检索结果-内蒙古大学图书馆

An Optimal Scheme for WSN Based on Compressed Sensing

computers, Materials & Continua 2022年第7期72卷 1053-1069页

作者： Firas Ibrahim AlZobi Ahmad Ali AlZubi Kulakov Yurii Abdullah Alharbi Jazem Mutared Alanazi Sami Smadi Department of Information Systems and Networks Faculty of Information TechnologyThe World Islamic Sciences&Education UniversityJordan Computer Science Department Community CollegeKing Saud UniversitySaudi Arabia Department of Computer Engineering National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic InstituteUkraine

Wireless sensor networks(WSNs)is one of the renowned ad hoc network technology that has vast varieties of applications such as in computer networks,bio-medical engineering,agriculture,industry and many *** has been used in the internet-of-things(IoTs)applications.A method for data collecting utilizing hybrid compressive sensing(CS)is developed in order to reduce the quantity of data transmission in the clustered sensor network and balance the network *** cluster head nodes are chosen first from each temporary cluster that is closest to the cluster centroid of the nodes,and then the cluster heads are selected in order based on the distance between the determined cluster head node and the undetermined candidate cluster head ***,each ordinary node joins the cluster that is nearest to *** greedy CS is used to compress data transmission for nodes whose data transmission volume is greater than the threshold in a data transmission tree with the Sink node as the root node and linking all cluster head *** simulation results demonstrate that when the compression ratio is set to ten,the data transfer volume is reduced by a factor of *** compared to clustering and SPT without CS,it is reduced by 75%and 65%,*** compared to SPT with Hybrid CS and Clustering with hybrid CS,it is reduced by 35%and 20%,*** and SPT without CS are compared in terms of node data transfer volume standard *** with Hybrid CS and clustering with Hybrid CS were both reduced by 62%and 80%,*** compared to SPT with hybrid CS and clustering with hybrid CS,the latter two were reduced by 41%and 19%,respectively.

关键词： Compressed sensing computer networks sensor networks ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Non-deep Approach to Classifying Movie Genres Based on Multimodal Data 13th

A Non-deep Approach to Classifying Movie Genres Based on M...

引用

13th International Conference on Image Processing and Communications, IP and C 2023, 13th International Conference on computer Recognition systems, CORES 2023

作者： Niedziólka, Pawel Zyblewski, Pawel Department of Systems and Computer Networks Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wybrzeże Wyspiańskiego 27 Wroclaw50-370 Poland

ISBN: (纸本)9783031416293

Multimodal data processing has recently become popular due to technological advances and easier access to real video, audio, images, or text data. This data type is often processed using deep neural networks associated with high time and computational complexity. The present work addresses the problem of classifying a multimodal MM-IMDb dataset, representing the problem of recognizing a movie genre based on a poster and a brief description of the plot. For experiments, 20 binary subsets were separated, from which features were then extracted. Features from the text were obtained using the tf-idf method, while the posters were reduced to a single color. computer experiments on the resulting tabular data were conducted separately on both modalities, as in the concatenated feature space. The results confirmed that classical approaches to feature extraction could allow satisfactory quality classification of multimodal data to be obtained even when using relatively simple pattern recognition algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Study of Factors Influencing on Mental Health and Their Relationships, of IT Sector Employees in Colombo District, Sri Lanka 5

Study of Factors Influencing on Mental Health and Their Rela...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Dias, S.P.L. Lokuliyana, S. University of Sabaragamuwa Faculty of Applied Sciences Department of Physical Sciences and Technology Belihuloya Sri Lanka Sri Lanka Institute Information Technology Faculty of Graduate Studies and Research Department of Computer Systems and Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This study focused on the mental health of IT sector employees in Colombo, using quantitative research methods and data from 300 participants (162 males and 138 females) using the DASS 21 questionnaire and self-administered surveys through convenience sampling. Correlation analysis, chi-square tests, and regression analysis were utilized to examine the data. It found significant correlations between mental health outcomes (stress, anxiety, and depression) and factors like work-life balance, workload, working conditions, and physical fitness. Work-life balance, working environment, and workload were identified as the most significant predictors of mental health outcomes. Physical fitness was associated with stress, depression, and anxiety but had a limited overall impact on mental health. Differences in depression, stress, and anxiety levels were observed based on marital status, age group, work experience, salary, and gender. These findings emphasize the importance of addressing work-life balance and working conditions to enhance the mental health of IT sector employees in Colombo. They provide valuable insights for organizations and policymakers to develop strategies and interventions that promote employee well-being and productivity, underscoring the need to prioritize mental health and create a supportive work environment. © 2023 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based on Clustering Algorithm and an Efficient Edge Detection 1st

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based...

