检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Yoo, Eunsoo Choi, Kyungrak Park, Hangue Sungkyunkwan University Department of MetaBioHealth Suwon Korea Republic of Texas A & M University Department of Electrical and Computer Engineering United States Sungkyunkwan University Department of Biomedical Engineering Department of Intelligent Precision Healthcare Convergence Department of MetaBioHealth Suwon Korea Republic of

ISBN: (纸本)9798331530839

Designing effective human-machine interfaces requires understanding complex interactions between humans and machines. However, even bi-directional communication that relies on sensor data is often insufficient due to the unpredictability of human behaviors. To better anticipate these behaviors, a computational model that reflects the operating principles of the human nervous system is essential. This study presents a computational neuromechanical model that focuses on human sensorimotor operations, particularly in the context of elbow joint rotation. The model leverages reinforcement learning (RL) to simulate the brain's reward mechanism in motor adjustment, with the reward function adjusted by a multiplication constant (M) that reflects individual variability in sensorimotor processing. Measurement and simulation data were evaluated based on their overlap ratios. The test results demonstrate that the RL-based model, when calibrated with an optimal M value, closely matches with measured motor outputs, indicating its potential for improving the effectiveness of the human-machine interface. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving the quality of diffuse optical tomography reconstruction with APU-Net: an attention-based physical U-Net model 16

Improving the quality of diffuse optical tomography reconstr...

引用

Optical Tomography and Spectroscopy of Tissue XVI 2025

作者： Xue, Minghao Li, Shuying Zhu, Quing Biomedical Engineering Department Washington University in St. Louis St. LouisMO63130 United States Electrical and Computer Engineering Department Boston University BostonMA02215 United States Electrical and Systems Engineering Department Washington University in St. Louis St. LouisMO63130 United States

ISBN: (纸本)9781510683761

Traditional diffuse optical tomography (DOT) reconstructions suffer from image artifacts due to various factors such as the proximity of DOT sources to shallow lesions, poor optode-tissue coupling, tissue heterogeneity, and large high-contrast lesions causing shadowing effects. This study introduces an attention-based U-Net (APU-Net) model with Contextual Transformer (CoT) attention modules to enhance DOT image quality and improve lesion diagnostic accuracy. Trained on simulation and phantom data, and evaluated on clinical data, the APU-Net model effectively reduced artifacts by 26.83% on average and significantly improved image contrast in deeper regions, with increases of 20.28% and 45.31% for the second and third target layers, respectively. These improvements demonstrate the potential of the APU-Net model in enhancing DOT reconstructions for better breast cancer diagnosis. © 2025 SPIE.

关键词： Tumor growth modeling Data modeling Image restoration Systems modeling Diffuse optical tomography Image enhancement Image quality Medical image reconstruction Commercial off the shelf technology Transformers

来源：评论

学校读者我要写书评

暂无评论

Stability Assessment of Ultramicroelectrode Arrays in Neural Stimulation: An Electrochemical Impedance Spectroscopy Analysis 46

Stability Assessment of Ultramicroelectrode Arrays in Neural...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Dong, Qiwei Ezeh, Cynthia Wu, Yupeng Hetke, Jamille F. Cogan, Stuart Orazem, Mark E. Otto, Kevin J. University of Florida Department of Electrical & Computer Engineering United States University of Florida Department of Chemical Engineering United States The University of Texas Department of Bioengineering Department of Material Sciences & Engineering Dallas United States NeuroNexus United States University of Florida J. Crayton Pruitt Family Department of Biomedical Engineering United States

