检索结果-内蒙古大学图书馆

Ensemble deep learning for high-precision classification of 90 rice seed varieties from hyperspectral images

Journal of Ambient Intelligence and Humanized Computing 2024年第6期15卷 2883-2899页

作者： Taheri, AmirMasoud Ebrahimnezhad, Hossein Sedaaghi, Mohammadhossein Computer Vision Research Laboratory Faculty of Electrical Engineering Sahand University of Technology Tabriz Iran

To develop rice varieties with better nutritional qualities, it is important to classify rice seeds accurately. Hyperspectral imaging can be used to extract spectral information from rice seeds, which can then be used to classify them into different varieties. The challenges of precise classification increase when there are many classes and few training samples. In this paper, we present a novel method for high-precision Hyperspectral Image (HSI) classification of 90 different classes of rice seeds using ensemble deep learning. Our method first employs band selection techniques to select the optimal hyperspectral bands for rice seed classification. Then, a deep neural network is trained with the selected hyperspectral and RGB data from rice seed images to obtain different models for different bands. Finally, an ensemble of deep learning models is employed to classify rice seed images and improve classification accuracy. The proposed method achieves an overall precision ranging from 92.73 to 96.17% despite a large number of classes and low data samples for each class and with only 15 selected hyperspectral bands. This precision is significantly higher than the state-of-the-art classical machine learning methods like random forest, confirming the effectiveness of the proposed method in classifying hyperspectral images of rice seeds. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Secure speech coding using chaotic shift keying for encryption combined with error recovery

引用

Multimedia Tools and Applications 2025年第7期84卷 3893-3927页

作者： Boumaraf, Messaouda Merazka, Fatiha LISIC Laboratory Telecommunications Department Electronic and Computer Engineering Faculty USTHB University Algiers Algeria LISIC Laboratory Telecommunications Department Electrical Engineering Faculty USTHB University Algiers Algeria

This paper presents a speech encryption algorithm utilizing chaotic shift keying alongside error recovery techniques for the G.722.2 codec. The algorithm employs chaotic data interleaving on speech inter-frames to replace continuous packet loss with isolated losses, thus restoring missing data packets. Codec parameters undergo encryption through the combination of multiple chaotic maps applied to intra sub-frames of speech, facilitating confusion and diffusion processes. Enhanced security is achieved through the utilization of multiple chaotic maps, including chaotic shift keying generators applied to codec sub-frame parameters. Specifically, the chaotic shift keying mechanism is employed using four chaotic maps: a Henon map for xn and yn, a logistic map for zn, a tent map for wn, and a cubic map for un. The keys derived from these maps are utilized for chaotic data interleaving on both inter-frames and intra sub-frames of the speech file to shuffle frame parameters (confusion) and scramble sub-frame parameters (diffusion). Additionally, the proposed system enhances speech quality by mitigating degradation caused by packet loss through a waveform substitution-based recovery method, which replaces lost packets with previously received copies. A series of experiments, including waveform representation, spectrogram analysis, Enhanced Modified Bark Spectral Distortion (EMBSD) test, WideBand Perceptual Evaluation of Speech Quality (WB-PESQ) test, MUltiple Stimuli with Hidden Reference and Anchor (MUSHRA) score, Mean Opinion Score (MOS) score, correlation test, entropy test, Number of Samples Change Rate (NSCR) test, Unified Average Modified Intensity (UACI) test, key space analysis, and sensitivity test, are conducted to evaluate the security and speech quality of the proposed system. The results validate the system’s security and confirm its ability to maintain good audio quality even under packet loss rates ranging from 5% to 20%. © The Author(s), under exclusive licen

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Fusion Framework Using Deep Learning for Visual-Textual Sentiment Classification

