检索结果-内蒙古大学图书馆

34th Medical Informatics Europe Conference, MIE 2024

作者： Rohani, Narjes Gallagher, Michael Gal, Kobi Banas, Kasia Manataki, Areti Usher institute University of Edinburgh United Kingdom Moray House School of Education and Sport University of Edinburgh United Kingdom School of Informatics University of Edinburgh United Kingdom Dept. of Software and Information Systems Engineering Ben-Gurion University Israel School of Computer Science University of St Andrews United Kingdom

ISBN: (纸本)9781643685335

Despite the proliferation of educational programmes in Health Informatics (HI) worldwide, there is limited knowledge regarding students' preferences and learning strategies in HI courses. To address this gap, we conducted a study to gather and analyse data from three HI courses. Employing the Motivated Strategies for Learning Questionnaire (MSLQ) and theories of deep and surface learning, we designed a questionnaire to collect data. The analysis of students' responses indicates that machine learning emerges as one of the most interesting topics, while certain topics such as data wrangling of genomics data were more challenging for students. Students expressed a preference for sequential learning. They exhibited multimodal tendencies regarding the type of learning resources, with tendency to prefer learning resources that have more visual contents. In all three courses, learners reported using deep learning strategy rather than surface learning, yet they appear to struggle with employing organisation, elaboration, and peer learning tactics. This study provides valuable insights into HI education, offering recommendations for educators, learners, and researchers to enhance HI education. © 2024 The Authors.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Data Transfer for YOLOv5 Based on Selector Network and Partial Pseudo-Labels

Data Transfer for YOLOv5 Based on Selector Network and Parti...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Guoqiang Qu Jianchu Lin Haiyi Bian Haiping Zhou Muhammad Raees UL Haq Bo Jiang Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an China Faculty of Electronic Information Engineering Huaiyin Institute of Technology Huai’an China Jiangsu Eazytec Co. LTD Yixin China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

YOLOv5 is a widely used object detection method for its high-performance of balancing speed and accuracy. Data transfer for YOLOv5 is a challenging task, as it could involve domain shift between different datasets. We propose a data transfer method for YOLOv5 based on a Selector Network and Partial Pseudo-Labeling. The backbone network of YOLOv5 is used for feature extraction, a Selector Network is employed to filter source domain outlier samples to address the domain shift issue, and Partial Pseudo-Labels are leveraged to improve classification performance in the target domain. The results show that our method improves detection accuracy by an average of 2.4% on public datasets (COCO and VOC) and our datasets, with a notable improvement of 3.1% under complex backgrounds and varying lighting conditions. It demonstrates that our method can effectively enhances the accuracy and stability of YOLOv5.

关键词： YOLO Training Accuracy Filtering Lighting Data transfer Feature extraction Cognitive systems Faces Batch normalization

来源：评论

学校读者我要写书评

暂无评论

Fitweet: Arduino-Based Smartwatch for Early Anticipatory Anxiety Notification System 9th

Fitweet: Arduino-Based Smartwatch for Early Anticipatory Anx...

引用

9th International Conference on Computational Science and Technology, ICCST 2022

作者： Abdulmanab, Muhammad Rahiman Nor’Azman, Nur Faidz Hazirah Meon, Hasni Razak, Chempaka Seri Abdul Ab Hamid, Siti Hafizah Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia Department of Communication Faculty of Communication Visual Art and Computing Universiti Selangor Bestari Jaya Malaysia School of Pre-University Studies Taylor’s College Lakeside Campus Subang Jaya Malaysia