ISBN: (纸本)9798350371499

The overall focus of this research program is to investigate the viability and safety of microelectrode arrays (MEAs) and ultramicroelectrode arrays (UMEAs) for microstimulation (μStim) in the brain. We aim to assess their potential to deliver adequate electrical stimulation for neural activation without causing electrode or tissue damage. To this end, here we conducted galvanostatic Electrochemical Impedance Spectroscopy (EIS) to assess the behavior of electrodes of various diameters both pre- and post-stimulation in a rat model. Our first-generation electrode arrays (G1) were designed with electrode diameters spanning 3 orders of magnitude and including subcellular dimensions. Using these devices, we delivered 0.4 nC/phase stimulation in vivo. We conducted in vitro EIS measurements before and after the current pulsing. Our findings show that these electrode arrays, including UMEAs, exhibit stable electrochemical behavior following a 0.4 nC/phase current pulse. To validate the EIS frequency range used for the G1 measurements, we designed a second-generation electrode array (G2) that included a terminating lead and a looping lead. This array provided the ability to assess the accuracy contour plot of our EIS system and electrode array platform. This exploratory research contributes to the ongoing knowledge of UMEAs in μStim applications. These developments may result in high-fidelity, non-damaging multichannel μStim, and improved neuromodulation technology for the treatment of neural diseases and injuries. © 2024 IEEE.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Representations of fricatives in subcortical model responses: Comparisons with human consonant perceptiona)

Representations of fricatives in subcortical model responses...

引用

作者： Hamza, Yasmeen Farhadi, Afagh Schwarz, Douglas M. McDonough, Joyce M. Carney, Laurel H. Department of Biomedical Engineering University of Rochester RochesterNY14627 United States Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States Depts. of Neuroscience and Biomedical Engineering University of Rochester RochesterNY14627 United States Department of Linguistics University of Rochester RochesterNY14627 United States Depts. of Biomedical Engineering Neuroscience and Electrical and Computer Engineering University of Rochester RochesterNY14627 United States

Fricatives are obstruent sound contrasts made by airflow constrictions in the vocal tract that produce turbulence across the constriction or at a site downstream from the constriction. Fricatives exhibit significant intra/intersubject and contextual variability. Yet, fricatives are perceived with high accuracy. The current study investigated modeled neural responses to fricatives in the auditory nerve (AN) and inferior colliculus (IC) with the hypothesis that response profiles across populations of neurons provide robust correlates to consonant perception. Stimuli were 270 intervocalic fricatives (10 speakers × 9 fricatives × 3 utterances). Computational model response profiles had characteristic frequencies that were log-spaced from 125 Hz to 8 or 20 kHz to explore the impact of high-frequency responses. Confusion matrices generated by k-nearest-neighbor subspace classifiers were based on the profiles of average rates across characteristic frequencies as feature vectors. Model confusion matrices were compared with published behavioral data. The modeled AN and IC neural responses provided better predictions of behavioral accuracy than the stimulus spectra, and IC showed better accuracy than AN. Behavioral fricative accuracy was explained by modeled neural response profiles, whereas confusions were only partially explained. Extended frequencies improved accuracy based on the model IC, corroborating the importance of extended high frequencies in speech perception. © 2023 Acoustical Society of America.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Multimodal Bio Cryptography for Securing Cloud Computing using Convolutional Neural Network 2

Multimodal Bio Cryptography for Securing Cloud Computing usi...

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Mammo, Andualem Fantahun Kassahun, Habitamu Endalamaew Gandhi, Smiley Gupta, Shashi Kant Salau, Ayodeji Olalekan Onibonoje, Moses Oluwafemi Kishore Kanna, R. University of Gondar Electrical and Computer Engineering Gondar Ethiopia Galgotias University Greater Noida Uttar Pradesh Greater Noida201310 India Eudoxia Research University Department of Computer Science and Engineering United States Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Biomedical Engineering Chennai India

