检索结果-内蒙古大学图书馆

Ensemble learning with temporal fusion for human activity recognition using model-based augmentation

学校读者我要写书评

暂无评论

Biomedical Signal Processing and Control 2025年 110卷

作者： Abdelghani Dahou Mohammed A.A. Al-qaness Mohamed Abd Elaziz Ahmed M. Helmi Nafissa Toureche Trouba Ahmed Ewess Zhonglong Zheng School of Computer Science and Technology Zhejiang Normal University Jinhua 321004 China Zhejiang Institute of Photoelectronics Jinhua Zhejiang 321004 China Department of Mathematics and Computer Science Faculty of Material Sciences Mathematics and Computer Science University of Ahmed Draia Adrar 01000 Algeria College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua 321004 China Department of Mathematics Faculty of Science Zagazig University Zagazig 44519 Egypt Faculty of Computer Science and Engineering Galala University Suez 435611 Egypt Artificial Intelligence Research Center (AIRC) College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Computer Engineering College of Engineering and Information Technology Buraydah Private Colleges Buraydah 51418 Saudi Arabia Department of Computer and Systems Engineering Faculty of Engineering Zagazig University Zagazig 44519 Egypt Department of Naural Science Faculty of Science and Technology University of Ahmed Draia Adrar 01000 Algeria Department of Computer Damietta University Damietta Egypt

Human Activity Recognition (HAR) is crucial for biomedical signal processing as it provides contextual information that enhances the interpretation and accuracy of physiological data. By identifying and classifying human activities, HAR enables the differentiation between normal and abnormal physiological states. This research addresses key challenges in HAR, including the lack of data diversity, the presence of noise, and imbalanced datasets, which prevent the development of robust and accurate HAR models. To overcome these challenges, we propose a novel ensemble framework, MK-WaveNet, designed to improve the generalization and accuracy of HAR systems. Our framework integrates a model-based data augmentation backbone, termed the Inverse Wavelet Augmented Convolutional Network (IWACN), to enhance feature representation and mitigate data imbalance issues. Additionally, a novel Minkowski distance-based temporal fusion algorithm is introduced to effectively merge the outputs of ensemble models, enhancing the overall performance of the framework. Comprehensive experiments conducted on four benchmark datasets (UCI-HAR, PAMAP2, DAPHNET, and MobiAct) and different backbones demonstrate the efficacy of the proposed framework in addressing the challenges of HAR. MK-WaveNet achieved F1-scores of 98.32% on UCI-HAR, 92.21% on PAMAP2, 94.83% on DAPHNET, and 98.86% on MobiAct. The results demonstrate that our proposed framework, alongside its backbones, sets a new benchmark by outperforming existing state-of-the-art models across all considered datasets.

关键词： Biomedical signal processing Deep learning Ensemble learning Human activity recognition (HAR) Temporal fusion Wearable sensors

Performance Analysis of QoS in MANET based on IEEE 802.11b

学校读者我要写书评

暂无评论

Performance Analysis of QoS in MANET based on IEEE 802.11b

2020 IEEE International Conference for Innovation in technology, INOCON 2020

作者： Hamdi, Mustafa Maad Mustafa, Ahmed Shamil Mahdi, Hussain Falih Abood, Mohammed Salah Kumar, Chanakya Al-Shareeda, Mahmood A. Al-Maarif University College Department of Computer Engineering Techniques Al-Anbar Iraq Faculty of Engineering University of Diyala Computer Engineering Department Baquba Diyala Province Iraq School of Information and Communication Engineering Beijing Institute of Technology Dept. of Information and Electronic Engineering Beijing100081 China Siddhant College of Engineering Dept. of Electronics and Telecommunication Engineering Pune India University Sains Malaysia Pulau Pinang Malaysia

ISBN: (纸本)9781728197449

Ad hoc wireless networks have gained worldwide attention from both academic groups and individual consumers in recent years. There are many very tiny autonomous networking, connectivity, and sensing systems with minimal energy and computational resources that function together to accomplish a big sensing mission. Wireless sensor systems include multiple sensing devices, some computing technology, and limited power supplies connectivity and processing capabilities that jointly serve a major sensing mission. Wireless sensor networks focused on IEEE802.11b pose a few concerns such as battery scavenging for a limited power source. Therefore, the proper functioning of such a device relies on wireless motes 'resources. In this paper, two theoretical models showing and forecasting the QoS as regards performance. The performance of star topology is 15 percent better than the grid topology in throughput. while the average end-to-end delay record is 17.25 ms and 76.25 ms respectively for star network topology and grid networks topology. The jitter decreases with a growing data rate of (1 to 11) Mbps in grid and star topology, the average jitter in star topology less than in grid in all tests. in terms of energy, in a star network, the average energy usage was 0.065 mWh while the average in grid record 0.045 mWh. These two distinct IEEE 802.11b network architectures are cluster-based and grid-based and are validated using simulators Qual-Net. © 2020 IEEE.