ISBN: (纸本)9789811984051

As anxiety becomes increasingly prevalent among youths especially university students, early prevention via anxiety disorder profiling is crucial. Nevertheless, most screening tools to date are not automated, labour-intensive and time-consuming. Mental health detection in online social networks (OSNs) using artificial intelligence (AI) can provide means for capturing overlooked behavioural attributes, but few are centred around anxiety detection. Internet of Things (IoT)’s increasing popularity enables bio-signals monitoring to aid in mental health care. However, minimum research has been devoted to IoT-based assistive technologies for anxiety, which currently are only used by individuals already diagnosed and actively monitored. This study proposes a novel approach to anticipatory anxiety detection for Malaysian university students aged between 18 and 25 inclusive as an early notification system using AI and IoT for bilingual Malay and English tweets and vital signs analysis respectively. Our result shows that Logistic Regression with Bag-of-Words (BoW) is the overall best performing model with 81.06% accuracy. The Arduino smartwatch sensor readings from the MAX30102 pulse oximeter sensor are used to determine different body conditions using a rule-based approach. The comparison test result between the prototype and conventional measuring devices shows the prototype’s ability to accurately distinguish vital signs with a relatively low Mean Absolute Percent Error (MAPE) rate of 10.92% and 1.51% for pulse rate and temperature respectively. Together, our proof-of-concept results indicate the potential of AI and IoT in deriving new measures of anxiety, by analysing social data combined with bio-signals monitoring to alert users regarding their anxiety state. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimizing Gammatone Cepstral Coefficients for Gear Fault Detection

引用

IEEE Access 2025年 13卷 101711-101720页

作者： Zrar Kh Abdul Abdulbasit K. Al-Talabani Wisam Hazim Gwad Entisar Alkayal Halgurd S. Maghdid Safar Maghdid Asaad Computer Department College of Science Charmo University Sulaymaniyah Iraq Department of Software Engineering Faculty of Engineering Koya University Koya Iraq Department of Artificial Intelligence Engineering College of Engineering Alnoor University Ninavah Iraq Information Technology Department Faculty of Computing and Information Technology-Rabigh King Abdulaziz University Jeddah Saudi Arabia Department of Engineering Research Center Deanship of Research and Development Centers Koya University Erbil Governorate Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil Iraq

Cepstral features, such as Gammatone Cepstral Coefficients (GTCC), have recently been applied in fault detection and diagnosis. However, GTCC was originally designed for speech feature extraction rather than fault detection, which limits its ability to capture relevant features for fault identification effectively. In this research, three key parameters of GTCC, namely, the number of coefficients, maximum frequency, and minimum frequency, are optimized using two metaheuristic algorithms: Fitness Dependent Optimizer (FDO) and Grey Wolf Optimization (GWO). These parameters are vital for enhancing the effectiveness of GTCC in extracting relevant features from the vibration signal for gear defect identification. Specifically, the maximum and minimum frequency values are critical for capturing the Gear Mesh Frequency (GMF), a common indicator of gear faults. Furthermore, optimizing the number of GTCC coefficients helps reduce model complexity. Experimental results demonstrate that optimizing GTCC parameters with GWO improves fault detection performance using an SVM classifier, achieving over 1% and 3% accuracy improvements on the PHM09 and DDS datasets, respectively.

关键词： Feature extraction Fault detection Optimization Gears Metaheuristics Mel frequency cepstral coefficient Mathematical models Filter banks Support vector machines Cepstrum

来源：评论

学校读者我要写书评

暂无评论

Dynamic AI-Driven Network Slicing with O-RAN for Continuous Connectivity in Connected Vehicles and Onboard Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 720-733页

作者： Shah, Syed Danial Ali Bashir, Ali Kashif Al-Otaibi, Yasser D. Dabel, Maryam M. Al Ali, Farman University of Leeds School of Electronic and Electrical Engineering LeedsLS2 9JT United Kingdom Manchester Metropolitan University Department of Computing and Mathematics M15 6BH United Kingdom Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Punjab Rajpura140401 India King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Jeddah21589 Saudi Arabia University of Hafr Al Department of Computer Science and Engineering Batin Saudi Arabia Sungkyunkwan University School of Convergence Seoul Korea Republic of