引用

computers, Materials & Continua 2023年第8期76卷 2145-2177页

作者： Israa K.Salman Al-Tameemi Mohammad-Reza Feizi-Derakhshi Saeed Pashazadeh Mohammad Asadpour Computerized Intelligence Systems Laboratory Department of Computer EngineeringFaculty of Electrical and Computer EngineeringUniversity of TabrizTabriz51368Iran Department of Computer Engineering Faculty of Electrical and Computer EngineeringUniversity of TabrizTabriz51368Iran State Company for Engineering Rehabilitation and Testing Iraqi Ministry of Industry and MineralsBaghdad10011Iraq

Multimodal Sentiment Analysis(SA)is gaining popularity due to its broad application *** existing studies have focused on the SA of single modalities,such as texts or photos,posing challenges in effectively handling social media data with multiple ***,most multimodal research has concentrated on merely combining the two modalities rather than exploring their complex correlations,leading to unsatisfactory sentiment classification *** by this,we propose a new visualtextual sentiment classification model named Multi-Model Fusion(MMF),which uses a mixed fusion framework for SA to effectively capture the essential information and the intrinsic relationship between the visual and textual *** proposed model comprises three deep neural *** different neural networks are proposed to extract the most emotionally relevant aspects of image and text ***,more discriminative features are gathered for accurate sentiment ***,a multichannel joint fusion modelwith a self-attention technique is proposed to exploit the intrinsic correlation between visual and textual characteristics and obtain emotionally rich information for joint sentiment ***,the results of the three classifiers are integrated using a decision fusion scheme to improve the robustness and generalizability of the proposed *** interpretable visual-textual sentiment classification model is further developed using the Local Interpretable Model-agnostic Explanation model(LIME)to ensure the model’s explainability and *** proposed MMF model has been tested on four real-world sentiment datasets,achieving(99.78%)accuracy on Binary_Getty(BG),(99.12%)on Binary_iStock(BIS),(95.70%)on Twitter,and(79.06%)on the Multi-View Sentiment Analysis(MVSA)*** results demonstrate the superior performance of our MMF model compared to single-model approaches and current state-of-the-art techniques based on model evaluation cr

关键词： Sentiment analysis multimodal classification deep learning joint fusion decision fusion interpretability

来源：评论

学校读者我要写书评

暂无评论

Studying the Role of Non-Player Users (Spectator and Operator) in XR Single and Multiplayer Experiences 14

Studying the Role of Non-Player Users (Spectator and Operato...

引用

14th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2023

作者： Žákovská, Uršul’a Sedláček, David Department of Computer Graphics and Interaction Faculty of Electrical Engineering Czech Technical University Prague Czech Republic

ISBN: (纸本)9798350325652

This paper presents a study on non-player users (NPUs) in experiences where active users (players) use Virtual Reality (VR), Augmented reality (AR) or any other spectrum of Extended Reality (XR). The spectator, a type of NPU, is hidden from players and does not actively participate in the virtual environment but observes the world and the activities of other users to understand their behaviour further, while the operator, another type of NPU, can manipulate the virtual environment without participating in the gameplay and is responsible for a smooth run of the experience. Both types can be implemented in AR or VR but usually have a desktop design. In most XR experiences, the presence of NPUs is unnecessary due to the nature of the application leading to the user base being composed of only players. However, in cases like location-based entertainment, XR training, or onboarding new hires, NPUs can significantly improve the process. The study examines the impact of NPUs on the user experience and the potential benefits and drawbacks of including them in XR experiences. Specifically, in a VR multi-user experience for assessing soft skills, the study found that with a desktop mode of the spectator, the preset camera views, timestamped notes, and audio activity visualization were the most appreciated functionalities. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Securing Data in Multimode Fibers by Exploiting Mode-Dependent Light Propagation Effects

引用

Research 2023年第3期2023卷 669-682页

作者： Stefan Rothe Karl-Ludwig Besser David Krause Robert Kuschmierz Nektarios Koukourakis Eduard Jorswieck Jürgen W.Czarske TU Dresden Faculty of Electrical and Computer EngineeringLaboratory of Measurement and Sensor System Technique01062 DresdenGermany TU Braunschweig Faculty of Electrical EngineeringInformation TechnologyPhysicsInstitute for Communications Technology38106 BraunschweigGermany TU Dresden Faculty of Physics01062 DresdenGermany