ISBN: (纸本)9798350364699

Cloud computing has grown in popularity as a storage platform that makes use of the internet to provide users with large amounts of data storage. The cloud's client base has grown throughout time, and access for consumers and businesses has expanded. At this time, security concerns develop among the cloud community. Different harmful assaults occur on well-known cloud services by exploiting weak password providers, causing them to lose confidentiality. Cryptography has evolved into an autonomous data encryption method, which allows users to manually cipher/decipher information. Secure keys can be generated using biometric key generation, eliminating the need for remembering. However, usability concerns persist since biometric credentials are required every time a file is encrypted or decrypted. This study focuses on multimodal biometrics, which will create a non-intrusive key for cryptography algorithms to encrypt/decrypt the file uploaded to the cloud by the client. To achieve this, this paper presents a convolutional neural networks approach which extract features from face and fingerprint biometrics and trains them to understand the patterns that are to be classified. Multi-label categorization features were employed as output labels, which were hashed to 512 bits from each of the multimodal biometrics and could be combined to yield 1024 bits for RSA cryptography encryption and decryption. False acceptance and rejection rates were utilized to assess the whole system. As a result, the face exhibits 2.13% FAR and the fingerprint 2.71% FAR on average. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Physical and Perceptual Features for Deepfake Audio Detection 1

A Comparative Study on Physical and Perceptual Features for ...

引用

1st International Workshop on Deepfake Detection for Audio Multimedia, DDAM 2022

作者： Li, Menglu Ahmadiadli, Yasaman Zhang, Xiao-Ping Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University TorontoON Canada

ISBN: (纸本)9781450394963

Audio content synthesis has stepped into a new era and brought a great threat to daily life since the development of deep learning techniques. The ASVSpoof Challenge and the ADD Challenge have been launched to motivate the development of Deepfake audio detection algorithms. Currently, the detection models, which consist of front-end feature extractors and back-end classifiers, utilize the physical features mainly, rather than the perceptual features that relate to natural emotions or breathiness. Therefore, we provide a comprehensive study on 16 physical and perceptual features and evaluate their effectiveness in both Track 1 and Track 2 of the ADD Challenge. Based on results, PLP, as a perceptual feature, outperforms the rest of the features in Track 1, while CQCC has the best performance in Track 2. Our experiments demonstrate the significance of perceptual features in detecting Deepfake audios. We also seek to explore the underlying characteristics of features that can distinguish Deepfake audio from a real one. We perform statistical analysis on each feature to show its distribution differences on real and synthesized audios. This paper will provide a potential direction in selecting appropriate feature extraction methods for the future implementation of detection models. © 2022 Association for Computing Machinery.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fractional Brownian motion with fluctuating diffusivities

引用

Physical Review E 2024年第1期110卷 014105-014105页

作者： Adrian Pacheco-Pozo Diego Krapf Department of Electrical and Computer Engineering and School of Biomedical Engineering <a href="https://***/03k1gpj17">Colorado State University</a> Fort Collins Colorado 80523 USA.

Despite the success of fractional Brownian motion (fBm) in modeling systems that exhibit anomalous diffusion due to temporal correlations, recent experimental and theoretical studies highlight the necessity for a more comprehensive approach of a generalization that incorporates heterogeneities in either the tracers or the environment. This work presents a modification of Lévy's representation of fBm for the case in which the generalized diffusion coefficient is a stochastic process. We derive analytical expressions for the autocovariance function and both ensemble- and time-averaged mean squared displacements. Further, we validate the efficacy of the developed framework in two-state systems, comparing analytical asymptotic expressions with numerical simulations.

关键词： Anomalous diffusion Fractional Brownian motion Disordered systems Statistical methods

来源：评论

学校读者我要写书评

暂无评论

Automated Deep Learning Pipeline for Accurate Segmentation of Aortic Lumen and Branches in Abdominal Aortic Aneurysm: A Two-Step Approach 2

Automated Deep Learning Pipeline for Accurate Segmentation o...

引用

2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024

作者： Hassan, Fatma N. Mahmoud, Ahmed M. Elnokrashy, Ahmed F. Hassan, Ashraf Y. Benha University Benha Faculty of Engineering Department of Electrical Engineering Benha Egypt Cairo University Department of Biomedical Engineering and Systems Giza Egypt Astute Imaging KirklandWA98033 United States Nile University Department of Computer Science Technology and Computer Science Giza Egypt Benha University Benha Egypt

