检索结果-内蒙古大学图书馆

Ensemble Learning Based on Feature Selection and Distance Normalization for Enhancing Corn and Weed Classification

Journal of Computing Science and Engineering 2024年第3期18卷 152-168页

作者： Adhinata, Faisal Dharma Wahyono Sumiharto, Raden Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Faculty of Informatics Institut Teknologi Telkom Purwokerto Jawa Tengah Indonesia

Weeds need to be removed from the immediate areas surrounding crops as they compete for soil nutrients. Farmers currently clear weeds manually, which is both tiring and imprecise. Therefore, researchers have developed artificial intelligence (AI) using deep learning or non-handcrafted methods to facilitate precise detection. However, these methods have yet to achieve real-time inference speeds. Consequently, this study adopts a handcrafted approach that employs visual leaf features for classification via ensemble learning. The objective is to employ feature selection and data normalization to create an accurate and efficient machine-learning model. The experimental findings obtained in this work demonstrate that Information Gain effectively reduces features by 50%, from 22 to 11, while maintaining accuracy. Chebyshev normalization emerges as the most suitable normalization technique, as it significantly enhances classification accuracy in ensemble learning. The accuracy obtained when using histogram gradient boosting is found to be 0.92 with an inference time of 5.955 ms per image. These outcomes illustrate that handcrafted features achieve higher accuracy than non-handcrafted methods, ultimately improving efficiency and enabling real-time implementation. © 2024. The Korean Institute of Information Scientists and Engineers

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

High-Precision Antenna Modeling Using Recurrent Neural Networks with Bidirectional LSTM Layers and Dimensionality Reduction

引用

IEEE Transactions on Antennas and Propagation 2025年第6期73卷 4011-4025页

作者： Sahu, Kaustab C. Koziel, Slawomir Pietrenko-Dabrowska, Anna Reykjavik University Engineering Optimization and Modeling Center Reykjavik102 Iceland Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk80-233 Poland

This research introduces a novel methodology for high-accuracy modeling of antenna characteristics. It is centered around a recurrent neural network (RNN) optimized through Bayesian Optimization (BO). The RNN architecture includes - among others - a feature input layer, a Long Short-Term Memory (LSTM) layer, a Gated Recurrent Unit (GRU) layer, and a bidirectional LSTM layer. BO is employed to fine-tune the network's hyperparameters, such as the number of units in each layer and the learning rate. The LSTM, GRU, and bidirectional LSTM layers are designed to capture frequency-wise dependencies in antenna responses. A distinctive feature of this approach is the utilization of frequency as a sequential parameter processed by the RNN, which enhances reliability and cost efficiency. These advantages are further bolstered by dimensionality reduction techniques based on rapid global sensitivity analysis. The proposed method has undergone extensive validation across four antennas and has been compared against several benchmark methods, including kernel-based regression models and various neural networks. The results demonstrate that our surrogates achieve outstanding accuracy, significantly surpassing the benchmark, and can construct reliable metamodels even with low-cardinality training datasets. Design applications and experimental validation have also been included. © 1963-2012 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of People Swimming in Water Reservoirs with the Use of Multimodal Imaging and Machine Learning 23rd

Detection of People Swimming in Water Reservoirs with the...

引用

Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023

作者： Konert, Jakub Dradrach, Adam Rumiński, Jacek Faculty of Electronics Telecommunications and Informatics Gdańsk University of Technology Gdańsk Poland

ISBN: (纸本)9783031384295

Every year in many countries, there are fatal unintentional drownings in different water reservoirs like swimming pools, lakes, seas, or oceans. The existing threats of this type require creating a method that could automatically supervise such places to increase the safety of bathers. This work aimed to create methods and prototype solutions for detecting people bathing in water reservoirs using a multimodal imaging system and machine learning. Two types of cameras, RGB and thermal, were integrated and calibrated to form a multimodal imaging system. The system was designed and implemented to acquire real-world data for bathing people in swimming pools. The EfficientDet models were adapted and trained on collected data reaching at least 94% detection accuracy, with the highest result equal to 97.47%. The best accuracy obtained for the thermal data was lower and equal to 94.85%. However, thermal imaging allows observing scenes in low-light conditions or darkness. This could potentially highly improve the effectiveness of rescue missions, decreasing the death rates or improving the health of early rescued people. Thermal imaging could also be more acceptable regarding privacy, as high-frequency biometric features are not as easy to extract from thermal images as from high-resolution RGB images. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Developing phoneme-based lip-reading sentences system for silent speech recognition

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 129-138页

作者： Randa El-Bialy Daqing Chen Souheil Fenghour Walid Hussein Perry Xiao Omar HKaram Bo Li School of Engineering London South Bank UniversityLondonUK Faculty of Informatics and Computer Science British University in EgyptCairoEgypt School of Electronics and Informatics Northwestern Polytechnical UniversityXi'anChina

