deep learning framework designed to predict lane departure events based on driver demographic traits including age and gender, further to driver in- puts like throttle and brake pedal positions, along with vehicle data such as speed and tires’ temperature obtained through a driving simulator. Dimensionality reduction has been endorsed using Random Forest and Principal Component Analysis to enhance the system’s performance. Moreover, the SMOTE-TL and ADASYN synthetic oversampling techniques were employed to resolve the data imbalance issue. The most favorable outcomes were achieved through the proposed deep learning MLP model. Notably, there has been limited exploration into assessing vehicle lane departure events during night times based on the proposed framework. In its entirety, the proposed system and its findings offer novel insights and present a promising tool for enhancing road safety within the realm of traffic intelligent transportation systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

IoT-Botnet Detection Using Deep Learning Techniques 17th

IoT-Botnet Detection Using Deep Learning Techniques

引用

17th International Conference on Information Technology and Applications, ICITA 2023

作者： Belkacem, Soundes LAMIE Laboratory Department of Computer Science University of Batna 2 Batna Algeria

ISBN: (纸本)9789819983230

Botnet attacks have become a major threat to the Internet of Things (IoT) over the past few years. Malicious operations, attacks, data loss, and network compromise are all possible outcomes of botnets. This paper presents a comparative study on advanced deep learning algorithms for IoT-Botnet attacks detection and classification. We explore the performances of four classifiers including autoencoders, CNN-LSTM, artificial neural network, and multi-layer perceptron for the detection of eleven attacks associated with the Mirai and Bashlite’s malware. We intend to thoroughly analyze and evaluate the DL techniques for multiclass classification problem to successfully identify attack types from 11attacks using the N-BaIoT dataset. The experimental results indicate that for multiclass classification, the multi-layer perceptron classifier outperforms other classifiers producing an accuracy of 0.91 with a precision of 0.90. Attacks associated with the Gafgyt malware exhibit the highest detection rate with an F1-score up to 1.00. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

A hybrid ensemble framework for integrating environmental parameters for improved crop yield prediction and sustainable agricultural decision-making in Iraq

引用

Neural Computing and Applications 2025年 1-23页

作者： Albaaji, Ghassan Faisal Chandra S S, Vinod Machine Intelligence Research Laboratory Department of Computer Science University of Kerala Thiruvananthapuram695581 India Directorate of Agriculture Wasit Governorate Wasit52001 Iraq

This study introduces the Hybrid Recurrent Ensemble Depth (HyRED) framework to enhance crop yield prediction in Iraq by integrating diverse environmental and agricultural parameters. The analysis utilises the Valued Agricultural Grounds (VAG) dataset, a novel resource developed exclusively for this study, comprising data from 1034 agricultural plots in Wasit Governorate, Iraq. This unique dataset combines soil properties, agricultural practices, meteorological data, geographic information, and remote sensing indicators such as vegetation health and biomass indices. By using this comprehensive dataset, HyRED employs an advanced hierarchical ensemble structure that integrates memory-based and pattern-recognition modules to capture both short-term temporal patterns and long-term dependencies. This approach achieves high predictive accuracy (MSE = 0.432) while reducing overfitting and enhancing generalisability. By using this novel dataset, remote sensing indicators, and advanced predictive tools, this study offers actionable recommendations for improving agricultural productivity and food security in Iraq, setting a new benchmark for sustainable agriculture research. Notable insights include the identification of optimal fertiliser rates: 60 kg / IQ Dunum for diammonium phosphate (DAP) and 100 kg / IQ Dunum for nitrogen, which increased productivity by up to 25% compared to conventional practices. Positive correlations with nitrogen (0.8985) and DAP (0.7853) underscore their importance, while negative correlations, such as soil electrical conductivity (− 0.9220) and extreme temperatures (− 0.5967), highlight environmental challenges. Integrating remote sensing indicators revealed critical growth stages and stress patterns, providing actionable insights to optimise crop management. This study sets a benchmark for sustainable agriculture by combining innovative predictive tools with a novel dataset to improve productivity and food security in Iraq. © The Author(s), under

关键词： Agro computer Decision-making Hybrid ensemble model Informatics agriculture Yield prediction

来源：评论

学校读者我要写书评

暂无评论

Cervical spine fracture detection using deep learning algorithm 8

Cervical spine fracture detection using deep learning algori...

引用

8th IEEE International Conference on Image and Signal Processing and their Applications, ISPA 2024

作者： Meadi, Mohamed Nadjib El Moumene Zerari, Abd Benbrahim, Hadjer University of Mohamed Khider LESIA Laboratory Department of Computer Science Biskra Algeria

ISBN: (纸本)9798350309249

Artificial intelligence (AI) has revolutionized various scientific fields, including healthcare. In particular, deep learning (DL) algorithms have shown remarkable potential in medical imaging, enabling accurate disease detection and diagnosis. Among the prevalent injuries, cervical spine fractures require rapid identification for timely treatment. Recent advancements in AI and DL techniques have opened up new possibilities for automated recognition and classification of cervical spine fractures using medical imaging data. In this study, we investigate the capabilities of deep learning algorithms, specifically the convolutional neural network (CNN) architecture, for automated detection and classification of cervical spine fractures. The outcomes of our research have the potential to significantly enhance early detection and treatment of cervical spine fractures, leading to improved patient outcomes. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Indexing dynamic encrypted database in cloud for efficient secure k-nearest neighbor query

引用

Frontiers of computer science 2024年第1期18卷 187-198页

作者： Xingxin LI Youwen ZHU Rui XU Jian WANG Yushu ZHANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 210016China Department of Mathematical Informatics University of TokyoTokyo 113-8654Japan Guangxi Key Laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China School of Computer Science China University of GeosciencesWuhan 430074China

Secure k-Nearest Neighbor(k-NN)query aims to find k nearest data of a given query from an encrypted database in a cloud server without revealing privacy to the untrusted cloud and has wide applications in many areas,such as privacy-preservingmachine elearning gand secure biometric *** solutions have been put forward to solve this challenging ***,the existing schemes still suffer from various limitations in terms of efficiency and *** this paper,we propose a new encrypt-then-index strategy for the secure k-NN query,which can simultaneously achieve sub-linear search complexity(efficiency)and support dynamical update over the encrypted database(flexibility).Specifically,we propose a novel algorithm to transform the encrypted database and encrypted query points in the *** indexing the transformed database using spatial data structures such as the R-tree index,our strategy enables sub-linear complexity for secure k-NN queries and allows users to dynamically update the encrypted *** the best of our knowledge,the proposed strategy is the first to simultaneously provide these two *** theoretical analysis and extensive experiments,we formally prove the security and demonstrate the efficiency of our scheme.

关键词： cloud computing secure k-NN query sub-linear complexity dynamicupdate

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：