检索结果-内蒙古大学图书馆

Mediterranean Conference on Control and Automation (MED)

作者： Loizos Hadjiloizou Evagoras Makridis Themistoklis Charalambous Kyriakos M. Deliparaschos Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Electrical and Computer Engineering and Informatics Department Cyprus University of Technology Limassol Cyprus

We present a multisensor fusion framework for the onboard real-time navigation of a quadrotor in an indoor environment. The framework integrates sensor readings from an Inertial Measurement Unit (IMU), a camera-based object detection algorithm, and an Ultra-WideBand (UWB) localisation system. Often the sensor readings are not always readily available, leading to inaccurate pose estimation and hence poor navigation performance. To effectively handle and fuse sensor readings, and accurately estimate the pose of the quadrotor for tracking a predefined trajectory, we design a Maximum Correntropy Criterion Kalman Filter (MCC-KF) that can manage intermittent observations. The MCC-KF is designed to improve the performance of the estimation process when is done with a Kalman Filter (KF), since KFs are likely to degrade dramatically in practical scenarios in which noise is non-Gaussian (especially when the noise is heavy-tailed). To evaluate the performance of the MCC-KF, we compare it with a previously designed Kalman filter by the authors. Through this comparison, we aim to demonstrate the effectiveness of the MCC-KF in handling indoor navigation missions. The simulation results show that our presented framework offers low positioning errors, while effectively handling intermittent sensor measurements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamics of cold random hyperbolic graphs with link persistence

引用

Physical Review E 2022年第6期106卷 064312-064312页

作者： Sofoclis Zambirinis Harrison Hartle Fragkiskos Papadopoulos Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology 3036 Limassol Cyprus Network Science Institute Northeastern University Boston Massachusetts 02115 USA

We consider and analyze a dynamic model of random hyperbolic graphs with link persistence. In the model, both connections and disconnections can be propagated from the current to the next snapshot with probability ω∈[0,1). Otherwise, with probability 1−ω, connections are reestablished according to the random hyperbolic graphs model. We show that while the persistence probability ω affects the averages of the contact and intercontact distributions, it does not affect the tails of these distributions, which decay as power laws with exponents that do not depend on ω. We also consider examples of real temporal networks, and we show that the considered model can adequately reproduce several of their dynamical properties. Our results advance our understanding of the realistic modeling of temporal networks and of the effects of link persistence on temporal network properties.

关键词： Evolving networks Random graphs

来源：评论

学校读者我要写书评

暂无评论

Harnessing Data Mining for Improved Hindi Isolated Speech Recognition

Harnessing Data Mining for Improved Hindi Isolated Speech Re...

引用

Futuristic Technologies in Control Systems & Renewable Energy (ICFCR), International Conference on

作者： Ayasha Malik Veena Parihar Shrikant Mapari Malathy Sathyamoorthy Shilpa Saini Department of CSE IIMT College of Engineering (AKTU) Greater Nida India Symbiosis Institute of Geo-informatics Symbiosis International (Deemed University) Pune India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) Pune India Department of Information Technology KPR Institute of Engineering and Technology Coimbatore India Chandigarh University Mohali

ISBN: (数字)9798331504601

ISBN: (纸本)9798331504618

Speech is the primary medium for the exchange and transfer of messages, making recognition of speech an extensive area of study. The phonic and linguistic outline is probable for this, mostly for the English verbal. In India, a considerable portion of the population faces challenges to communicate in English. Henceforward, English speech detection is not useful for such persons. The recognition method of Hindi words is an integral segment of the automatic speech detection technique that has been proposed in this paper. The primary objective of Automatic Speech Recognition (ASR) is to recognize and interpret spoken input from a device or microphone and convert it into a textual document to execute the appropriate action. The procedure of detecting speech solely relies on the abstraction of attributes and the detection of patterns within the content. This research paper employs the Hidden Markov Model (HMM) along with the Hidden Markov Toolkit (HMT) and Pratt software for attribute detection. In the proposed scheme, a set of data is apprehended having 10 Hindi words: from “Shunya” to “Nau” (Shunya, Ek, Do, Teen, Chaar, Paanch, Chae, Saat, Aath, Nau) from the 15 voices of different age group then applying training along with testing over the set of data. The projected structure computes and compares the Linear Predictive Coding (LPC), Perceptual Linear Prediction (PLP), and Mel Frequency Cepstral Coefficients (MFCC) algorithms. These algorithms are applied to talker-reliant ASR and talker-free ASR in sound-dependent and word-based environments to figure out the top feature mining technique which is MFCC in our proposed system.