Lip-reading is a process of interpreting speech by visually analysing lip *** research in this area has shifted from simple word recognition to lip-reading sentences in the *** paper attempts to use phonemes as a classification schema for lip-reading sentences to explore an alternative schema and to enhance system *** classification schemas have been investigated,including characterbased and visemes-based *** visual front-end model of the system consists of a Spatial-Temporal(3D)convolution followed by a 2D *** utilise multi-headed attention for phoneme recognition *** the language model,a Recurrent Neural Network is *** performance of the proposed system has been testified with the BBC Lip Reading Sentences 2(LRS2)benchmark *** with the state-of-the-art approaches in lip-reading sentences,the proposed system has demonstrated an improved performance by a 10%lower word error rate on average under varying illumination ratios.

关键词： deep learning deep neural networks lip-reading phoneme-based lip-reading spatial-temporal convolution,transformers

来源：评论

学校读者我要写书评

暂无评论

Leveraging Activation Maps for Improved Acoustic Events Detection and Classification 27

Leveraging Activation Maps for Improved Acoustic Events Dete...

引用

27th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2024

作者： Szczodrak, M. Kotus, J. Szczuko, P. Szwoch, G. Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Multimedia System Department Gdansk Poland

ISBN: (纸本)9788362065486

This paper presents a novel approach to enhance the accuracy of deep learning models for acoustic event detection and classification in real-world environments. We introduce a method that leverages activation maps to identify and address model overfitting, combined with an expert-knowledge-based event detection algorithm for data pre-processing. Our approach significantly improved classification performance, increasing the F1 score from 0.65 in the baseline model to 0.96 in the optimized model. The method was evaluated on a diverse validation dataset of 100 samples per each of 8 classes of urban acoustic events, including gunshots, explosions, and screams. Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations confirmed that our enhanced model focuses on relevant signal components, reducing reliance on irrelevant background information. Additionally, our expert detection module enables efficient online processing by bypassing the classifier for non-event signals. This research demonstrates the effectiveness of combining explainable AI techniques with domain expertise to improve the robustness and efficiency of acoustic event classification systems. © 2024 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing Critical Success Factors of IoT-Enabled Green Supply Chain Management Using Bipolar Neutrosophic-DEMATEL

引用

Neutrosophic Sets and Systems 2023年 55卷 132-159页

作者： Saleh, Wafaa A. Abdelkaderb, Sherine M. Rashada, Heba Abdelgawad, Amal Department of Decision Support Faculty of Computers and Informatics Zagazig University Egypt Department of Computers and Systems Electronics Research Institiute Egypt

Recent Supply Chain Management Systems (SCMS) that is based on newer technologies are intelligent enough to lower costs, improve product quality, and speed up the decision-making process in the manufacturing operation. The reduction of overall environmental impact, is a goal of the Green Supply Chain Management (GSCM) systems. It is achieved by integrating environmentally friendly processes into SCMS. The main and most crucial role in achieving the goal of sustainable development is played by the GSCM practices. It is proved that, the adoption of IoT technology into the GSCM systems can increase its performance and productivity. The goal of this paper is to examine the Critical Success Factors (CSFs) for the efficient adoption of IoT and green solutions throughout the supply chain for the manufacturing sector. As a result of pressure from the government and increased customer awareness of environmental issues, manufacturers are currently focusing on GSCM that is enabled by IoT gadgets. The selection and prioritization of IoTenabled GSCM success variables is performed, in this paper, using bipolar neutrosophic-DEMATEL approach. © 2023, Neutrosophic Sets and Systems. All Rights Reserved.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Evaluation of ChatGPT Applicability to Learning Quantum Physics 16

Evaluation of ChatGPT Applicability to Learning Quantum Phys...

引用

16th International Conference on Signal Processing and Communication System, ICSPCS 2023

作者： Stefanska, Agata Stefański, Tomasz P. Czubenko, Michal Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk Poland

ISBN: (纸本)9798350333510

ChatGPT is an application that uses a large language model. Its purpose is to generate answers to various questions as well as provide information, help solve problems and participate in conversations on a wide range of topics. This application is also widely used by students for the purposes of learning or cheating (e.g., writing essays or programming codes). Therefore, in this contribution, we evaluate the ability of ChatGPT to answer questions in quantum physics. That is, we develop a benchmark consisting of ten questions, whose difficulty is measured on a ten-grade scale. Then ChatGPT answers are evaluated and discussed. In this way, we can measure how well quantum-physics information is processed by this application. Our results demonstrate that ChatGPT does not notice subtle differences between physical terms, and can provide wrong answers to quantum-physics-related questions. It can also provide false mathematical formulas, claim that they are correct and confirm its answers. Note that this AI application is not sure of its answers, and in seven cases it apologizes for the first answer when a user has negated it. To sum up, AI represented by ChatGPT is only able to support students in the process of learning quantum physics at the fundamental level. Moreover, during collective exams in the future, where cheating and the use of AI by students may occur, exam questions should not be descriptive, but should be focused on solving computational problems. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Application of AI-Enhanced Image Processing Methods for Educational Applied Physics Experiments 15

Application of AI-Enhanced Image Processing Methods for Educ...

