检索结果-内蒙古大学图书馆

DTS-TSCH: Adaptive Thompson sampling for channel estimation in TSCH networks for IIoT

Scientific African 2025年 29卷

作者： Adugna Necho Mulatu Marco Zennaro Fikreselam Gared Prabhakar T V Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Electronic Systems Engineering Indian Institute of Science (IISc) Bengaluru India The Abdus Salam International Centre for Theoretical Physics (ICTP) Trieste Italy

Real-time data transmission is crucial for the Industrial Internet of Things (IIoT), where communication networks must ensure high reliability and deterministic behavior. The IEEE 802.15.4e standard introduced the Time Slotted Channel Hopping (TSCH) MAC mode, which enhances network reliability through multi-channel access and periodic channel hopping. While channel hopping can help mitigate external interference, it does not always ensure optimal channel quality, leading to packet loss and unreliable communication. This is often insufficient due to overlapping channels in coexisting networks. Retransmitting lost packets on different physical channels is also inadequate because of potential interference from these networks. Existing link quality assessments often fall short in multi-channel scenarios due to their inability to adapt to changing interference patterns. These approaches do not cope with the complexity and dynamic nature of wireless conditions, especially in environments characterized by high mobility and time-varying interference. This results in more retransmissions, increased delays, and degraded reliability. To address these limitations, we propose an adaptive channel estimation model that selects channels with high link quality, thereby meeting the stringent requirements of IIoT. The proposed approach leverages Dynamic Thompson Sampling (DTS), a powerful multi-armed bandit (MAB) technique that optimally balances exploration and exploitation to improve channel selection performance. The DTS-TSCH model significantly enhances communication reliability while reducing the negative impact of poor-quality channels by leveraging online learning mechanisms. The model effectively identifies channels with good link quality, continuously learning from their behavior and making informed selections based on recent assessment values. This adaptive approach surpasses existing methods by responding to real-time data and optimizing channel selection dynamically. The r

关键词： Channel estimation model Channel selection DTS-TSCH IIoT TSCH

来源：评论

学校读者我要写书评

暂无评论

ORCA Optimization Algorithm: A New Meta-Heuristic Tool for Complex Optimization Problems

ORCA Optimization Algorithm: A New Meta-Heuristic Tool for C...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： Noorbakhsh Amiri Golilarz Hui Gao Abdoljalil Addeh Saeid Pirasteh School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Electrical and Computer Engineering Babol Noshirvani University of Technology Babol Iran Faculty of Geosciences & Environmental Engineering Southwest Jiaotong University Chengdu China

ISBN: (数字)9781665405058

ISBN: (纸本)9781665405065

In this paper, a new meta-heuristic algorithm called Orca Optimization Algorithm (OOA) is proposed for complex and nonlinear optimization problems, especially practical engineering problems. This developed method is based on unique wave-washing orcas hunting technique. In the OOA, different random candidates (orcas) implement the cunning tactic of regularly hunting in packs and building waves to wash seals off drifting piece of ice. Application of the proposed algorithm on some benchmark functions including Schaffer, Griewank, Ackley, and Rosenbrock proved its excellent capability in comparison with other similar algorithms such as Genetic Algorithm (GA), Flower Pollination Algorithm (FPA), Harris Hawk Optimization (HHO) algorithm, and Imperialist Competitive Algorithm (ICA). Moreover, the performance of the proposed optimization algorithm applied on real engineering problems. In this experiment, OOA applied for online parameter estimation of photovoltaic modules equivalent circuit and optimal design of brushless direct current (BLDC) motor. The numerical analysis and obtained simulation results of the experiments showed the excellent performance of OOA.

关键词： Optimization Ice Seals Integrated circuit modeling Genetic algorithms Equivalent circuits Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of deep learning and machine learning techniques for forecasting new malaria cases in Cameroon's Adamaoua region

引用

Intelligence-Based Medicine 2025年 11卷 100220-100220页

作者： Naroum, Esaie Maka, Ebenezer Maka Abboubakar, Hamadjam Dayang, Paul Bamana, Appolinaire Batoure Garga, Benjamin Daouda, Hassana Daouda Bakouri, Mohsen Khan, Ilyas University of Ngaoundéré Department of Mathematics and computer Science Faculty of Science P.O. Box 455 Ngaoundéré Cameroon University of Douala National Higher Polytechnic School Department of Computer Engineering and Telecommunications P.O. Box 2701 Douala Cameroon University of Ngaoundéré University Institute of Technology Department of Computer Engineering P.O. Box 455 Ngaoundéré Cameroon University of Ngaoundéré Laboratory of Analysis Simulation and Test (LASE) P.O. Box 455 Ngaoundéré Cameroon University of Ngaoundéré School of Geology and Mining Engineering Department Applied Mathematics and Computer Science P.O. Box 115 Meiganga Cameroon University of Ngaoundéré ENSAI Department of Electrical Electronic and Automatic Engineering P.O. Box 455 Ngaoundéré Cameroon Majmaah University College of Applied Medical Science Department of Medical Equipment Technology Al-Majmaah 11952 Saudi Arabia Department of Mathematics College of Science Al-Zulfi Majmaah University Al-Majmaah 11952 Saudi Arabia

