检索结果-内蒙古大学图书馆

Real-time behavior recognition of animal: an IoT-based system design using acceleration data

Multimedia Tools and Applications 2024年 1-26页

作者： Tran, Duc-Nghia Manh, Do Viet Van Thanh, Pham Shankar, A. Achyut Joshi, Kireet Tran, Duc-Tan Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam University of Fire Prevention and Fighting Hanoi100000 Viet Nam Department of Cyber Systems Engineering WMG University of Warwick CoventryCV74AL United Kingdom Department of CSE University Centre for Research & ampDevelopment Chandigarh University Punjab Mohali140413 India School of Computer Science Engineering Lovely Professional University Punjab Phagwara144411 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India Center of Research Impact and Outcome Chitkara University Punjab Chandigarh India Department of Computer Science & amp Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi12116 Viet Nam

By analyzing large amounts of animal behavior data, humans can assess cattle’s condition. It leads to research and development a field using accelerometers and machine learning algorithms to ‘study’ behavior from acceleration data. It is challenging to analyze animal behavior due to the activity complexity. For example, acceleration data of some cow behaviors (e.g., feeding and standing) are similar if these behaviors contain similar gestures. In practical, real-time applications even bring more challenging since it is necessary to minimize a data window for behavior consideration. Using short data window often reduces the performance of classification algorithms. This study proposes a new solution for the mentioned challenges by combining neck-mounted and leg-mounted accelerometers, then using the vector of the dynamic body acceleration (VeDBA) and Mean features of synchronized acceleration data for the Decision Tree algorithm. The proposed method is demonstrated that performs well (0.94 accuracy, 0.91 sensitivity, 0.90 positive predictive value) within a low computational complexity algorithm and short data window (3-second data window, at the rate of one sample per second). It is particularly suited for the case of a real-time IoT-based system. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Knowledge Graph Completion Based on Gated Attention Unit 29

Sequence-to-Sequence Knowledge Graph Completion Based on Gat...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yi, Fengge Wei, Xiumei Liu, Xiaojing Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (纸本)9798350330717

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5's proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment. © 2023 IEEE.

关键词： gated attention unit knowledge graph completion sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Studying the Fundamentals of Internet of Things (IoT) in the Healthcare Applications 1

Studying the Fundamentals of Internet of Things (IoT) in the...

引用

1st International Conference on Healthcare Innovations, Software and engineering Technologies, HISET 2024

作者： Abu Eid, Aws Ismail Kadam Rangrao, Shrikant Patil Abhijit, Seema Sharma, Lakshay Rani, D Shobha Ukirade, Chaitali Arab Open University Faculty of Computing Studies Amman Jordan Jaywant College of Engineering and Polytechnic Department of Computer Science Engineering Karad India Jaywant College of Management Karad India Indraprastha Institute of Information Technology Delhi India Institute of Aeronautical Engineering Department of Electrical and Electronics Engineering Hyderabad India Department of Obstetrics and Gynecology Karad India

ISBN: (纸本)9798350360707

The Internet of Things (IoT) has brought smart healthcare systems to the medical industry. These systems are typically made up of a network, a remote server, and sensors with smart capabilities. The primary goals of this system are to offer multidimensional feature monitoring and fundamental therapy recommendations. The primary goals of Internet of Things (IoT)-based healthcare services are to enhance quality of life and offer a great user experience at an affordable price. The primary purpose of IoT is to give elderly patients with chronic illnesses access to trustworthy, efficient, and intelligent healthcare services as well as connectivity to the medical resources that are readily available. Thus, many studies are developed on the different applications which worked on the IoT for the healthcare which includes wearable as well as non-wearable devices or machines. Thus, it makes the users to obtain the data from anywhere and wherever required for the study or analysis of the patients. In the meantime, the Internet of Things is expanding to include even the tiniest sensors and the fundamentals of automation and machine-to-machine communication. © 2024 IEEE.

关键词： healthcare internet of things (IoT) network service

来源：评论

学校读者我要写书评

暂无评论

A Low-Complexity Time Synchronization Algorithm for MIMO ZP-OFDM in Urban Impulsive Noise Environments

A Low-Complexity Time Synchronization Algorithm for MIMO ZP-...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Koosha Pourtahmasi Roshandeh Mostafa Mohammadkarimi Masoud Ardakani Electrical and Computer Engineering Department University of Alberta Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology

The zero padding (ZP) variants of orthogonal frequency-division multiplexing (OFDM) exhibit a lower bit error rate (BER) and higher energy efficiency compared to their cyclic prefix (CP) counterparts. However, the employment of ZP-OFDM demands strict time synchronization, which is challenging in the absence of pilots or CP. Moreover, time synchronization in OFDM systems is even more challenging when impulsive noise is present. It is well known that urban noise, which consists largely of impulsive noise generated by spark plugs used in internal combustion engines, switching and industrial activities, and discharge of high voltage distribution lines, has a strong influence on digital mobile communications. In this paper, we propose a new low-complexity approximate maximum likelihood (A-ML) timing offset (TO) estimator for ZP multiple-input multiple-output (MIMO)-OFDM in impulsive-noise environments. Performance comparison of the A-ML estimator with existing TO estimators demonstrates a superior performance in terms of lock-in probability with similar computational complexity. Also, compared to the optimal ML TO estimator, it offers a significantly lower computational complexity with negligible performance loss. The A-ML estimator can be employed for both frame and symbol synchronization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Pneumonia, Covid-19 and Tuberculosis Using Deep Learning Methods 4

Detection and Classification of Pneumonia, Covid-19 and Tube...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Gaurkhede, Sanskruti Shendre, Sanika Izankar, Sakshi Burle, Rushikesh Gudadhe, Amit Datta Meghe Institute of Higher Education and Research Computer Science and Design Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Artifical Intelligience & Machine Learning Mahartashtra Wardha442001 India

ISBN: (纸本)9798331523923

The deep learning literature is presented in this publication. in the classification of respiratory diseases, focusing on pneumonia, COVID-19, and tuberculosis. The review explores the potential of various Complex patterns that can be extracted from medical images using advanced neural network designs, like recurrent neural network designs (RNNs) and convolutional neural networks (CNNs). It evaluates the efficacy of these models using a range of datasets and considers limitations like interpretability, class disparity, and data scarcity. The study also discusses integrating multimodal data sources to enhance diagnostic accuracy. A comparative analysis of deep learning models highlights ResNet-18's superior performance in classifying CT scans of tuberculosis, pneumonia, and COVID-COVID-19. The findings suggest that deep learning models can aid radiologists in accurately diagnosing respiratory diseases from CT images, potentially transforming early detection and classification methods. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis on Machine Learning Based Methods for Lung Cancer Level Classification

SSRN

引用

SSRN 2025年

作者： Farshchiha, Shayli Asoudeh, Salman Kuhshuri, Maryam Shavali Eisaei, Mehrshad Azadi, Mohamadreza Hesaraki, Saba Department of Computer Science Shamsipour Technical College Tehran Iran Islamic Azad University Science and Research Branch Faculty of Mechanics Electrical Power and Computer Iran University of Birjand Iran Isfahan University of Technology Department of Electrical and Computer Engineering Faculty of Engineering Isfahan Iran Faculty of Computer College of Technical and Engineering University of Velayat Iran University of Isfahan Department of Electrical Engineering Faculty of Engineering Isfahan Iran University of Mazandaran Mazandaran Iran

Lung cancer is a major issue in worldwide public health, requiring early diagnosis using stable techniques. This work begins a thorough investigation of the use of machine learning (ML) methods for precise classification of lung cancer stages. A cautious analysis is performed to overcome overfitting issues in model performance, taking into account minimum child weight and learning rate. A set of machine learning (ML) models including XGBoost (XGB), LGBM, Adaboost, Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), CatBoost, and k-Nearest Neighbor (k-NN) are run methodically and contrasted. Furthermore, the correlation between features and targets is examined using the deep neural network (DNN) model and thus their capability in detecting complex patterns is established. It is argued that several ML models can be capable of classifying lung cancer stages with great accuracy. In spite of the complexity of DNN architectures, traditional ML models like XGBoost, LGBM, and Logistic Regression excel with superior performance. The models perform better than the others in lung cancer prediction on the complete set of comparative metrics like accuracy, precision, recall, and F-1 score. © 2025, The Authors. All rights reserved.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A deep convolutional visual encoding model of neuronal responses in the LGN

引用

Brain Informatics 2021年第1期8卷 11页

作者： Mounier, Eslam Abdullah, Bassem Mahdi, Hani Eldawlatly, Seif Computer and Systems Engineering Department Faculty of Engineering Ain Shams University 1 El-Sarayat St. Abbassia Cairo Egypt Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt

The Lateral Geniculate Nucleus (LGN) represents one of the major processing sites along the visual pathway. Despite its crucial role in processing visual information and its utility as one target for recently developed visual prostheses, it is much less studied compared to the retina and the visual cortex. In this paper, we introduce a deep learning encoder to predict LGN neuronal firing in response to different visual stimulation patterns. The encoder comprises a deep Convolutional Neural Network (CNN) that incorporates visual stimulus spatiotemporal representation in addition to LGN neuronal firing history to predict the response of LGN neurons. Extracellular activity was recorded in vivo using multi-electrode arrays from single units in the LGN in 12 anesthetized rats with a total neuronal population of 150 units. Neural activity was recorded in response to single-pixel, checkerboard and geometrical shapes visual stimulation patterns. Extracted firing rates and the corresponding stimulation patterns were used to train the model. The performance of the model was assessed using different testing data sets and different firing rate windows. An overall mean correlation coefficient between the actual and the predicted firing rates of 0.57 and 0.7 was achieved for the 10 ms and the 50 ms firing rate windows, respectively. Results demonstrate that the model is robust to variability in the spatiotemporal properties of the recorded neurons outperforming other examined models including the state-of-the-art Generalized Linear Model (GLM). The results indicate the potential of deep convolutional neural networks as viable models of LGN firing. © 2021, The Author(s).

