检索结果-内蒙古大学图书馆

27th Pan-Hellenic Conference on Progress in Computing and informatics with International Participation, PCI 2023

作者： Tsalera, Eleni Stratogiannis, Dimitrios Papadakis, Andreas Voyiatzis, Ioannis Samarakou, Maria Department of Informatics and Computer Engineering University of West Attica Greece Athens Greece

ISBN: (纸本)9798400716263

Deep learning is increasingly used in diverse application fields with results typically surpassing those of traditional machine learning techniques. The portfolio of available neural networks is wide, consisting of the full range in terms of complexity, from compact networks to large ones with multiple layers and parameters. This heterogeneity in the model topology is reflected, not necessarily linearly, on the required computational resources for training and inference. Similarly, the environments where the neural networks are trained and executed are transformed from fully-fledged centralized nodes to distributed architectures with constrained resources. In this view, computational resource requirements can be one of the criteria for resource usage management and neural network selection. In this work we measure the training times for a set of five convolutional neural networks of varying complexity and age (GoogleNet, ShuffleNet, VGGish, YAMNet) under different training configurations, considering the batch size, the number of epochs and the learning rate. These measurements are used to create a CPU-time-training dataset of more than 500 values. This dataset is used to train and evaluate models, based on neural networks, for estimating and predicting training times depending on the models employed and the training parameters. Five regression models have been trained and evaluated in terms of correlation coefficient and root mean square error. In addition, we measure the CPU times needed for inference for a subset of the trained models, which prove to be uncorrelated with the corresponding training times. © 2023 Owner/Author.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Spectral Efficiency in 5G MIMO Networks Through Adaptive Beamforming Techniques 7

Enhancing Spectral Efficiency in 5G MIMO Networks Through Ad...

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Konstantinos, Tsachrelias Katsigiannis, Chrisostomos-Athanasios Kokkinos, Vasileios Gkamas, Apostolos Bouras, Christos Pouyioutas, Philippos University of Patras Computer Engineering and Informatics Department Patras Greece University of Ioannina Department of Chemistry Ioannina Greece University of Cyprus Computer Science Department Nicosia Cyprus

ISBN: (纸本)9798350367027

The evolution of 5G networks is driving advancements in data rates, latency reduction, and connectivity, with adaptive beamforming emerging as a core technology to enhance spectral efficiency. This study demonstrates how integrating beamforming with spatial filtering can effectively optimize signal quality in 5G MIMO networks. Through simulations, we show that our approach achieves significant improvements in Signal-To-Noise Ratio (SNR) by optimizing beam directions. Specifically, results indicate that optimal beamforming angles can yield SNR values as high as 78 dB, substantially outperforming lower SNRs observed at less favorable angles. These findings underscore the potential of combined beamforming and spatial filtering to enhance communication reliability and network performance, particularly in high-density settings. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Modified MobileNetV2 with Convolutional Block Attention Module for Facial Expression Recognition

Modified MobileNetV2 with Convolutional Block Attention Modu...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Nafi'an, Muh. Hafidh Ilmi Bachtiar, Fitra Abdurrachman Setiawan, Budi Darma Brawijaya University Computer Science Faculty Informatics Engineering Department Malang Indonesia

ISBN: (纸本)9798350382914

Facial emotion recognition is one of the artificial intelligence implementations used to recognize emotions based on data learned by computers. Unlike humans, who can recognize a person's emotions directly, computers need several trainings procedures conducted by humans to be able to recognize a person's emotions. Previous research has proposed various methods with deep learning and traditional machine learning approaches to classify emotions based on faces. Some studies obtained relatively high accuracy, but on evaluation by cross-validation, the results were much lower than the accuracy obtained. Therefore, this study proposes an approach using a modified MobileNetV2 deep learning architecture in the residual layer by adding a Convolutional Block Attention Module (CBAM) to improve accuracy and data generalization. This experiment uses the Karolinska Directional Emotional Faces (KDEF) public benchmark dataset. Preprocessing is done with image augmentation to enrich the training data by resizing, center cropping, random horizontal flipping, random affine, and random rotation. The proposed method is evaluated by 5-fold cross-validation and compared with MobileNetV2 without modification and state-of-the-art methods. Experimental results show that the proposed model outperform all comparative methods by achieving a 5 -fold cross-validation accuracy of 94.387%. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Agricultural Education with Virtual Reality and Gamification: A Novel Approach for Enhancing Knowledge Transfer and Skill Acquisition 1