The rise of connected and autonomous vehicles signifies an era of intelligent transportation systems, where robust and continued network connectivity is essential for critical applications and enhanced in-vehicle Consumer Electronics (CE) experiences. Slicing at the network's edge offers tailored and dedicated logical networks for diverse and low-latency vehicular demands, including Advanced Driver Assistance systems (ADAS) and in-car infotainment. However, seamless migration of network slices as vehicles traverse coverage areas of different network operators presents formidable challenges, such as ensuring continuous connectivity and uninterrupted service for both safety-critical systems and consumer-oriented services. In this paper, we introduced dynamic network slicing for continuous connectivity in connected vehicles and onboard CE using the Open Radio Access Network (O-RAN) framework in a highly dynamic and mobile environment. We implemented an xAPP within O-RAN that enables Deep Reinforcement Learning (DRL) agent to learn optimal policies through interaction with the network, guiding intelligent decisions on slice migration, resource allocation, and handover optimization. We conducted simulations and evaluations to demonstrate the effectiveness of the proposed xAPP in maintaining optimal Quality of Service (QoS), ensuring efficient RAN resource utilization, minimizing service interruptions, and prioritizing safety-critical slices, all while supporting seamless operation of CE within vehicles during mobility. © 1975-2011 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Intrusion Detection System with SVM

Performance Evaluation of Intrusion Detection System with SV...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Ricky Aurelius Nurtanto Diaz I Ketut Gede Darma Putra Made Sudarma I Made Sukarsa Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Bali Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Various machine learning techniques have been proposed to improve the effectiveness of Intrusion Detection systems (IDS), where IDS is one of the important parts of the network that functions to maintain network security. With its various capabilities and reputation, Support Vector Machine (SVM) is often applied in various classification cases. However, it has constraints with accuracy and computing time when it comes to data that has large dimensions. Utilizing metaheuristic techniques is one possibility that researchers can use to solve this problem. To overcome this, in this study, we will evaluate the performance of SVM for the IDS case by utilizing the metaheuristic Grey Wolf Optimization (GWO) algorithm. From the experiments with three different iteration models, the best results of the combination of SVM and GWO were found in a model with 10 GWO iterations and 10 populations with an accuracy of 97.47% using 15 features out of 48 original features of the UKM-IDS20 dataset.

关键词： Support vector machines Performance evaluation Accuracy Metaheuristics Intrusion detection Machine learning Network security Intelligent systems Cybernetics

来源：评论

学校读者我要写书评

暂无评论

A Novel Peak-to-Average Power Ratio Reduction for 5G Advanced Waveforms

引用

computers, Materials & Continua 2022年第10期73卷 1637-1648页

作者： Rajneesh Pareek Karthikeyan Rajagopal Himanshu Sharma Nidhi Gour Arun Kumar Sami Althahabi Haya Mesfer Alshahrani Mohamed Mousa Manar Ahmed Hamza Department of Computer Science&Engineering JECRC UniversityJaipur303905India Centre for Nonlinear Systems Chennai Institute of TechnologyChennaiIndia Department of Electronics and Communication JECRC UniversityJaipur303905India Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityAbhaSaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Electrical Engineering Department Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Multi and single carrier waveforms are utilized in cellular systems for high-speed data *** The Fifth Generation(5G)system,several waveform techniques based on multi carrier waveforms are ***,the Peak to Average Power Ratio(PAPR)is seen as one of the significant concerns in advanced waveforms as it degrades the efficiency of the *** proposed article documents the study,progress,and implementation of PAPR reduction algorithms for the 5G radio *** compare the PAPR algorithm performance for advanced and conventional *** simulation results reveal that the advanced Partial Transmission Sequence(PTS)and Selective Mapping(SLM)methods enhanced the throughput and gain of the 5G ***,we have also analyzed the performance of Orthogonal Time Frequency Space Modulation(OTFSM)based on a single carrier system and found that PAPR is significantly low and is best suited to fading *** is seen that the conventional algorithms lower the PAPR but increase the *** proposed PTS and SLM have shown good performance with low computational complexity.