关键词： Jitter

Hexagonal Resonator Loaded Star Shaped Polarization Insensitive Compact Broadband Zero Indexed Nano-Meta Absorber for Optical Region Applications: A Numerical Approach

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Samsuzzaman, MD. Hossain, Ismail Hoque, Ahasanul Islam, Mohammad Tariqul Almutairi, Ali F. Universiti Kebangsaan Malaysia UKM Selangor Bangi43600 Malaysia Faculty of Computer Science and Engineering Patuakhali Science and Technology University Bangladesh Electrical Engineering Department Kuwait University Kuwait City13060 Kuwait Dept. of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Malaysia

Broadband response metamaterial absorber (MMA) remains a challenge among researchers. A nanostructured new Zero Indexed Metamaterial (ZIM) absorber is presented in this study, which is constructed with a hexagonal shape resonator for the optical region applications. The design consists of a resonator and dielectric layers made with tungsten and quartz (Fused), respectively. The proposed absorbent exhibits average absorption of more than 0.8972 (89.72%) within the visible wavelength of 450-600 nm and almost perfect absorption 0.99 (99%) at 458.54 nm. Based on computational analysis, the proposed absorber can be characterized as Zero Indexed Metamaterial. The developments of ZIM absorbers have demonstrated plasmonic resonance characteristics and a perfect impedance match. The incidence obliquity in typically the range of 0°–90° both in TE and TM mode with maximum absorbance is more than 0.8972 (~89.72%) and up to 35° angular stability,which is suitable for solar cell applications, like exploiting solar energy. The proposed structure prototype is designed and simulated by a study of microwave technology numerical computer simulation (CST) tools. Finite integration technique (FIT) and finite element method (FEM) is performed to data analysis in CST software, and HFSS also helps validate the numerical data of the proposed ZIM absorber. The proposed MMA design is appropriate for substantial amounts of absorption, wide-angle stability, absolute invisible layers, magnetic resonance imaging (MRI), color images, and thermal imaging applications. © 2021, CC BY.

关键词： Polarization

Local Neighbor Propagation Embedding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Shenglan Yu, Yang School of Computer Science and Technology Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Liaoning116024 China

Manifold Learning occupies a vital role in the field of nonlinear dimensionality reduction and its ideas also serve for other relevant methods. Graph-based methods such as Graph Convolutional Networks (GCN) show ideas in common with manifold learning, although they belong to different fields. Inspired by GCN, we introduce neighbor propagation into LLE and propose Local Neighbor Propagation Embedding (LNPE). With linear computational complexity increase compared with LLE, LNPE enhances the local connections and interactions between neighborhoods by extending 1-hop neighbors into n-hop neighbors. The experimental results show that LNPE could obtain more faithful and robust embeddings with better topological and geometrical properties. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

Deep Learning for Brain Age Estimation: A Systematic Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tanveer, M. Ganaie, M.A. Beheshti, Iman Goel, Tripti Ahmad, Nehal Lai, Kuan-Ting Huang, Kaizhu Zhang, Yu-Dong Ser, Javier Del Lin, Chin-Teng Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Biomedical Imaging Lab National Institute of Technology Assam Silchar788010 India Department of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Data Science Research Center Duke Kunshan University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Derio48160 Spain Bilbao48013 Spain School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Intelligent Computing: The Latest Advances, Challenges and Future

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Shiqiang Yu, Ting Xu, Tao Chen, Hongyang Dustdar, Schahram Gigan, Sylvain Gunduz, Deniz Hossain, Ekram Jin, Yaochu Lin, Feng Liu, Bo Wan, Zhiguo Zhang, Ji Zhao, Zhifeng Zhu, Wentao Chen, Zuoning Durrani, Tariq S. Wang, Huaimin Wu, Jiangxing Zhang, Tongyi Pan, Yunhe Zhejiang Lab Hangzhou China TU Wien Austria Sorbonne University Paris France Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Department of Electrical and Computer Engineering University of Manitoba Manitoba Canada Faculty of Technology Bielefeld University Bielefeld Germany Chinese Academy of Engineering Beijing China Department of Electronic and Electrical Engineering University of Strathclyde Glasgow United Kingdom National University of Defense Technology Changsha China National Digital Switching System Engineering & Technological R&D Center Zhengzhou China Materials Genome Institute Shanghai University Shanghai China Zhejiang University Hangzhou China

