检索结果-内蒙古大学图书馆

GestureSet: Public Domain Dataset for Human Gesture Recognition using Wrist-worn Devices: A Preliminary Version 19

GestureSet: Public Domain Dataset for Human Gesture Recognit...

19th Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

作者： Tzamalis, Pantelis Nikoletseas, Sotiris Spirakis, Paul G. University of Patras Computer Engineering and Informatics Department Patras Greece Patras Greece University of Liverpool Department of Computer Science United Kingdom

ISBN: (纸本)9798350346497

Human Gesture Recognition (HGR) has become an increasingly important research area in recent years, driven by the need for more natural and intuitive ways of interacting with machines. Wearable smart devices, such as smartwatches, smart wristbands, and other wrist-worn devices have the potential to enable accurate and efficient gesture recognition in real-world settings. However, equivalent problems, such as object detection in computer vision and audio identification in audio analysis, have obtained enormous advantages from comprehensive datasets over the last years, for instance, ImageNet and AudioSet, accordingly. This paper proposes the structure and the creation of a preliminary version of GestureSet, an HGR large-scale multitask dataset, which includes manually annotated data of gesture events that were collected from wrist-worn devices. In particular, it proposes a hierarchy abstraction schema for the proper dataset structure and instantiates the basis of the dataset through the first HGR task that is related to the collection and annotation of gestures related to allergic rhinitis identification. Thus, through this preliminary version, we describe how the proper dataset structure is divided into different groups, each one including sessions, individual gestures, and pilot data that could be used for evaluating the learning algorithms' performance in real-world scenarios. To the best of our knowledge, this is the first attempt that envisions a unified dataset for various HGR tasks that can find applications in different domains. Our vision, specifically, is for this work to set the basis for the dataset enrichment in a wide range of various tasks, and its data to be used in multiple learning and identification settings, providing circularity in different domains, and enabling reproducibility of the dataset's gestures events. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Classification of Alzheimer’s Disease Subjects from MRI Using Deep Convolutional Neural Networks 3rd

Classification of Alzheimer’s Disease Subjects from MRI Usi...

引用

3rd International Conference on Novel and Intelligent Digital Systems, NiDS 2023

作者： Papadimitriou, Orestis Kanavos, Athanasios Mylonas, Phivos Maragoudakis, Manolis Department of Information and Communication Systems Engineering University of the Aegean Samos Greece Department of Informatics and Computer Engineering University of West Attica Athens Greece Department of Informatics Ionian University Corfu Greece

ISBN: (纸本)9783031441455

The classification of Alzheimer’s disease (AD) using deep learning techniques has shown promising results. However, achieving successful application in medical settings requires a combination of high precision, short processing time, and generalizability to different populations. In this study, we propose a convolutional semantic network (CNN)-based classification algorithm that utilizes magnetic resonance imaging (MRI) scans from individuals with AD. Our models achieved average area under the curve (AUC) values of 0.91−0.94 for within- dataset recognition and 0.88−0.89 for between-dataset recognition. The proposed convolutional framework can be potentially applied to any image dataset, offering the flexibility to design a computer-aided diagnosis system targeting the prediction of various clinical conditions and neuropsychiatric disorders using multimodal imaging and tabular clinical data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Accurate Deep Learning-Based Sleep Apnea Detection from Cardiac Physiological Signals 8

Accurate Deep Learning-Based Sleep Apnea Detection from Card...

引用

8th IEEE Asia Pacific Conference on Wireless and Mobile, APWiMob 2023

作者： Delimayanti, Mera Kartika Muharram, Asep T. Pradipta, Ayres Ismail, Muhammad K. Ryanari, Rinaldito A. Prasetyo, Raditya A. Faisal, Mohammad Reza Politeknik Negeri Jakarta Department of Computer and Informatics Engineering Depok Indonesia Lambung Mangkurat University Department of Computer Science Banjarbaru Indonesia

ISBN: (纸本)9798350327861

Sleep apnea is a severe sleep disorder characterized by interrupted breathing during sleep. Early detection and accurate diagnosis of sleep apnea are essential to avoiding potentially dangerous health complications. This study proposes a sleep apnea detection model using cardiac physiological signals and a deep learning approach. This model uses Convolutional Neural Networks (CNN) to learn patterns and features in cardiac signal data. Heart signal data is collected from individuals with sleep apnea and normal sleeping individuals as datasets. Datasets consisting of heart signal data were gathered from patients diagnosed with sleep apnea and people with normal sleeping patterns. The public dataset was enhanced and utilized for training, employing a Convolutional Neural Network (CNN) architecture of six layers. The improved data is derived from the process of segmenting the data. The trained model demonstrated a high accuracy of 98.4% in effectively classifying physiological heart signal samples into two categories: 'normal' and 'sleep apnea'. This project aims to develop a model that can assist medical professionals in diagnosing sleep apnea and providing early warning to patients. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Advancing Weather Image Classification Using Deep Convolutional Neural Networks 18

Advancing Weather Image Classification Using Deep Convolutio...

