检索结果-内蒙古大学图书馆

1st International Symposium on Systems Modelling and Simulation, SMS 2024

作者： Mugunthan, Sivaguru Abdul Rahman, Juwairiyyah Abu Hassan, Hasliza Muslim, Norliana Ab Rahman, Mohammad Syuhaimi Department of Engineering Faculty of Engineering and Life Sciences Universiti Selangor Selangor Bestari Jaya45600 Malaysia Department of Computer and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar31900 Malaysia Department of Electrical Electronic and System Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Bangi Malaysia

ISBN: (纸本)9789819646128

Modeling Fiber To The Home (FTTH) networks involves several technical aspects and design considerations to enable effective and high-quality service delivery. This research seeks to boost the received signal quality for end-users inside a FTTH network. In order to create suitable and high-quality FTTH networks, this study will simulate FTTH networks utilizing network feasibility criteria, with an emphasis on BER and Q-factor. The signal distribution inside access networks is improved using Wavelength Division Multiplexing (WDM) and 10G-Passive Optical Network (PON) technology is used since it can deliver a fourfold improvement in downstream data transfer rates per user. Simulation result using OptiSystem 21 software, by setting transmitter wavelengths of 1490 nm and 1550 nm with a loss of 0 dB for a maximum of 2 users for total access based on the Q-factor calculation, which must be more than 6, while the BER must be less than 1 × e−9. System performance parameters that demonstrate Q-factor and Bit Error Rate (BER) give good quality and good performance is also shown by eye pattern in optical simulation. For 1490 nm, the highest Q-factor for 2 users is 35.8226, with a minimum BER of 2.4360 × 10−281. For 1550 nm, the highest Q-factor is 15.3668 (in phase) and 14.8087 (in quadrature), with minimal BER values of 1.3674 × e−53 (in phase) and 6.4291 × e−50 (in quadrature). Good performance is also shown by eye pattern in optical simulation that displays amplitude signals. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

An Advanced NLP Framework for Automated Medical Diagnosis with DeBERTa and Dynamic Contextual Positional Gating

arXiv

引用

arXiv 2025年

作者： Khaniki, Mohammad Ali Labbaf Saadati, Sahabeh Manthouri, Mohammad Faculty of Electrical Engineering K.N. Toosi University of Technology Tehran Iran Department of Computer Engineering North Tehran Branch Islamic Azad University Tehran Iran Department Department of Electrical and Electronic Engineering Shahed University Tehran Iran

This paper presents a novel Natural Language Processing (NLP) framework for enhancing medical diagnosis through the integration of advanced techniques in data augmentation, feature extraction, and classification. The proposed approach employs back-translation to generate diverse paraphrased datasets, improving robustness and mitigating overfitting in classification tasks. Leveraging Decoding-enhanced BERT with Disentangled Attention (DeBERTa) with Dynamic Contextual Positional Gating (DCPG), the model captures fine-grained contextual and positional relationships, dynamically adjusting the influence of positional information based on semantic context to produce high-quality text embeddings. For classification, an Attention-Based Feedforward Neural Network (ABFNN) is utilized, effectively focusing on the most relevant features to improve decision-making accuracy. Applied to the classification of symptoms, clinical notes, and other medical texts, this architecture demonstrates its ability to address the complexities of medical data. The combination of data augmentation, contextual embedding generation, and advanced classification mechanisms offers a robust and accurate diagnostic tool, with potential applications in automated medical diagnosis and clinical decision support. This method demonstrates the effectiveness of the proposed NLP framework for medical diagnosis, achieving remarkable results with an accuracy of 99.78%, recall of 99.72%, precision of 99.79%, and an F1-score of 99.75%. These metrics not only underscore the model's robust performance in classifying medical texts with exceptional precision and reliability but also highlight its superiority over existing methods, making it a highly promising tool for automated diagnostic systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Twenty years of e-learning in health science: A bibliometric

引用

Procedia computer Science 2023年 216卷 604-612页

作者： Fairuz Iqbal Maulana M. Aldiki Febriantono Dwi Risza Budi Raharja Khaeruddin Ridho Herasmara Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Diploma III Electronic Technology Vocational Study Program University of Muhammadiyah Malang Indonesia Electrical Engineering Faculty of Science and Technology Raden Rahmat Islamic University Malang Indonesia

Education about health sciences has historically been limited in the curriculum of health professionals and largely inaccessible to the public. In practice, most of the health science education is still running conventionally. Supposedly with the advancement of technology and the use of the internet everywhere, learning such as e-learning can be important, especially in the health sector. Until this research was conducted, only 514 academic documents about e-learning in health sciences were found for 20 years from 2001 to 2020, obtained in searching on the Scopus database. This study presents a comprehensive overview of studies related to E-learning in the Health Sciences sector. This study uses bibliometric analysis and indexed digital methods to map scientific publications throughout the world. This research employs the Scopus database to gather information, as well as the Scopus online analysis tool and Vosviewer to show the bibliometric network. The method consists with five stages: determining search keywords, initial search results, refinement of search results, initial compilation, and data analysis. Among the most published and indexed articles by Scopus, papers published by researchers in the United States have the highest number of publications (80), followed by United Kingdom (63) and Australia with 45 academic publications. The processed data shows the pattern and trend of increasing the number of international publications in E-learning in Health Sciences field, which Scopus index.