The Plasmodium parasite, which causes malaria is transmitted by Anopheles mosquitoes, and remains a major development barrier in Africa. This is particularly true considering the conducive environment that promotes the spread of malaria. This study examines several machine learning approaches, such as long short term memory (LSTM), random forests (RF), support vector machines (SVM), and data regularization models including Ridge, Lasso, and ElasticNet, in order to forecast the occurrence of malaria in the Adamaoua region of Cameroon. The LSTM, a recurrent neural network variant, performed the best with 76% accuracy and a low error rate (RMSE = 0.08). Statistical evidence indicates that temperatures exceeding 34 degrees halt mosquito vector reproduction, thereby slowing the spread of malaria. However, humidity increases the morbidity of the condition. The survey also identified high-risk areas in Ngaoundéré Rural and Urban and Meiganga. Between 2018 and 2022, the Adamaoua region had 20.1%, 12.3%, and 10.0% of malaria cases, respectively, in these locations. According to the estimate, the number of malaria cases in the Adamaoua region will rise gradually between 2023 and 2026, peaking in 2029 before declining in 2031. © 2025 The Authors

关键词： Adamaoua-Cameroon Deep learning Machine learning Malaria Metric evaluation Time-series forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhanced geometric properties prediction for carrots in motion using a Multi-task YOLO-based Linked Network (YL-Net)

引用

computers and electronics in Agriculture 2025年 237卷

作者： Yi-Liang Wu Sze-Teng Liong Gen-Bing Liong Jun-Hui Liang Y.S. Gan Department of Electronic Engineering Feng Chia University Taichung 40724 Taiwan ROC Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia School of Architecture Feng Chia University Taichung 40724 Taiwan ROC

With a growing shortage of manual labor in agriculture, there is an urgent need for efficient and automated solutions to address the complex challenges of inspecting and classifying agricultural products, such as carrots, which exhibit irregular shapes, occlusions, and high variability in geometric properties. This study introduces a novel Multi-task YOLO-based Linked Network (YL-Net) designed to estimate the geometric properties of carrots in motion, including width, length, volume, and mass. The proposed network integrates RGB-D input with decoupled multi-task learning to simultaneously perform instance segmentation and regression. Building upon our previous work, the enhanced framework presented herein achieves outstanding performance, with MAPE values below 2.5% for all estimated properties. When aggregating multi-view data from a rolling conveyor system, the accuracy further improves, yielding MAPE values below 2%. In terms of detection, the model demonstrates excellent performance, achieving a mean F1-score of 98.78% and an instance segmentation IoU of 89.25%. To evaluate its scalability, the system was deployed on an NVIDIA Jetson Orin Nano, where it achieved a real-time processing speed of 80 FPS. Beyond carrots, the proposed approach can be extended to inspect other agricultural products, such as potatoes and sweet potatoes, where geometric properties are essential for sorting and grading. This work provides a scalable and transferable solution for automated agricultural inspection, laying a robust foundation for broader applications in smart farming, industrial automation, and food quality control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing

引用

Informatics in Medicine Unlocked 2021年 26卷 100709页

作者： Hasan, Md. Kamrul Jawad, Md. Tasnim Hasan, Kazi Nasim Imtiaz Partha, Sajal Basak Masba, Md. Masum Al Saha, Shumit Moni, Mohammad Ali Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna-9203 Bangladesh Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna-9203 Bangladesh Department of Electronics and Communication Engineering Khulna University of Engineering & Technology Khulna-9203 Bangladesh Department of Computer Science & Engineering Pabna University of Science and Technology Pabna-6600 Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia QLD 4072 Australia