引用

18th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2023

作者： Papadimitriou, Orestis Kanavos, Athanasios Mylonas, Phivos Maragoudakis, Manolis University of the Aegean Department of Information and Communication Systems Engineering Samos Greece University of West Attica Department of Informatics and Computer Engineering Athens Greece Ionian University Department of Informatics Corfu Greece

ISBN: (纸本)9798350327717

Automatic classification of weather images is a crucial task in the field of meteorology. Recent advancements in Convolutional Neural Networks (CNNs) have demonstrated their effectiveness in image classification. In this paper, we propose an innovative CNN-based approach for weather image classification. Building upon prior research, our model capitalizes on the exceptional feature extraction capabilities of CNNs to accurately classify weather images across various categories. To enhance the generalization performance, we train the model using a combination of data augmentation techniques, including rotation, scaling and flipping. This paper introduces a CNN model specifically made for weather image classification, encompassing categories such as cloudy, sunny, rainy and snowy conditions. Through extensive training and evaluation on a substantial weather image dataset, our proposed model achieves an impressive accuracy rate of 98%. Our experimental results highlight the superior performance of our CNN model when compared to various state-of-The-Art methods in weather image classification. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Method for Automatic Fruit Fly Detection and Counting

Deep Learning-based Method for Automatic Fruit Fly Detection...

引用

2024 IEEE International Conference on Computing, ICOCO 2024

作者： Wahyuni, Indah Desri Shabrina, Nabila Husna Suputa Department of Computer Engineering Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Department of Plant Protection Faculty of Agriculture Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9798331530303

Fruit flies are a major threat faced by snake fruit farmers. Fruit flies can degrade the quality of snake fruits and reduce the overall yield. Traps stuffed with Methyl Eugenol are commonly placed across snake fruit plantations to attract fruit flies. Farmers then manually counted and reported the trapped fruit flies as part of their pest management strategies. However, manually counting trapped fruit flies is time-consuming, leading to unwillingness among farmers to perform this task. This study aims to develop an automated detection and counting system using deep-learning-based methods to address this issue. The proposed system was built on a modified YOLOv5 algorithm, achieving a precision of 0.944, recall of 0.947, and mAP of 0.946, with an object-counting time of only 50 ms. These results demonstrate that the proposed fruit-fly detection and counting system offers excellent performance with rapid detection times ©2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Bottleneck-Minimal Indexing for Generative Document Retrieval 41

Bottleneck-Minimal Indexing for Generative Document Retrieva...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Du, Xin Xiu, Lixin Tanaka-Ishii, Kumiko Waseda Research Institute for Science and Engineering Waseda University Japan Department of Mathematical Informatics The University of Tokyo Japan Department of Computer Science and Engineering Waseda University Japan

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document x ∈ X is indexed by t ∈ T, and a neural autoregressive model is trained to map queries Q to T. GDR can be considered to involve information transmission from documents X to queries Q, with the requirement to transmit more bits via the indexes T. By applying Shannon's rate-distortion theory, the optimality of indexing can be analyzed in terms of the mutual information, and the design of the indexes T can then be regarded as a bottleneck in GDR. After reformulating GDR from this perspective, we empirically quantify the bottleneck underlying GDR. Finally, using the NQ320K and MARCO datasets, we evaluate our proposed bottleneck-minimal indexing method in comparison with various previous indexing methods, and we show that it outperforms those methods. Copyright 2024 by the author(s)

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble based unsupervised anomaly detection with concept drift adaptation for time series data 10

Ensemble based unsupervised anomaly detection with concept d...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Li, Danlei Nair, Nirmal Wang, Kevin I-Kai Sakurai, Kouichi University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Kyushu University Department of Informatics Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798331520861

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework's longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability. © 2024 IEEE.