引用

1st edition of the International Conference on Artificial Intelligence and Green Computing, ICAIGC 2023

作者： Hamout, Hamza Elyousfi, Abderrahmane Computer Systems and Vision Laboratory Faculty of Sciences Ibn-Zohr University Agadir80000 Morocco Department of Computer Science National Engineering School of Applied Sciences Ibn-Zohr University Agadir80000 Morocco

ISBN: (纸本)9783031465833

In 2016, ITU-T Video Coding Experts Group (VCEG) and ISO/IEC MPEG finalize the recent 3-dimensional video coding standard founded on Multi-view texture Videos plus Depth maps (MVD) format called, the 3D extension of High-Efficiency Video Coding (3D-HEVC). In the current design of 3D-HEVC, the conventional intra-prediction modes and Depth Modeling Modes are exploited sophistically to improve the depth map coding performance. However, the coding efficiency improvement is achieved at the cost of computational complexity load, which obstructs 3D-High Efficiency Video Coding standards from practical world applications. In the 3D-HEVC, the depth maps are described by enormous homogeneous regions, and it is observed that for most of the cases, the DMMs and all or the majority of angular intra modes could be skipped for the homogenous area. Thus, we propose an efficient intra-coding model decision for a depth map founded on the clustering algorithm and edge detection to resolve the above-mentioned complexity increase. Experimental results demonstrate that the proposed intra-coding model decision for depth map can decrease the encoding time up to 41.35%, with insignificant loss of rate-distortion performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review of Security Control Assessment Challenges 12

Systematic Literature Review of Security Control Assessment ...

引用

12th IEEE International Conference on Control System, Computing and Engineering, ICCSCE 2022

作者： Abu Othman, Noor Ashitah Norman, Azah Anir Mat Kiah, Miss Laiha Universiti Malaya Faculty of Comp. Science & Information Technology Kuala Lumpur Malaysia Universiti Teknologi MARA Faculty of Computer & Math. Sciences Melaka Malaysia Universiti Malaya Faculty of Computer Science & Information Technology Dept. of Information Systems Kuala Lumpur Malaysia Universiti Malaya Faculty of Computer Science & Information Technology Dept. of Computer System &Technology Kuala Lumpur Malaysia

ISBN: (数字)9781665483391

ISBN: (纸本)9781665483391

The advancement of cybersecurity has called for active effective information security management. Security control (SC) assessment must be empowered to ensure that security implementation is effective and provides expected protection. Lack of comprehensive literature analysis on SC assessment compared to risk and threats assessments are concerning. This research aims to systematically review the trends of SC assessment by identifying, categorizing and analyzing the challenges and available solutions of SC assessment. 34 articles were qualitatively selected with a definite contribution in SC assessment. These articles were reviewed using thematic analysis according to Theme 1: Assessment Challenges, and Theme 2: Proposed Solution. Findings from each theme are systematically categorized to answer research questions. The results of this review are significant in identifying the issues and areas of improvement for future research and can serve as the baseline for SC assessment characteristics. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Residual Network for Motorcyclist Behavior Recognition Using Inertial Sensors 8

Lightweight Deep Residual Network for Motorcyclist Behavior ...

引用

8th International Conference on information Technology, InCIT 2024

作者： Hnoohom, Narit Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Faculty of Engineering Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand University of Phayao Department of Computer Engineering School of Information and Communication Technology Phayao Thailand King Mongkut's University of Technology Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics North Bangkok Thailand

ISBN: (纸本)9798350366303

Motorcyclist behavior recognition (MBR) is a significant factor in improving road safety and preventing accidents. Inertial sensors, such as accelerometers, gyroscopes, and magnetometers, have shown promising potential for capturing the dynamic behavior of motorcyclists. However, existing approaches often require complex models and significant computational resources, limiting their deployment in real-world scenarios. This study presents a MotoNeXt architecture, which is a light deep residual network for correctly identifying the behavior of motorcyclists using data from inertial sensors. Our approach leverages the power of deep learning while maintaining a compact model size, making it suitable for resource-constrained environments. The proposed network incorporates multi-kernel residual blocks to facilitate the learning of hierarchical features and improve gradient flow during training. We evaluate our method on a publicly available benchmark dataset, MB-IMU, collected from multiple riders under various riding conditions. Experimentation has shown that our lightweight model achieves cutting-edge performance, outperforming a variety of existing techniques. In Scenario I, using accelerometer, gyroscope, and magnetometer data, MotoNeXt achieved an accuracy result of 78.90088% along with an F1-score of 81.56738%. According to Scenario II, which included additional sensor data such as VelInc, OriInc, and Euler angles, MotoNeXt further improved its performance, achieving an accuracy result of 83.29735% along with an F1-score of 84.95352%. The proposed approach offers a practical solution for real-time MBR, enabling the development of intelligent transportation systems and rider assistance technologies. Our experiments highlight the effectiveness of lightweight deep learning models in extracting meaningful patterns from inertial sensor data. This opens up opportunities for further investigation in this field. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