引用

15th International Scientific and Practical Conference on Environment. Technology. Resources, ETR 2024

作者： Laukhammer, Eivin Mačerauskas, Eugenijus Lučun, Andžej Kozič, Antoni Tumasonis, Romanas Vilnius Kolegija Faculty of Electronics and Informatics J. Jasinskio st. 15 VilniusLT-01111 Lithuania Vilnius Kolegija Faculty of Electronics and Informatics J. Jasinskio st. 15 VilniusLT-01111 Lithuania

ISBN: (纸本)9781713899570

This article examines the use of an AI-powered automated image analysis system. The system's purpose is to enhance the workflow of students during applied physics laboratory experiments, helping them analyze images and perform accurate microobject counting. On the software side, the system incorporates machine learning algorithms for visual processing applications using Python and its’ extension libraries – CV2, Tensorflow, Keras, SkLearn etc.. The hardware consists of a camera and microprocessor, which, in conjunction with the image processing software, perform microobject recognition and counting in real-time. The goal is to automate applied physics laboratory experiments in which the counting of microobjects, be it organic or human-made, is usually done manually. During these applied physics laboratory experiments and with the aid of this system, students are exposed to a modern workflow, further preparing them for future work environments, teaching them about process automation, and further increasing their interest in micro-scale related science subjects. Automation using image processing technology combined with automatic data logging from images allows for fast and accurate micro-object counting. © 2024 Eivin Laukhammer, Eugenijus Mačerauskas, Andzej Lučun, Antoni Kozič, Romanas Tumasonis.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Understanding Electrochemical Migration Behavior in Fe2O3-Enhanced SAC Lead-Free Alloys 30

Understanding Electrochemical Migration Behavior in Fe2O3-En...

引用

30th IEEE International Symposium for Design and Technology in Electronic Packaging, SIITME 2024

作者： Gharaibeh, Ali Dayoub, Ali Medgyes, Balint Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Electronics Technology Budapest Hungary

ISBN: (纸本)9798331539511

The effect of ferric oxide (Fe2/ O3) nanoparticle incorporation on the reliability of SAC305 solder alloy, in terms of electrochemical migration (ECM) behavior, was studied using water drop (WD) tests performed in a 0.1 M Na_{2 SO_{4 solution with a 10 VDC. The incorporation of Fe2O3 nanoparticles at different weight percentages (\mathbf{0. 1% and 0.25%) into SAC305, referred to as nanocomposite SAC305-x (0.1,0.25 wt.% Fe2O3), resulted in a significant shorter mean time to failure (MTTF) compared to pure SAC305. This result indicates that the SAC305 alloy with incorporated Fe2O3 nanoparticles exhibits lower ECM resistance than undoped SAC305. A comprehensive surface analysis was conducted on the dendrites formed during the WD test for nanocomposite solders in various solutions, including 0.1 M Na_{2 SO_{4, 10 mM HO2, 10 mM HCl, and 10 mM HNO3. In all cases, the dendrite morphology predominantly displayed straight, perpendicular branching, resembling a fishbone-like structure. Elemental composition analysis consistently identified Sn as the dominant element in the dendrites, indicating that the ECM behavior of the nanocomposite solders is still primarily governed by the dissolution of Sn. © 2024 IEEE.

关键词： Lead alloys

来源：评论

学校读者我要写书评

暂无评论

Experimental Framework for Secure Post-Quantum TLS Client-Server Communication 66

Experimental Framework for Secure Post-Quantum TLS Client-Se...

引用

66th International Symposium ELMAR, ELMAR 2024

作者： Kupcova, Eva Simko, Jozef Pleva, Matus Drutarovsky, Milos Technical University of Kosice Faculty of Electrical Engineering and Informatics Department of Electronics and Multimedia Telecommunications Kosice Slovakia

ISBN: (纸本)9798350375411

This article presents the development of an experimental framework for secure communication between client and server. The framework is based on the TLS 1.3 protocol and utilizes post-quantum cryptography. This framework aims to enable our further development in the field of post-quantum cryptography through the integration and testing of post-quantum algorithms, as well as the generation of corresponding certificates for our future sensor nodes. This framework has the potential to provide a platform for experimenting with new security technologies and contribute to the future development of cryptographic systems in the context of wireless communication, the Internet of Things, and sensor nodes. © 2024 IEEE.

关键词： Quantum cryptography

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：