关键词： Anomaly detection Concept drift adaptation Ensemble method Time series Unsupervised method

来源：评论

学校读者我要写书评

暂无评论

BAHGRF^(3):Human gait recognition in the indoor environment using deep learning features fusion assisted framework and posterior probability moth flame optimisation

引用

CAAI Transactions on Intelligence Technology 2025年第2期10卷 387-401页

作者： Muhammad Abrar Ahmad Khan Muhammad Attique Khan Ateeq Ur Rehman Ahmed Ibrahim Alzahrani Nasser Alalwan Deepak Gupta Saima Ahmed Rahin Yudong Zhang Foundation University Islamabad IslamabadPakistan Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl KhobarSaudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadhSaudi Arabia Department of Computer Science Maharaja Agrasen Institute of TechnologyDelhiIndia United International University DhakaBangladesh School of Informatics University of LeicesterLeicesterUK

Biometric characteristics are playing a vital role in security for the last few *** gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is *** the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and *** models are selected based on the top-5 accuracy and less number of ***,both models are trained through deep transfer learning and extracted deep features fused using a voting *** the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best *** selected features are classified using several supervised learning *** CASIA-B publicly available dataset has been employed for the experimental *** this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.

关键词： deep learning feature fusion feature optimization gait classification indoor environment machine learning

来源：评论

学校读者我要写书评

暂无评论

Groundbreaking taxonomy of metaverse characteristics

引用

Artificial Intelligence Review 2025年第8期58卷 1-50页

作者： Sadeghi-Niaraki, Abolghasem Rahimi, Fatema Azlan, Nur Alya Emanuelle Binti Song, Houbing Ali, Farman Choi, Soo-Mi Department of Computer Science and Engineering and Convergence Engineering for Intelligent Drone XR Research Center Sejong University Seoul Korea Republic of BaltimoreMD21250 United States Department of Applied AI School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

The Metaverse, a dynamic and immersive virtual realm, has captured the imagination of researchers and enthusiasts worldwide. This survey paper aims to introduce a groundbreaking taxonomy for the characteristics of the Metaverse offering a structured and adaptable framework that extends beyond existing categorizations by incorporating dynamic transformations. Unlike prior taxonomies, which often focus on fixed attributes, our approach emphasizes the dynamic evolution of Metaverse characteristics. Through an extensive review of published literature, this study explores key technological, social, economic, and ethical dimensions of the Metaverse. It introduces a process-oriented classification based on 23 distinct characteristics, including immersification, spatiotemporalification, interactification, persistentification, presentification, personification, unification, imaginification, economification, uncertaintification, and credification. By mapping these evolving aspects, we provide a structured and future-proof foundation for understanding the Metaverse’s continuous development. This survey establishes a new standard for comprehensiveness and innovation, shedding light on the diverse facets that have been explored in literature. Through this novel taxonomy, we provide a detailed map of the current landscape and offer insights that pave the way for future research and development in this burgeoning digital frontier. © The Author(s) 2025.

关键词： Comprehensive analysis Futuristic exploration Metaverse characteristics Paradigm-shifting taxonomy Revolutionary categorization

来源：评论

学校读者我要写书评

暂无评论

"I Have to Use My Son's QR Code to Run the Business": Unpacking Senior Street Vendors' Challenges in Mobile Money Collection in China

引用

Proceedings of the ACM on Human-computer Interaction 2023年第CSCW1期7卷 1-28页

作者： He, Changyang He, Lu Lu, Zhicong Li, Bo Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Department of Informatics University of California Irvine United States Department of Computer Science City University of Hong Kong Hong Kong Hong Kong

Mobile payment systems have become an infrastructural component in citizens' socio-economic life in China. The rapid shift to a cashless society demands vendors of all ages to quickly adapt themselves to the ubiquitous mobile payment era. However, how this trend may impact senior vendors, a group that typically uses less technology, remains unknown despite its significance in inclusive mobile payment design. This work aims to address this gap by investigating the challenges and strategies of senior vendors in mobile payment adoption. Particularly, we focus on a traditional low-resource setting with a large volume of senior vendors: street vending. We conduct a qualitative study incorporating field observations on 33 senior street vendors and semi-structured interviews with 15 of them (aged 53-78), and take Moneywork as an analytical lens to unpack their challenges in physical and social interactions. We find that senior street vendors are a group passively adopting mobile payments due to business requirements instead of recognizing their advantages. Vendors with relatively low digital literacy have to take an alternative method - using family members' QR codes - to run the business as family-dependent money receivers. With limited considerations for senior vendors' situational vulnerabilities, unexpected difficulties of payment confirmation emerge during transactions, such as reduced confirmation efficacy under noisy surroundings and degraded hearing. Transaction security issues also appear when mobile payment-based frauds target both confirmation interfaces (e.g., fake sounds of successful payment) and trust systems (e.g., showing half-done proof to flee without paying) in street vending. Finally, we raise a less visible yet critical concern of family-dependent vendors on the lost money freedom when their income flows into their families' wallets. We propose design implications for mobile payment systems to support more secure, efficient and accessible money collec

关键词： Electronic money

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：