The novel COVID-19 is a global pandemic disease overgrowing worldwide. computer-aided screening tools with greater sensitivity are imperative for disease diagnosis and prognosis as early as possible. It also can be a helpful tool in triage for testing and clinical supervision of COVID-19 patients. However, designing such an automated tool from non-invasive radiographic images is challenging as many manually annotated datasets are not publicly available yet, which is the essential core requirement of supervised learning schemes. This article proposes a 3D Convolutional Neural Network (CNN)-based classification approach considering both the inter-and intra-slice spatial voxel information. The proposed system is trained end-to-end on the 3D patches from the whole volumetric Computed Tomography (CT) images to enlarge the number of training samples, performing the ablation studies on patch size determination. We integrate progressive resizing, segmentation, augmentations, and class-rebalancing into our 3D network. The segmentation is a critical prerequisite step for COVID-19 diagnosis enabling the classifier to learn prominent lung features while excluding the outer lung regions of the CT scans. We evaluate all the extensive experiments on a publicly available dataset named MosMed, having binary- and multi-class chest CT image partitions. Our experimental results are very encouraging, yielding areas under the Receiver Operating Characteristics (ROC) curve of 0.914±0.049 and 0.893±0.035 for the binary- and multi-class tasks, respectively, applying 5-fold cross-validations. Our method's promising results delegate it as a favorable aiding tool for clinical practitioners and radiologists to assess COVID-19. © 2021

关键词： 3D convolutional neural network 3D patches COVID-19 Progressive resizing Volumetric chest CT scans

来源：评论

学校读者我要写书评

暂无评论

Applying classical control techniques to quantum systems: Entanglement versus stability margin and other limitations

arXiv

引用

arXiv 2022年

作者： Weidner, Carrie A. Schirmer, S.G. Langbein, F.C. Jonckheere, E. The Quantum Engineering Technology Laboratories H. H. Wills Physics Laboratory Department of Electrical and Electronic Engineering University of Bristol BristolBS8 1FD United Kingdom The Faculty of Science & Engineering Swansea University SwanseaSA2 8PP United Kingdom The School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom The Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States

Development of robust quantum control has been challenging and there are numerous obstacles to applying classical robust control to quantum system including bilinearity, marginal stability, state preparation errors, nonlinear figures of merit. The requirement of marginal stability, while not satisfied for closed quantum systems, can be satisfied for open quantum systems where Lindbladian behavior leads to non-unitary evolution, and allows for nonzero classical stability margins, but it remains difficult to extract physical insight when classical robust control tools are applied to these systems. We consider a straightforward example of the entanglement between two qubits dissipatively coupled to a lossy cavity and analyze it using the classical stability margin and structured perturbations. We attempt, where possible, to extract physical insight from these analyses. Our aim is to highlight where classical robust control can assist in the analysis of quantum systems and identify areas where more work needs to be done to develop specific methods for quantum robust control. Copyright © 2022, The Authors. All rights reserved.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis using Digitized Images of FNA Breast Biopsy and Optimized Neurofuzzy System

Breast Cancer Diagnosis using Digitized Images of FNA Breast...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： Jalaluddin Khan Noorbakhsh Amiri Golilarz Jian Ping Li Paidar Kuzeli Abdoljalil Addeh Amin Ul Haq School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Amirkabir University of Technology Tehran Iran Faculty of Electrical and Computer Engineering Babol Noshirvani University of Technology Babol Iran

ISBN: (数字)9781665405058

ISBN: (纸本)9781665405065

Breast cancer is the second highest cause of cancer death among women all around the world, especially between the ages of 40 and 65. Early detection of breast cancer tumor type, benign or malignant, has remained a big challenge for physicians and radiologists. By timely identifying the tumor and knowing its type, it can allow physicians to conduct the treatment in the right direction and to take appropriate medications for that type of tumor. Therefore, it is highly important to know the type of tumor accurately to save the patient's life. This paper proposes an intelligent diagnosis method for breast cancer tumor type detection and classification based on fine needle aspirate (FNA) of a breast mass and optimized fuzzy sets. The developed method applied image processing and feature selection techniques to analyze the digitized image of a FNA. In the developed method, nine features computed from a digitized image of a FNA of a breast mass are uses as the initial input of neuro-fuzzy system. In the proposed method, we applied the Association Rules (AR) to find the most informative and effective features of the extracted features. Moreover, in order to advance the act of neuro-fuzzy system, Chaotic Bat Optimization Algorithm (CBOA) is used as learning algorithm. The proposed method is tested on Breast Cancer Wisconsin (Diagnostic) data set. The obtained numerical analysis showed that the developed diagnostic system has excellent performance and high degree of precision.

关键词： Breast cancer Classification algorithms Tumors Feature extraction Breast Training Optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Direction of Arrival Estimation Algorithms for 5G Network and Beyond

Adaptive Direction of Arrival Estimation Algorithms for 5G N...