关键词： PAPR 5G OFDM NOMA OTFSM PTS SLM

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning for Cross-Domain Recommendation 38

Federated Graph Learning for Cross-Domain Recommendation

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Yang, Ziqi Peng, Zhaopeng Wang, Zihui Qi, Jianzhong Chen, Chaochao Pan, Weike Wen, Chenglu Wang, Cheng Fan, Xiaoliang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computing and Information Systems The University of Melbourne Australia College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer between source and target domains. However, many recent CDR models overlook crucial issues such as privacy as well as the risk of negative transfer (which negatively impact model performance), especially in multi-domain settings. To address these challenges, we propose FedGCDR, a novel federated graph learning framework that securely and effectively leverages positive knowledge from multiple source domains. First, we design a positive knowledge transfer module that ensures privacy during inter-domain knowledge transmission. This module employs differential privacy-based knowledge extraction combined with a feature mapping mechanism, transforming source domain embeddings from federated graph attention networks into reliable domain knowledge. Second, we design a knowledge activation module to filter out potential harmful or conflicting knowledge from source domains, addressing the issues of negative transfer. This module enhances target domain training by expanding the graph of the target domain to generate reliable domain attentions and fine-tunes the target model for improved negative knowledge filtering and more accurate predictions. We conduct extensive experiments on 16 popular domains of the Amazon dataset, demonstrating that FedGCDR significantly outperforms state-of-the-art methods. We open source the code at https://***/LafinHana/FedGCDR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent System to Maximize Customer Experience in Restaurants

Intelligent System to Maximize Customer Experience in Restau...

引用

Advancements in Computing (ICAC), International Conference on

作者： R.U.A Jayalal Y.E Nimeshika G.N.N Samarasekara G.R.C.I Wijerathna Narmada Gamage Poojani Gunathilake Department of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

With technological improvements in the restaurant industry, competition is fierce, and a restaurant's success depends on providing excellent and luxury customer satisfaction. The food industry has had to continuously advance with technology in order to adequately satisfy the wants of people leading increasingly luxurious lives. While some restaurants still rely on manpower, the majority are eager to advance with technology in order to improve the standard of their offerings and enhance their customers' experiences. In order to optimize customer satisfaction and experience, this research project intends to investigate the potential of intelligence in the restaurant business. This research has explored intelligent systems such as digital self-service menus for ordering food, augmented reality (AR) visualization systems for customers, the observation of chefs in the kitchen, and the usage of robots to serve meals. This research paper analyzes the advantages of automating restaurant operations and how to do so to enhance customer satisfaction. Overall, this study has the potential to transform the restaurant industry and increase customer satisfaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicle type recognition based on audio data 58

Vehicle type recognition based on audio data

引用

58th Hawaii International Conference on System Sciences, HICSS 2025

作者： Kobiela, Dariusz Hajdasz, Michal Erezman, Mateusz Nurzyńska, Karolina Zaporowski, Szymon Kurowski, Adam Weichbroth, Pawel Department of Software Engineering Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Multimedia Systems Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Algorithmics and Software Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

ISBN: (纸本)9780998133188

Identifying different vehicle types can help manage traffic more efficiently, reduce congestion, and improve public safety. This study aims to create a classification model that can recognize vehicle types based on the sound of passing vehicles. To achieve this, a database of raw audio files containing 1763 samples from two sources was assembled. The time-domain signals were converted to a time-frequency representation using the short-time Fourier transform to generate Mel Spectrograms. Mel-frequency Cepstral Coefficients (MFCCs) were also generated using the discrete cosine transform. In our experiments we compared these approaches. Since the data was imbalanced we applied online augmentation. Based on the literature review, we chose a Convolutional Neural Network (CNN) classifier because it is particularly well suited for analyzing large datasets due to its automatic feature extraction, parameter sharing and sparsity. The results showed that Mel Spectrograms were more effective for audio data preprocessing in this particular use case, achieving the highest accuracy of 0.875 and the highest f1-score of 0.877 compared to MFCCs. © 2025 IEEE computer Society. All rights reserved.

关键词： Image coding

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：