关键词： Voice activity detection Training Renewable energy sources Hidden Markov models Speech recognition Prediction algorithms Software Data mining Mel frequency cepstral coefficient Testing

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Hospital Readmissions Using Logistic Regression and IoT Sensor Data 6

Predictive Analytics for Hospital Readmissions Using Logisti...

引用

6th International Conference on Energy, Power and Environment, ICEPE 2024

作者： Kiruthiga, B. Riazulhameed, Arshadh Ariff Mohamed Abuthahir Rajapriya, M. Sarasu, R. Mohankumar, N. Kasthuri, A. Srm Valliammai Engineering College Department of Management Studies Tamil Nadu Chennai India Blackstraw Technologies Pvt Ltd Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Management Studies Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Spatial Informatics Tamil Nadu Chennai India Maharashtra Nagpur India Vinayaka Mission's Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India

ISBN: (纸本)9798350379297

Hospital readmissions affect healthcare systems globally, increasing costs and morbidity. Readmissions must be predicted and prevented to improve patient outcomes and save healthcare costs. This research leverages the Internet of Things (IoT) sensor data and Logistic Regression (LR) to reduce hospital readmissions using predictive analytics. Patient health data from IoT devices during and after hospitalization is used in the paper. Heart rate, blood pressure, and oxygen saturation are constantly monitored. LR is used to examine this dataset and create a prediction model. The LR algorithm trains us to recognize IoT sensor data patterns and correlations that indicate readmission risks. Our methodology provides developed risk estimates incorporating patient-specific parameters, including age, multiple illnesses, and medical history. The temporal data permits dynamic predictions, considering patient health changes over time. This research detected hospital readmission risk with promising accuracy. These predictions allow healthcare practitioners to proactively intervene and deliver targeted treatments, including prescription modifications, lifestyle advice, and follow-up consultations to decrease readmission. This proactive strategy may improve patient outcomes and save healthcare expenses. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Classifying Upper Extremity Motor Function Using Deep Learning and Third-Person Video Data

Classifying Upper Extremity Motor Function Using Deep Learni...

引用

IEEE International Conference on Big Data

作者： Tan Tran Lin-Ching Chang Peter Lum Department of Electrical Engineering and Computer Science The Catholic University of America Washington DC USA Department of Informatics New Jersey Institute of Technology Newark NJ USA Department of Biomedical Engineering The Catholic University of America Washington DC USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Post-stroke rehabilitation of upper extremity (UE) motor function is essential. Despite the widespread use of UE rehabilitation in clinical settings, assessing the success of these treatments is challenging. Methods for evaluating UE motor function include task performance under clinical supervision, patient self-reports, and data analysis from wearable devices equipped with accelerometers and gyroscopes. In prior research, we demonstrated that machine learning and deep learning models using data from a single wrist-worn accelerometer sensor could accurately differentiate between functional and non-functional UE movements in stroke patients. To overcome the limitations of single wrist-worn accelerometer sensors – challenges in capturing the full context of functional movements – this study presents a new deep learning (DL) based framework designed to classify functional and non-functional arm movements in videos captured from a conventional camera. The system is entirely automated and comprises two DL networks. The first network performs human pose estimation, extracting 2D pose key points of the paretic arm(s) and torso on 2-second sequences of the frames. The second network then uses these 2D pose landmarks to classify the movement sequence as functional or non-functional. This system offers two key benefits for rehabilitation. First, it can automatically generate initial annotations for video frames, significantly reducing the time needed for manual labeling. Second, analyzing the effectiveness of UE rehabilitation through third-person videos allows for objective outcome measurement of UE treatments in stroke survivors' home environments.