引用

International Conference on computer, Control, Electrical, and electronics engineering (ICCCEEE)

作者： Adam Mohamed Ahmed Abdo Aamer Mohamed Huroon Mohamed Mohamed H. M. Nerma Sara Yahia Altahir Mohamed Adam Osman Ahmed Mohammed Fculty of Engineering Science University of Nyala Nyala Sudan Institute of Electronic Engineering National Chiao Tung University Taiwan Fculty of Computer and Information Technology Tabuk University Tabuk Kingdom of Saudi Arabia College of Engineering Sudan University of Sceince and Technology Khartoum Sudan Faculty of Engineering Sudan International University Khartoum Sudan Nyala Technical Collage Nyala Sudan

Multiuser-multiple input multiple output (MU-MIMO) systems can provide a substantial performance for cellular networks by applying direction of arrival (DOA) technique, in which the direction of sidelobe signals can be estimated. Therefore, this paper presents a different adaptive DOA algorithms where the performance of communication networks can be enhanced, in the meantime the minimizing interferences. Meanwhile, The DOA algorithm such as multi signal classification (MUSIC), minimum norm (Min-Norm), minimum variance distortionless response (MVDR) and Bartlett algorithms are studied and compared extensively regarding the estimation angles and peak power spectrum. In this regard, uniform linear array (ULA) antenna is employed to construct the weight vector for incoming sensor signals. Furthermore, this paper compares the DOA algorithms concerning the number of antenna elements as well as the incoming signal angles. The simulation results approve that the algorithms are likely have the same performance in accuracy of scanning angles. However, it is realized that all algorithms have different peak power values in order to beamwidth. Moreover, the results indicate that the DOA algorithms with the different number of antenna elements have a significant impact on a directivity and gain. Hereafter, this work can be extended to higher frequency of mmWave communication with massive number of antenna, which can meet the requirement of fifth generation (5G) network.

关键词： Wireless communication Direction-of-arrival estimation Adaptive systems 5G mobile communication Simulation Classification algorithms Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Dual-band mimo antenna system for next generation smartphone applications

Dual-band mimo antenna system for next generation smartphone...

引用

1st International Multi-Disciplinary Conference Theme: Sustainable Development and Smart Planning, IMDC-SDSP 2020

作者： Ullah, Atta Parchin, Naser Ojaroudi Melha, Mohammed S Bin Ullah, Rahat Al Abdullah, Ali A. S. Kosha, Jamal Elkhazmi, E. Abd-Alhameed, Raed A. Faculty of Engineering and Informatics University of Bradford BradfordBD7 1DP United Kingdom School of Computer Science Liverpool John Moores University United Kingdom College of Electronics Engineering Nineveh University Mosul Iraq Electronic Technology College Engineering & Information Tech Research Center Bani walid Libya

ISBN: (纸本)9781631902611

In this new article, a different model of dual-band MIMO compact antenna array is proposed for the upcoming fifth generation smartphone mobile terminal. The antenna conatins eight antenna elements covering dual frequency rang including 3.18-3.96 GHz and 4.95-5.52 GHz of sub 6 GHz 5G spectrums. The elements are fed by modified Fshaped microstrip feeding lines. Essential characteristics of the suggested model are examined. It proposes adequate S-parameters, suitable isolation, sufficient radiation analysis, and efficiency. At 3.6 GHz the Ant 5 has maximum return loss of-25dB while Ant 7 has maximum return loss of-26dB at 5.2 GHz of the proposed dual band frequency of 5G smartphones. © 2020 EAI.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Secondary spin current driven efficient THz spintronic emitters

arXiv

引用

arXiv 2022年

作者： Agarwal, Piyush Yang, Yingshu Medwal, Rohit Asada, Hironori Fukuma, Yasuhiro Battiato, Marco Singh, Ranjan Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 21 Nanyang Link Singapore637371 Singapore Center for Disruptive Photonic Technologies The Photonics Institute Nanyang Technological University Singapore639798 Singapore Department of Physics Indian Institute of Technology Uttar Pradesh Kanpur208016 India Department of Electronic Devices and Engineering Graduate School of Science and Engineering Yamaguchi University Ube755-8611 Japan Department of Physics and Information Technology Faculty of Computer Science and System Engineering Kyushu Institute of Technology Iizuka820-8502 Japan

Femtosecond laser-induced photoexcitation of ferromagnet (FM)/heavy metal (HM) heterostructures have attracted attention by emitting broadband terahertz frequencies. The phenomenon relies on the formation of ultrafast spin current, which is largely attributed to the direct photoexcitation of the FM layer. However, we reveal that during the process, the FM layer also experiences a secondary excitation led by the hot electrons from the HM layer that travel across the FM/HM interface and transfer additional energy in the FM. Thus, the generated secondary spins enhance the total spin current formation and lead to amplified spintronic terahertz emission. The results also emphasize the significance of the secondary spin current, which even exceeds the primary spin currents when FM/HM heterostructures with thicker HM are used. An analytical model is developed to provide deeper insights into the microscopic processes within the individual layers, underlining the generalized ultrafast superdiffusive spin-transport mechanism. Copyright © 2022, The Authors. All rights reserved.

关键词： Hot electrons

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：