How to Construct Pseudorandom Bit Sequences from Mazes by a Method Digging Out Walls

How to Construct Pseudorandom Bit Sequences from Mazes by a ...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Miyazaki, Takeru Araki, Shunsuke Uehara, Satoshi Kyushu Inst. of Information Sciences Faculity of Management and Information Sciences Fukuoka Japan Kyushu Inst. of Technology Faculty of Computer Science and Systems Engineering Fukuoka Japan The Univ. of Kitakyushu Faculty of Environmental Engineering Fukuoka Japan

ISBN: (纸本)9798350324174

In this paper, we propose a new pseudorandom bit sequence generator, which is based on a method digging out walls. Although each of these sequences lacks enough randomness, synthesized sequences of them can pass all of the NIST statistical test suite. We also describe a conjectural relation between the number of types on the square mazes and their sizes. © 2023 IEEE.

关键词： Digging Out the Walls Maze Generator Pseudorandom Bit Sequence

来源：评论

学校读者我要写书评

暂无评论

Machine learning models for modeling the biosorption of Fe(III) ions by activated carbon from olive stone

引用

Neural Computing and Applications 2024年第21期36卷 13357-13372页

作者： Massaoudi, Ayman Echouchene, Fraj Ben Ayed, Mossaad Berguiga, Abdelwahed Harchay, Ahlem Al-Ghamdi, Sara Belmabrouk, Hafedh Department of Computer Science College of Science and Arts in Gurayat Jouf University Sakakah Saudi Arabia Olive Research Center Jouf University Sakakah Saudi Arabia Laboratory of Electronics and Microelectronics Faculty of Science of Monastir University of Monastir Environment Boulevard Monastir5019 Tunisia Higher Institute of Applied Sciences and Technology of Sousse University of Sousse Sousse Tunisia Department of Industrial Electronics ENISo University of Sousse Sousse Tunisia Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Physics College of Science Majmaah University Al Majma’ah11952 Saudi Arabia

Using experimental results related to the biosorption of Fe(III) by activated carbon derived from olive pit waste, we developed and evaluated four artificial neural network (ANN) models in this study, namely MLP-ANN, RBF-ANN, GR-ANN, and PSO-ANN, to predict the removal efficiency of Fe(III) during the adsorption process. The purpose of these models was to forecast the effect of the following five important operational variables: the initial concentration, time, stirring speed, temperature, and biosorbent dose. We conducted a thorough assessment of the performance of these models and compared their ability to predict the removal capacity. Several statistical metrics have been used to quantify the quality of the different models. The results calculated by the machine learning models were analyzed and compared with the experimental results. The obtained values of the coefficient of determination were 0.9997 for the PSO-ANN model, 0.991 for the GR-ANN model, 0.983 for the RBF-ANN model, and 0.837 for the MLP-ANN model concerning the removal efficiency. All the studied models are able to accurately predict the adsorbed quantity. ANOVA analysis was used to evaluate the effect of the parameters inherent to the PSO-ANN model. The PSO-ANN model proves to be a powerful tool for estimating the efficiency of Fe(III) ion removal. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. corrected publication 2024.

关键词： Biosorption

来源：评论

学校读者我要写书评

暂无评论

Analysis of Feature Parameters and Their Time-Transition for Shockable Arrhythmia and Prediction of the Effect of Electrical Defibrillation 3

Analysis of Feature Parameters and Their Time-Transition for...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Noguchi, Shunta Yoshikawa, Yuta Okai, Takayuki Oya, Hidetoshi Rahman, Md. Masudur Yoshida, Minoru Graduate School of Integrative Science and Engineering Tokyo City University Tokyo Japan Tokyo City University Department of Computer Science Tokyo Japan Noakhali Science and Technology University Department of Information and Communication Engineering Bangladesh Kanagawa University Department of Applied Systems and Mathematics Kanagawa Japan

ISBN: (纸本)9798331540319

In this paper, we propose a prediction system of the effect of electrical defibrillation. In order to develop the proposed system, we firstly analyze from pre-shock (immediately before defibrillation) ECGs (ElectroCardioGrams) by using Gabor Wavelet Transform, Poincaré plot analysis, Spectral entropy, and feature parameters are extracted by those extracted analysis results, we focus on time-transition feature parameter. Next, effective feature parameters are selected based on χ2 -test. Finally, 'Effective' and 'Ineffective' for electrical defibrillation are classified by using SVM (Support Vector Machine) with three kernels (Linear, Gaussian, and Polynomial) and regularization. In this way, we shows the effectiveness of the proposed feature extraction methods and prediction system. © 2024 IEEE.

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：