Multimode fibers hold great promise to advance data rates in optical communications but come with the challenge to compensate for modal crosstalk and mode-dependent losses,resulting in strong *** holographic measurement of the transmission matrix enables not only correcting distortions but also harnessing these effects for creating a confidential data connection between legitimate communication parties,Alice and *** feasibility of this physical-layer-security-based approach is demonstrated experimentally for the first time on a multimode fiber link to which the eavesdropper Eve is physically *** the proper structured light field is launched at Alice’s side,the message can be delivered to Bob,and,simultaneously,the decipherment for an illegitimate wiretapper Eve is *** a real communication scenario,we implement wiretap codes and demonstrate confidentiality by quantifying the level of *** to an uncoded data transmission,the amount of securely exchanged data is enhanced by a factor of *** complex light transportation phenomena that have long been considered limiting and have restricted the widespread use of multimode fiber are exploited for opening new perspectives on information security in spatial multiplexing communication systems.

关键词： distortion destroyed holographic

来源：评论

学校读者我要写书评

暂无评论

Towards Green AI by Reducing Training Effort of Recurrent Neural Networks Using Hyper-Parameter Optimization with Dynamic Stopping Criteria 22

Towards Green AI by Reducing Training Effort of Recurrent Ne...

引用

22nd IEEE International Symposium on Intelligent Systems and Informatics, SISY 2024

作者： Podgorelec, Vili Fister, Iztok Vrbancic, Grega University of Maribor Intelligent Systems Laboratory Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9798350385601

Neural networks have become a leading model in modern machine learning, able to model even the most complex data. For them to be properly trained, however, a lot of computational resources are required. With the carbon footprint of ever-growing adoption of neural networks in mind, an approach to reduce the required training resources would be very welcome. We designed a new training effort reduction method based on the calculation of area under the normalized loss curve and assessed it on the electricity consumption forecasting problem with the recurrent neural networks. The results show that the proposed method was able to considerably reduce the amount of computational resources, while maintaining the predictive performance, and thus contributing towards the Green AI. © 2024 IEEE.

关键词： Green AI hyper-parameter optimization machine learning neural networks resource optimization

来源：评论

学校读者我要写书评

暂无评论

The Most Expensive Museum in the World: Three Player Cooperative Game between VR and PC Platforms Investigating Empathy between Players and Historical Characters. 23

The Most Expensive Museum in the World: Three Player Coopera...

引用

2023 SIGGRAPH Asia 2023 Art Papers, SA 2023

作者： Radakulan, Vojtech Sedláček, David Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Graphics and Interaction Prague Czech Republic

ISBN: (纸本)9798400703201

The paper describes an art installation based on a local cooperative cross platform VR/PC game for three players. The story is based on the historical story of a nuclear power plant, which was built, but never turned on because of a public referendum. The game mechanics are built upon the interaction of three playable historical characters: engineer, activist, and politician. The main goal was to foster empathy in the players by replaying the game from each character's perspective. We present the story implementation, custom-made interfaces, physical setup, and an evaluation of recordings from a four-month display in a public gallery. © 2023 Owner/Author.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Network Embedding Methods: Study and Comparison

EEA - Electrotehnica, Electronica, Automatica

引用

EEA - Electrotehnica, Electronica, Automatica 2024年第4期72卷 72-78页

作者： Benbatata, Sabrina Saoud, Bilal LIMPAF laboratory Department of Computer Sciences University of Bouira Bouira10000 Algeria Electrical Engineering Department Sciences and Applied Sciences Faculty LISEA laboratory University of Bouira Bouira10000 Algeria