关键词： e-learning health science bibliometric vosviewer education

来源：评论

学校读者我要写书评

暂无评论

Ternary Spike-Based Neuromorphic Signal Processing System

SSRN

引用

SSRN 2024年

作者： Wang, Shuai Zhang, Dehao Belatreche, Ammar Xiao, Yichen Qing, Hongyu Wei, Wenjie Zhang, Malu Yang, Yang Department of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Department of Computer and Information Sciences Faculty of Engineering and Environment Northumbria University Newcastle upon TyneNE1 8ST United Kingdom

Deep Neural Networks (DNNs) have been successfully implemented across various signal processing fields, resulting in significant enhancements in performance. However, DNNs generally require substantial computational resources, leading to significant economic costs and posing challenges for their deployment on resource-constrained edge *** this study, we take advantage of spiking neural networks (SNNs) and quantization technologies to develop an energy-efficient and lightweight neuromorphic signal processing system. Our system is characterized by two principal innovations: a threshold-adaptive encoding (TAE) method and a quantized ternary SNN (QT-SNN). The TAE method can efficiently encode time-varying analog signals into sparse ternary spike trains, thereby reducing energy and memory demands for signal processing. QT-SNN, compatible with ternary spike trains from the TAE method, quantifies both membrane potentials and synaptic weights to reduce memory requirements while maintaining performance. Extensive experiments are conducted on two typical signal-processing tasks: speech and electroencephalogram recognition. The results demonstrate that our neuromorphic signal processing system achieves state-of-the-art (SOTA) performance with a 94% reduced memory requirement. Furthermore, through theoretical energy consumption analysis, our system shows 7.5× energy saving compared to other SNN works. The efficiency and efficacy of the proposed system highlight its potential as a promising avenue for energy-efficient signal processing. © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Disease Classification in Coffee Plants with Coral Developer Board Mini

Real-Time Disease Classification in Coffee Plants with Coral...

引用

Agrosystem engineering, technology & Applications (AGRETA), IEEE International Conference on

作者： Mohammad Hamzah Warsi Hermawan Nugroho Haider Abbas AlMurib Tay Fei Siang Sivaraman Eswaran Department of Electrical and Electronic Engineering University of Nottingham Malaysia Semenyih Malaysia Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Campus Sarawak Malaysia Department of Electrical and Computer Engineering Curtin University Malaysia Miri Malaysia

ISBN: (数字)9798350373660

ISBN: (纸本)9798350373677

Coffee significantly contributes to the socioeconomic development of numerous countries. However, coffee production faces several challenges, including the detrimental effects of coffee leaf diseases, which impact crop yield and quality. Traditional methods for diagnosing coffee leaf diseases are time-consuming and prone to human error. This paper presents an automated system for coffee leaf disease classification with edge computing using the Coral Developer Board Mini, featuring Google's Edge TPU. The system leverages advanced convolutional neural network (CNN) models, including MobileNetV2, VGG-16, VGG19, and DenseNet121, to achieve high accuracy in disease identification. The MobileNetV2 model achieved the highest training accuracy of 98.9%. Inference time comparisons revealed that the Coral Developer Board Mini, with an inference time of 10 milliseconds, outperformed a traditional GPU-based workstation, which had an inference time of 40 milliseconds. Results highlight the efficiency and suitability of the Coral Developer Board Mini for real-time, on-device machine learning applications in agriculture.

关键词： Training Accuracy Computational modeling Scalability Real-time systems Workstations Convolutional neural networks Socioeconomics Diseases Edge computing

来源：评论

学校读者我要写书评

暂无评论

MTSN: A Multi-Temporal Stream Network for Spotting Facial Macro- and Micro-Expression with Hard and Soft Pseudo-labels 2

MTSN: A Multi-Temporal Stream Network for Spotting Facial Ma...

引用

2nd Workshop on Facial Micro-Expression: Advanced Techniques for Multi-Modal Facial Expression Analysis, FME 2022

作者： Liong, Gen-Bing See, John Liong, Sze-Teng Chan, Chee-Seng Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia School of Mathematical and Computing Sciences Heriot-Watt University Malaysia Putrajaya Malaysia Department of Electronic Engineering Feng Chia University Taichung Taiwan

ISBN: (纸本)9781450394956

This paper considers the challenge of spotting facial macro- and micro-expression from long *** propose the multi-temporal stream network (MTSN) model that takes two distinct inputs by considering the different temporal information in the facial movement. We also introduce a hard and soft pseudo-labeling technique to enable the network to distinguish expression frames from nonexpression frames via the learning of salient features in the expression peak frame. Consequently, we demonstrate how a single output from the MTSN model can be post-processed to predict both macro- and micro-expression intervals. Our results outperform the MEGC 2022 baseline method significantly by achieving an overall F1-score of 0.2586 and also did remarkably well on the MEGC 2021 benchmark with an overall F1-score of 0.3620 and 0.2867 on CAS(ME)2and SAMM Long Videos, respectively. © 2022 IEEE. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Development of Smart Beehive Frame for Multi-Parameter Monitoring

Development of Smart Beehive Frame for Multi-Parameter Monit...