关键词： Deep learning Accelerometers Torso Pose estimation Manuals Stroke (medical condition) Motors Cameras Wearable devices Videos

来源：评论

学校读者我要写书评

暂无评论

MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network

MSEMG: Surface Electromyography Denoising with a Mamba-based...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yu-Tung Liu Kuan-Chen Wang Rong Chao Sabato Marco Siniscalchi Ping-Cheng Yeh Yu Tsao Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Department of Computer Science and Information Engineering National Taiwan University Taiwan University of Palermo Italy

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Surface electromyography (sEMG) recordings can be contaminated by electrocardiogram (ECG) signals when the monitored muscle is closed to the heart. Traditional signal processing-based approaches, such as high-pass filtering and template subtraction, have been used to remove ECG interference but are often limited in their effectiveness. Recently, neural network-based methods have shown greater promise for sEMG denoising, but they still struggle to balance both efficiency and effectiveness. In this study, we introduce MSEMG, a novel system that integrates the Mamba state space model with a convolutional neural network to serve as a lightweight sEMG denoising model. We evaluated MSEMG using sEMG data from the Non-Invasive Adaptive Prosthetics database and ECG signals from the MIT-BIH Normal Sinus Rhythm Database. The results show that MSEMG outperforms existing methods, generating higher-quality sEMG signals using fewer parameters.

关键词： Adaptation models Databases Computational modeling Surface contamination Noise reduction Interference Electrocardiography Electromyography Speech processing Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Enabling light coupling between nanowires and low refractive index contrast optical waveguides towards scalable quantum circuits 28

Enabling light coupling between nanowires and low refractive...

引用

Integrated Optics: Devices, Materials, and Technologies XXVIII 2024

作者： Tsintzos, Symeon I. Tsimvrakidis, Konstantinos Sinani, Alexandra Gates, James C. Elshaari, Ali W. Smith, Peter G. R. Zwiller, Val Riziotis, Christos Theoretical and Physical Chemistry Institute National Hellenic Research Foundation Athens11635 Greece Department of Informatics and Computer Engineering University of West Attica Egaleo12243 Greece Optoelectronics Research Centre University of Southampton SouthamptonSO17 1BJ United Kingdom Stockholm106 91 Sweden Institute for Advanced Modelling and Simulation University of Nicosia Nicosia2417 Cyprus Qubitech Quantum Technologies Chalandri Athens15231 Greece

ISBN: (纸本)9781510670389

A primary constraint in the major photonic integration platform of Silica-on-Silicon, especially when combined with fabrication approaches like Direct Laser Writing is the optical waveguides' low refractive index contrast, leading thus to limitations for efficient coupling with currently available state-of-the-art single photon emitters such as semiconductor nanowires with quantum dots (NWQD). We propose and demonstrate a novel approach to drastically enhance the light coupling between silica based Laser-written channel waveguides and NWQDs, by incorporating an optical microsphere in their intermediate space. It is demonstrated that the induced photonic nanojet action of a suitably designed microsphere illuminated by the NWQD, excites efficiently the channel waveguide's modes and can enable light coupling to a degree even above 50%. The proposed method is reasonably robust to imperfections and misalignments and could be implemented by current state-of-the-art micro/nano patterning techniques. It is anticipated that the practical implementation of the method will allow the integration of multiple quantum emitters in silica based hybrid integrated circuits thus enabling their scalability towards for quantum computing and sensing applications. © 2024 SPIE.

关键词： Silica

来源：评论

学校读者我要写书评

暂无评论

When Sign Language Meets Semantic Communications 35

When Sign Language Meets Semantic Communications

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Kouvakis, Vasileios Trevlakis, Stylianos E. Boulogeorgos, Alexandros-Apostolos A. Tsiftsis, Theodoros Singh, Keshav Qi, Nan InnoCube P.C. Department of Research and Development 17th Noemvriou 79 Thessaloniki55535 Greece University of Western Macedonia Department of Electrical and Computer Engineering Kozani50100 Greece University of Thessaly Department of Informatics & Telecommunications Lamia35100 Greece Institute of Communications Engineering National Sun Yat-sen University Kaohsiung804 Taiwan Nanjing University of Aeronautics and Astronautics Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing210016 China

ISBN: (纸本)9798350362244

This paper presents an American sign language (ASL) semantic communications scheme. The scheme consists of a semantic encoder that leverages a convolutional neural network to effectively utilize the ASL alphabet. The encoded information is transmitted with the 24-QAM quadrature amplitude modulation (QAM). Additionally, this paper introduces a dataset that involves the overlaying of red-green-blue landmarks and key-points onto the acquired images, thereby augmenting the depiction of hand posture. The quantification of the proposed system's training, testing, and communication performance is accomplished through numerical results, which serve to emphasize the attainable benefits and stimulate meaningful discussions. © 2024 IEEE.