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

End-to-End Anti-Backdoor Learning on Images and Time Series

arXiv

引用

arXiv 2024年

作者： Jiang, Yujing Ma, Xingjun Erfani, Sarah Monazam Li, Yige Bailey, James Faculty of Engineering and Information Technology The University of Melbourne Australia School of Computer Science Fudan University China School of Computer Science and Technology Xidian University China

Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the training phase, allowing unauthorized control over the model’s output during inference time. Although numerous defenses exist for image classification models, there is a conspicuous absence of defenses tailored for time series data, as well as an end-to-end solution capable of training clean models on poisoned data. To address this gap, this paper builds upon Anti-Backdoor Learning (ABL) and introduces an innovative method, End-to-End Anti-Backdoor Learning (E2ABL), for robust training against backdoor attacks. Unlike the original ABL, which employs a two-stage training procedure, E2ABL accomplishes end-to-end training through an additional classification head linked to the shallow layers of a Deep Neural Network (DNN). This secondary head actively identifies potential backdoor triggers, allowing the model to dynamically cleanse these samples and their corresponding labels during training. Our experiments reveal that E2ABL significantly improves on existing defenses and is effective against a broad range of backdoor attacks in both image and time series domains. © 2024, CC0.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Bounded Simultaneous Messages 43

Bounded Simultaneous Messages

引用

43rd IARCS Annual Conference on Foundations of Software technology and Theoretical computer Science, FSTTCS 2023

作者： Bogdanov, Andrej Dinesh, Krishnamoorthy Filmus, Yuval Ishai, Yuval Kaplan, Avi Sekar, Sruthi School of EECS University of Ottawa Canada Dept. of Computer Science and Engineering Indian Institute of Technology Palakkad India The Henry and Marylin Taub Faculty of Computer Science Technion Haifa Israel University of California BerkeleyCA United States

ISBN: (纸本)9783959773041

We consider the following question of bounded simultaneous messages (BSM) protocols: Can computationally unbounded Alice and Bob evaluate a function f(x, y) of their inputs by sending polynomial-size messages to a computationally bounded Carol? The special case where f is the mod-2 inner-product function and Carol is bounded to AC0 has been studied in previous works. The general question can be broadly motivated by applications in which distributed computation is more costly than local computation. In this work, we initiate a more systematic study of the BSM model, with different functions f and computational bounds on Carol. In particular, we give evidence against the existence of BSM protocols with polynomial-size Carol for naturally distributed variants of NP-complete languages. © 2023 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. All rights reserved.

关键词： Automata theory

来源：评论

学校读者我要写书评

暂无评论

Yolov8-Based Deep Learning Model for Improved Drone Intrusion Detection

Yolov8-Based Deep Learning Model for Improved Drone Intrusio...

引用

Technological Advancements in Computational Sciences (ICTACS), International Conference on

作者： Mohini Darji Khushi Patel Bansari Patel Krishna Thakkar Mehul Minat Meet K. Patel Computer Science & Engineering Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Gujarat India Department of Computer Science & Engineering Student of Bachelor of Technology Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Changa Gujarat India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

Real-time identification of unmanned aerial vehicle (drone) is a relatively growing nascent research area which leverages on deep learning and computer vision methods. However, the question arises as to possible dangers, and misuse of drones in different circumstances. These concerns are in respect to privacy, safety and security possible violations. Cameras and software are for example bundled in detection systems where visual information is used to facilitate the detection process. Thus, This Study was devoted to examining the object detection feature of the YOLO Only Look Once (YOLOv8) algorithm and its applicability for analyzing visual material captured by drones. One of the challenges in reviewing literature was to look for an online dataset of small drones and make it publicly available. Therefore, a real-world dataset was established accurately in this study and it includes small drones. The outcome presented in the document is expected to help understand the capability of the chosen models when one attempts to recognize drones in complex conditions. Further this shall serve as base on enhancing the development of even better and long-lasting anti-drone detection systems. The mentioned issues were addressed and solved with the help of the YOLOv8 architecture implementation, and the outstanding results were obtained: the mean average precision (mAP) of $\mathbf{9 3. 9 \%}$ , the precision of $\mathbf{9 2. 9 \%}$ , and the recall of $\mathbf{9 0. 3 \%}$ .

关键词： Deep learning YOLO Visualization Software algorithms Software Safety Security Drones Videos Testing

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：