ISBN: (纸本)9798350362633

Abdominal Aortic Aneurysm (AAA) is a serious medical condition characterized by the abnormal enlargement of the abdominal aorta. If left untreated, AAA can have life-threatening consequences. Accurate segmentation of the aorta in Computed Tomography Angiography (CTA) images plays a vital role in treatment planning for AAA. However, manual and semi-automatic segmentation methods suffer from limitations in terms of time and accuracy. This study presents a deep learning pipeline that aims to fully automate the precise and efficient segmentation of the aorta and its branches within CTA images. A two-step approach is proposed for the segmentation of the aorta and its branches in contrast-enhanced CTA scans. The first step involves utilizing a UNet++ model to perform aortic segmentation across the entire set of CTA axial slices. In the second step, a post processing algorithm is employed to track the continuity of the segmented aorta while effectively discarding false positive (FP) objects. The assessment of the fully automated method revealed remarkable outcomes, with a mean Dice coefficient of 0.941 on a test set consisting of 10 CTA scans. The automated segmentation results are utilized to create a comprehensive 3D model. The study results indicate that the utilization of the proposed deep learning-based pipeline is highly effective in achieving accurate segmentation of the aortic lumen and its branches. The practical implications of this approach extend to pre-operative planning. This highlights the valuable contribution of the proposed method in improving the management and treatment of patients diagnosed with aortic aneurysm. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Using Random Forest and Linear SVM for Dyslexia Classification on Hebb-Williams Mazes 59

Using Random Forest and Linear SVM for Dyslexia Classificati...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Kaushik, Padmanabh Yu, Yih-Choung Gabel, Lisa Lafayette College Department of Electrical and Computer Engineering EastonPA18042 United States Lafayette College Department of Psychology and Neuroscience Program EastonPA18042 United States

ISBN: (纸本)9798331513269

Dyslexia is a learning disability that negatively impacts an individual's ability to read, write, spell, and sometimes speak. It results in difficulties in recognizing and decoding words and patterns, despite normal level of education and intelligence. Studies have shown that early detection of dyslexia is vital for improving learning abilities in young children. Many virtual platforms exist for diagnosing and rehabilitating dyslexia;however, most require tests that measure reading skills. Since developing reading capabilities can delay the detection of dyslexia, a gaming platform based on Hebb-Williams mazes has been developed. This platform does not rely on reading skills and can diagnose dyslexia in young children. This paper presents a machine learning driven approach using two algorithms - Random Forest and Linear SVM - to classify reading abilities based on data from participants performing virtual maze tasks, which are indicative of symptoms of dyslexia. Results from this study indicate that it is possible to predict dyslexia with up to 95% accuracy based on a participant's performance in virtual gaming environments. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Reward-Driven Clustered Federated Learning for DRL Based UAV-RIS Networks 8

Reward-Driven Clustered Federated Learning for DRL Based UAV...

引用

8th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2023

作者： Wong, Yi Jie Tham, Mau-Luen Kwan, Ban-Hoe Iqbal, Amjad Lee, Ying Loong Chang, Yoong Choon Universiti Tunku Abdul Rahman Department of Electrical and Electronic Engineering Kajang Malaysia Universiti Tunku Abdul Rahman Department of Mechatronics and Biomedical Engineering Kajang Malaysia Carleton University Department of System and Computer Engineering Canada

ISBN: (纸本)9798350315516

Deep reinforcement learning (DRL) has empowered numerous reconfigurable intelligent surface (RIS) aided millimeter-wave unmanned aerial vehicle (UAV) communications. However, most existing works often employ single-Task DRL, that could only handle one specific environment (or task). This hurdles the large-scale adoption of DRL-based UAV-RIS networks, since the environment has infinite variations. In this paper, we aim to solve diverse UAV-RIS tasks with a minimum number of DRLs required. Specifically, we proposed a reward-driven clustering technique to autonomously cluster all 50 simulated tasks into 10 clusters. For each cluster, we train a multi-Task DRL using Federated Learning to handle all tasks in the cluster. Simulation shows that given 50 unique tasks, the proposed method could reduce the total agents required from 50 to 10, which is a 5-fold reduction. © 2023 IEEE.

关键词： Reinforcement learning

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

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

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：