关键词： Quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Tweet Analysis Algorithms Using Natural Language Processing and Machine Learning Models

A Comparative Analysis of Tweet Analysis Algorithms Using Na...

引用

International Workshop on Semantic Media Adaptation and Personalization (SMAP)

作者： Andreas Kanavos Nikos Antonopoulos Ioannis Karamitsos Phivos Mylonas Department of Informatics Ionian University Corfu Greece Department of Digital Media and Communication NeMeCULAB Ionian University Argostoli Greece Department of Graduate and Research Rochester Institute of Technology Dubai UAE Department of Informatics and Computer Engineering University of West Attica Athens Greece

Online Social Networks (OSNs) have become integral platforms for information sharing, attracting both legitimate users and spammers. Detecting and mitigating spam within these networks pose significant challenges due to the dynamic nature of content and user behavior. In this paper, we present a comprehensive comparative analysis of algorithms for tweet analysis, focusing on Natural Language Processing (NLP) and Machine Learning (ML) models. We evaluate these algorithms through sentiment analysis and multiple attribute analysis, utilizing diverse methodologies and datasets. Our study explores feed-forward neural networks, Bayesian classifiers, and transformer-based models for NLP tasks, achieving high prediction accuracy and insightful metrics such as precision, recall, and F1 score. Furthermore, we delve into multiple attribute analysis using Random Forest, Logistic Regression, and Gradient Boosting algorithms. Through a systematic exploration of various approaches, this work contributes to a deeper understanding of spam detection and sentiment analysis within the context of OSNs, paving the way for enhanced social network security and content analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Glaucoma Detection Using Deep Learning Approach in research Detection

Expression of Concern for: Glaucoma Detection Using Deep Lea...

引用

Advances in Computing, Communication and Applied informatics (ACCAI), International Conference on

作者： Anil Pandurang Shinde Ramandeep Singh Renuka Shantappa Anami Noor Mohammed R. Selvameena Ashwini Jotiram Patil Department of Computer Technology Bharati Vidyapeeth's Jawaharlal Nehru Institute of Technology (Poly) Pune Maharashtra Department of Computer Science Guru Nanak Khalsa College Daroli Kalan Jalandhar Jalandhar Punjab Department of Computer Technology Bharati Vidyapeeth's Jawaharlal Nehru Institute of Technology (Poly) Pune Department of Computer Science Engineering Graphic Era Deemed to be University Dehradun Uttrakhand Department of Computer Science and Engineering Dr.M.G.R Educational and Research Institute Chennai TamilNadu India

ISBN: (数字)9798350315905

ISBN: (纸本)9798350315912

An persistent eye infection called glaucoma causes irreversible vision loss. A crucial problem in the clinical field is glaucoma identification. There have been very few studies designed to detect glaucoma in its early stages. However, using current techniques to carry out glaucoma infection detection was ineffective. Moreover, the conventional glaucoma infection diagnosis method required additional time. Glaucoma identification in various fundus images is a challenging task that necessitates mastery and extensive training. Glaucoma is an ocular neuropathy characterized by mild retinal ganglion cell degeneration. There are several different types of glaucoma, each having a unique a etiology and set of pathogenic factors, but they all have alterations in the structure and function of the optic nerve that are essentially universal. Convolution organisations, a type of deep learning computation, have swiftly emerged as a method for making decisions while analyzing clinical images. A chronic eye condition called glaucoma causes irreversible vision loss. In this section, we discuss two state-of-the-art glaucoma detection methods in the light of deep learning. The glaucoma dataset is used in this deep learning computation proposed for glaucoma photo analysis. This finding contrasts with convolutional brain network grouping techniques in the context of deep learning. Each rating indicates that the newly proposed worldview is more favorable than the one currently in use.

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：