引用

3rd International Conference on Novel and Intelligent Digital Systems, NiDS 2023

作者： Strousopoulos, Panagiotis Troussas, Christos Papakostas, Christos Krouska, Akrivi Sgouropoulou, Cleo Department of Informatics and Computer Engineering University of West Attica Egaleo12243 Greece

ISBN: (数字)9783031441462

ISBN: (纸本)9783031441455

Agricultural education holds significant importance as it provides comprehensive training in the principles and practices of agriculture, including apiculture, which plays a crucial role in sustainable practices and the cultivation of skilled farmers and apiarists. However, traditional approaches to agricultural education face inherent limitations when it comes to engaging students effectively and facilitating optimal knowledge transfer and skill acquisition. Recognizing this compelling need for innovative methodologies, this research paper introduces a novel approach to apiculture education that harnesses the power of virtual reality (VR) and gamification principles in a captivating application named Beekeeper World. Beekeeper World immerses users in an interactive and engaging VR environment where they assume the role of beekeepers responsible for safeguarding bees from threats, symbolized by spiders. By leveraging digital technologies and gamification techniques, this application aims to cultivate a new generation of passionate and skilled apiarists. This study explores the implications of Beekeeper World for apiculture education and the broader agricultural sector, underscoring the importance of innovative teaching methods in preparing future professionals for the dynamic realm of apiculture and ensuring the long-term sustainability of global food systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in physiological characteristics recognition for internet of things authentication

引用

Digital Communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

来源：评论

学校读者我要写书评

暂无评论

ERAS-NETS: An Efficient Resource Allocation Scheme-based Nonlinear Energy Harvesting Timeslot Switching 8

ERAS-NETS: An Efficient Resource Allocation Scheme-based Non...

引用

8th IEEE International Conference on engineering Technologies and Applied Sciences, ICETAS 2023

作者： Guler, Nivine Gunes, Ali University of Technology Bahrain Department of Informatics Engineering Bahrain Istanbul Aydin University Department of Computer Engineering Turkey

ISBN: (纸本)9798350327090

In this paper, an efficient resource allocation scheme-based nonlinear energy harvesting (EH) Timeslot switching (TS) for single-input-single-output (SISO) SWIPT systems-(ERAS-NETS) is presented. The energy saturation characteristic is considered in the EH model where point-to-point (P2P) single-input single-output (P2P-SISO) SWIPT system is studied. Harvesting energy is based on Timeslot switching (TS) aiming at optimizing the average data rate where the TS ratio is a binary value (0 or 1). Hence, the problem is a nonconvex optimization problem because of the binary factor of the TS ratio. The optimization problem is solved using the Lagrange dual theorem that states that the optimal values of the Primal (P) and Dual (D) linear problem are the same if either solution is a basic feasible solution. Accordingly, the derivation of the optimal solution helps receiver to switch either to EH or information decoding (ID) based on the SNR value. Hence, the receiver will switch to EH in the districts having medium values of SNR, otherwise, the receiver will switch to ID in districts having SNR less than 5 dB or more than 25 dB. Different network performance metrics were considered in evaluating the proposed ERAS-NETS scheme in comparison with traditional state-in-the-art TS resource allocation schemes such as transmission power, distance between source and destination, pathloss exponent, and minimum required harvested energy. Simulations showed that ERAS-NETS improves energy efficiency with respect to different transmission power by 20%, 10%, and 3 % for high SNR, medium SNR, and low SNR districts, respectively. Improvement with respect to average energy efficiency versus other system performance metrics has also been noted for the proposed scheme. © 2023 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

A Terramechanics-based Dynamic Model for Motion Control of Unmanned Tracked Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Zhang, Ruizeng Zhou, Wei Liu, Haiou Gong, Jianwei Chen, Huiyan Khajepour, Amir School of Mechanical Engineering Beijing Institute of Technology Beijing China School of Computer Science and Informatics Cardiff University Cardiff U.K Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo Canada

Existing terramechanics-based dynamic models for tracked vehicles (TRVs) are widely used in dynamics analysis. However, these models are incompatible with model-based controller design due to their high complexity and computational costs. This study presents a novel and simplified terramechanics-based dynamic model for TRVs that can be used in optimization-based real-time motion controller design. To this end, we approximated the track-ground interactions with an averaged term of the track-ground shear stresses to make the model computationally efficient and linearizable. By introducing the concepts of slip ratio and slip angle in the field of wheeled vehicles, the terramechanics-based dynamic model was finally simplified into a compact and practical single-track dynamic model reducing the demand for precise slip ratio measurements. The single-track model enables us to design an efficient motion control scheme by considering lateral and longitudinal dynamics separately. Finally, the proposed dynamic model was verified and validated under various road conditions using a real TRV. Additionally, the performance of different models was compared in simulation as an example to demonstrate that the proposed model outperforms the existing ones in TRV path-following tasks. IEEE

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

GAN-generated Synthetic Data and SVM-based Feature Selection for Improved Cardiovascular Disease Prediction

GAN-generated Synthetic Data and SVM-based Feature Selection...