Graph is a powerful language that can model many systems in different fields such as information sciences, social sciences, Biology, mathematics, physics, etc. Graphs can capture very well the relationships between nodes and their structure. Representing data through graphs has some limitations and is challenging to use them like input in machine learning and deep learning models. This challenge can be overcome by using network embedding. Embedding represents a network into low-dimensional vector space. Several methods have been proposed to embed networks. Methods like DeepWalk, Node2Vec and GraphSAGE have gained traction. DeepWalk employs random walks to capture local neighborhood information, generating embeddings using skip-gram models. Node2Vec extends this by incorporating biased random walks, balancing exploration and exploitation of the network. GraphSAGE adopts a neighborhood aggregation strategy, aggregating features from a node's local graph structure through different convolutional layers. These methods facilitate downstream tasks like node classification, link prediction and clustering. Challenges include scalability to large networks, handling heterogeneous information and preserving structural characteristics. Recent advancements integrate techniques like attention mechanisms and reinforcement learning for improved embeddings. Network embedding methods continue to evolve, catering to diverse applications in social networks, biology and recommendation systems, offering insights into complex network structures. In this paper we provide networks embedding concepts and some methods. A comparison between embedding methods is presented. Embedding network methods on node classification tasks on different benchmark datasets have been conducted in order to evaluate them. Through rigorous evaluation, we assess their effectiveness in capturing latent features and improving classification accuracy across various domains. © Editura ELECTRA 2024. All rights reserved

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Dual-Mode Resonant Sectorial Monopole Antenna with Stable Backfire Gain

引用

Chinese Journal of Electronics 2024年第6期33卷 1478-1486页

作者： Feiyan JI Heng ZHANG Xiuqiong XING Wenjun LU Lei ZHU Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

A novel design approach to wideband, dual-mode resonant monopole antenna with stable, enhanced backfire gain is advanced. The sectorial monopole evolves from a linear, 0.75-wavelength electric prototype monopole under wideband dual-mode resonant operation. As theoretically predicted by the two resonant modes TE3/5,1and TE9/5,1within a 150° radiator, the operation principle is revealed at first. As have been numerically demonstrated and experimentally validated at 2.4-GHz band, the designed antenna exhibits a wide impedance bandwidth over 90.1%（i.e., 2.06–5.44 GHz）, in which the stable gain bandwidth in the backfire,-x-direction（θ = 90°, φ = 180°） with peak value of 3.2 dBi and fluctuation less than 3 dB is up to 45.3%（i.e., 3.74–5.44 GHz）. It is concluded that the stable wideband backfire gain frequency response should be owing to the high-order resonant mode in the unique sectorial monopole antennas.

关键词： Fluctuations Azimuth Prototypes Metals Resonance Frequency measurement Broadband antennas Impedance Gain Wideband

来源：评论

学校读者我要写书评

暂无评论

Fine-tuning Specialized NER Model for Symptom Extraction from Slovenian Medical Texts 9

Fine-tuning Specialized NER Model for Symptom Extraction fro...

引用

9th International Conference on Mathematics and computers in Sciences and Industry, MCSI 2024

作者： Sallauka, Rigon Arioz, Umut Mlakar, Izidor University of Maribor Faculty of Electrical Engineering and Computer Science Laboratory of Digital Signal Processing Maribor Slovenia

ISBN: (纸本)9798350377224

In this study, we aim to develop a robust model capable of accurately extracting symptoms from clinical texts written in the Slovenian language. Our methodology involves several steps to achieve this objective. Initially, we identify datasets containing clinical texts in English and select a specialized model designed for symptom extraction from these texts. Then, we annotate the datasets and undertake the translation process into Slovenian, ensuring the preservation of annotations to maintain data integrity. Utilizing the translated dataset, we proceed to fine-tune the selected model specifically for Slovenian texts. Despite our efforts, optimal performance has not yet been attained. Challenges encountered include the translation methodology employed and the architectural limitations of the chosen model, which is primarily optimized for English texts. However, ongoing efforts are underway to address these challenges and enhance the model's performance. Our study represents a step towards improving automated symptom extraction in Slovenian clinical texts, with ongoing work focused on mitigating identified issues to achieve better outcomes. © 2024 IEEE.

关键词： Machine translation

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：