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

Deep Learning Methods for Calibrated Photometric Stereo and Beyond

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ju, Yakun Lam, Kin-Man Xie, Wuyuan Zhou, Huiyu Dong, Junyu Shi, Boxin School of Electrical and Electronic Engineering Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong The Research Institute for Future Media Computing Shenzhen University Shenzhen China The Department of Informatics University of Leicester Leicester United Kingdom The Faculty of Information Science and Engineering The Institute for Advanced Ocean Study Ocean University of China Qingdao China The National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models. Copyright © 2022, The Authors. All rights reserved.

关键词： Light sources

Terahertz Metamaterial Absorber for Microorganism and Pesticide Detection Applications

学校读者我要写书评

暂无评论

Optik 2025年

作者： Muhammad Amir Khalil Mohammad Tariqul Islam Mohamad A. Alawad Mohamed Ouda Yazeed Alkhrijah Phumin Kirawanich Naveed Ur Rehman Junejo Abdul Waheed Khawaja Faculty of Engineering Multimedia University (MMU)63100 Cyberjaya Selangor Malaysia Department of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment University Kebangsaan Malaysia Bangi 43600 Malaysia Department of Electrical Engineering Faculty of Engineering Mahidol University Salaya Nakhon Pathom 73170 Thailand Department of Electrical Engineering College of Engineering Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudia Arabia Electrical Engineering Technology College of Engineering & Technology University of Doha for Science and Technology 24449 Doha Qatar Department of Computer Engineering The University of Lahore Lahore 54000 Punjab Pakistan Department of Electrical Engineering Faculty of Engineering & Technology Bahauddin Zakariya University Multan 60800 Pakistan

This study investigates a metamaterial absorber based on concentric square and octagon structures aimed at improving the detection of microorganisms and pesticides. The absorber achieves perfect absorption with a single resonance peak and a 100% absorption rate. The sensor's effectiveness is further analyzed by varying the refractive index and thickness of the analyte layer, which results in exceptional sensitivity. The sensor demonstrates a 0.44 THz/RIU sensitivity within a refractive index range of 1.3 to 2.08 RI. The sensor is particularly effective in detecting pesticides and bacteria, with a notable 48 MHz frequency shift observed for pesticide detection, which has not been documented in previous studies. This significant shift makes the sensor especially useful for agricultural and food industry applications and other chemical and biological sensing domains.

关键词：

Exergy graph-based fault detection and isolation of a gas-to-liquids process

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第2期53卷 13674-13681页

作者： Sarita Greyling George van Schoor Kenneth Richard Uren Henri Marais School of Electrical Electronic and Computer Engineering Faculty of Engineering North-West University Potchefstroom 2531 South Africa Unit for Energy and Technology Systems Faculty of Engineering North-West University Potchefstroom 2531 South Africa

With the sheer size of modern process plants, the Fault Detection and Isolation (FDI) field continues to gain popularity. FDI is a sophisticated concept which aims to detect and isolate anomalies that occur within a plant to avoid losses of personnel, damages to the environment, and financial implications. It does so in a way which is more direct, efficient and safer than what human operators are capable of. One approach to FDI is to consider the exergy characterisation of a system. By describing the exergy of the system units and streams, in this case a gas-to-liquids (GTL) process plant, the various process variables are encapsulated under a universal energy-domain parameter. The advantage of this being that it can describe the physical states as well as the chemical characteristics of the process. Previous work which utilised exergy characterisation along with a fixed-threshold approach showed promise. This study however, shows that the approach falls short when presented with 3 % faults. These results motivated the investigation of utilising attributed graphs, which package exergy data into a framework that preserves structural information of the plant. The usefulness of finding similarities (called graph matching) between the graphs constructed of operational conditions and pre-collected fault conditions to detect and isolate faulty conditions, is demonstrated. The technique performs well when considering fault magnitudes bigger than 8 % but deteriorates when applied to smaller, 3 % faults. The poor performance could be ascribed to the graph matching aspect, which is described by a single distance value that discards dimensionality. Future work will therefore look into the graph matching technique specifically, aiming to retain more informative dimensions.

关键词： Fault detection Fault isolation Exergy Gas-to-liquids Graph matching Attributed graphs