引用

2023 Medical Technologies Congress, TIPTEKNO 2023

作者： Mandan, Amel Sulaiman Hazzaa, Nidhal Mohsin Yildiz, Oktay Informatics Institute Gazi University Computer Science Department Ankara Turkey Gazi University Faculty of Engineering Department of Computer Engineering Ankara Turkey

ISBN: (纸本)9798350328967

Early diagnosis requires cardiovascular disease forecasting. Past patient interests can improve machine learning predictions. This study uses a Generative Adversarial Network (GAN) to augment data to address the issue of insufficient datasets. Our objective is to use the GAN and feature selection (FS) to tackle the issue of class imbalance. The study assesses the efficacy of three different machine learning (ML) algorithms in predicting coronary artery disease (CAD). The UCI repository provided the Z-Alizadeh sani dataset for our analysis. A GAN was used to balance an imbalanced dataset. We used GAN to augment data and synthesise data to improve the models. Support Vector Machine (SVM) as feature selection tool was used to extract more effective attributes. We trained and tested CAD prediction using machine learning algorithms using 5-fold cross validation. We compared the machine-learning algorithm's outcomes with and without GAN-based data enhancement and feature selection to evaluate its predicted accuracy. According to results GAN and feature selection improved accuracy, sensitivity, and specificity for all algorithms, suggesting that generated data and selected attributes can identify positive and negative cases. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Eye Disease Classification Based on Fundus Images Using Convolutional Neural Network 25

Eye Disease Classification Based on Fundus Images Using Conv...

引用

25th International Electronics Symposium, IES 2023

作者： Denandra, Rafi Fariza, Arna Prayogi, Yanuar Risah Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

The eye is a vital organ in the human body. Through the eyes, humans can absorb over 80% of visual information used to carry out various daily activities. However, in Indonesia, there are many cases of vision impairments that, if not properly addressed, can lead to blindness. Examples of such impairments include cataracts, glaucoma, and diabetic retinopathy. Currently, there are many research studies on eye diseases that are aided by technologies like Artificial Intelligence (AI). One of the AI technologies that is commonly developed is Convolutional Neural Network (CNN). CNN is a deep learning framework that excels in solving image or picture classification problems because its architecture applies convolution layers, which can break down images to extract features and easily reduce the high dimensionality without losing the image's information itself. In this study, the author used various CNN models to find the most suitable model for classifying eye diseases, including EfficientNet, ResNet, Inception V3, and many others. Through various model training experiments, the accuracy for the ResNet50 model was found to be 95% with a loss of 17%, followed by Xception with an accuracy of 95% and a loss of 21%, and EfficientNetV2B2 with an accuracy of 92% and a loss of 25%. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Equipment Parameter Investigation for a Proposed Power Conductor Hot Spot Identification system 10

Equipment Parameter Investigation for a Proposed Power Condu...

引用

10th International Conference on Modern Power Systems, MPS 2023

作者： Polycarpou, Alexis Komodromos, Michael Kalli, Kyriacos Argyrou, Maria C. Ioannou, Andreas Computer Engineering and Informatics Frederick University Frederick Research Center Deparment of Electrical Nicosia Cyprus Cyprus University of Technology PhOSLab Department of Electrical Engineering/Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798350326826

Reliability, efficiency and continuity of power energy supplied is an area which receives increasing attention as the main infrastructure of power transmission and distribution systems in many countries is ageing. Hot spot related cable failures and power interruptions have a big financial impact on the power provider. The operational parameters of a method to identify in real time hot spots on cables is investigated in this paper, which can result to timely fault prevention. This can be achieved through exploiting the optical sensing capabilities of the existing optical fibre on-grid network. The resulting parameters aim to be advantageous for the system as they increase accuracy and will enable the Remote, automated, continuous, and real time monitoring of the grid infrastructure integrity. © 2023 IEEE.

关键词： Cables

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：