引用

International Conference on Microelectronics, MIEL

作者： M. Milovanović J. Pejić P. Pejić Department of Electronics Faculty of Electronic Engineering University of Niš Niš Serbia Department of Computer Science Faculty of Sciences and Mathematics University of Niš Niš Serbia Faculty of Information Technology Belgrade Metropolitan University

Honeybees are essential for pollination in agriculture. This paper presents a smart beehive frame for multi-parameter monitoring. The system is based on opto elements that emit IR light to the honeycomb and measure the reflection. The results showed that this kind of system can be used in practice to decrease the number of the visual on-site observations of the bee colonies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structural plasticity-based hydrogel optical Willshaw model for one-shot on-the-fly edge learning

引用

InfoMat 2023年第4期5卷 48-59页

作者： Dingchen Wang Dingyao Liu Yinan Lin Anran Yuan Woyu Zhang Yaping Zhao Shaocong Wang Xi Chen Hegan Chen Yi Zhang Yang Jiang Shuhui Shi Kam Chi Loong Jia Chen Songrui Wei Qing Wang Hongyu Yu Renjing Xu Dashan Shang Han Zhang Shiming Zhang Zhongrui Wang Department of Electrical and Electronic Engineering The University of Hong KongHong Kongthe People's Republic of China ACCESS-AI Chip Center for Emerging Smart Systems InnoHK CentersHong Kong Science ParkHong Kongthe People's Republic of China School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyMacaothe People's Republic of China Key Laboratory of Microelectronics Devices and Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijingthe People's Republic of China Collaborative Innovation Center for Optoelectronic Science Technology International Collaborative Laboratory of 2D Materials for OptoelectronicsScience and Technology of Ministry of EducationInstitute of Microscale OptoelectronicsShenzhen UniversityShenzhenthe People's Republic of China School of Microelectronics Southern University of Science and TechnologyShenzhenthe People's Republic of China Microelectronics Thrust Function Hub of the Hong Kong University of Science and Technology(Guangzhou)Guagndongthe People's Republic of China

Autonomous one-shot on-the-fly learning copes with the high privacy,small dataset,and in-stream data at the *** such learning on digital hardware suffers from the well-known von-Neumann and scaling *** optical neural networks featuring large parallelism,low latency,and high efficiency offer a promising ***,ex-situ training of conventional optical networks,where optical path configuration and deep learning model optimization are separated,incurs hardware,energy and time overheads,and defeats the advantages in edge ***,we introduced a bio-inspired material-algorithm co-design to construct a hydrogel-based optical Willshaw model(HOWM),manifesting Hebbian-rule-based structural plasticity for simultaneous optical path configuration and deep learning model optimization thanks to the underlying opto-chemical *** first employed the HOWM as an all optical in-sensor AI processor for one-shot pattern classification,association and *** then leveraged HOWM to function as a ternary content addressable memory(TCAM)of an optical memory augmented neural network(MANN)for one-shot learning the Omniglot *** HOWM empowered one-shot on-the-fly edge learning leads to 1000boost of energy efficiency and 10boost of speed,which paves the way for the next-generation autonomous,efficient,and affordable smart edge systems.

关键词： associative memory hydrogel one-shot learning optical neural network structural plasticity Willshaw model

来源：评论

学校读者我要写书评

暂无评论

Ternary Spike-based Neuromorphic Signal Processing System

arXiv

引用

arXiv 2024年

Deep Neural Networks (DNNs) have been successfully implemented across various signal processing fields, resulting in significant enhancements in performance. However, DNNs generally require substantial computational resources, leading to significant economic costs and posing challenges for their deployment on resource-constrained edge devices. In this study, we take advantage of spiking neural networks (SNNs) and quantization technologies to develop an energy-efficient and lightweight neuromorphic signal processing system. Our system is characterized by two principal innovations: a threshold-adaptive encoding (TAE) method and a quantized ternary SNN (QT-SNN). The TAE method can efficiently encode time-varying analog signals into sparse ternary spike trains, thereby reducing energy and memory demands for signal processing. QT-SNN, compatible with ternary spike trains from the TAE method, quantifies both membrane potentials and synaptic weights to reduce memory requirements while maintaining performance. Extensive experiments are conducted on two typical signal-processing tasks: speech and electroencephalogram recognition. The results demonstrate that our neuromorphic signal processing system achieves state-of-the-art (SOTA) performance with a 94% reduced memory requirement. Furthermore, through theoretical energy consumption analysis, our system shows 7.5× energy saving compared to other SNN works. The efficiency and efficacy of the proposed system highlight its potential as a promising avenue for energy-efficient signal processing. © 2024, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT Enabled Bee Hive Monitoring System

IoT Enabled Bee Hive Monitoring System

引用

International Conference on Microelectronics, MIEL

Beehive monitoring can provide useful information for people associated with beekeeping to help to manage their honey bee (Apis mellifera) colonie. This paper presents the development and experimental results of a IoT...

关键词：

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：