检索结果-内蒙古大学图书馆

A Comparative Study of DeepLabCut and Other Open-Source Pupillometry Data Analysis Algorithms – Which to Choose?

Machine Graphics and Vision 2024年第2期33卷 77-90页

作者： Badkul, Amitesh Mishra, Sonakshi Kommajosyula, Srinivasa P. Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Department of Pharmacy Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States

Pupillometry measures pupil size, and several open-source algorithms are available to analyse pupillometry data. However, only a few studies compared these algorithms’ accuracy and computational resources. This study aims to compare the accuracy of computer vision-based algorithms (Swirski, Starburst, PuRe, ElSe, ExCuSe algorithms) and the machine learning algorithm, DeepLabCut, to the double-blinded human examiners (gold-standard). Training of DeepLabCut with different architectures and a variable number of markers (2-9 markers) was done on an open-source dataset. The duration of training was statistically longer for the ResNet152 model compared to the MobileNet model. The pupil diameters in computer vision-based software such as PuRe, Starburst, and Swirski were statistically different from human measurements. MobileNet 2 and 3 marker models were the closest to the human measurements. In conclusion, this work highlights the efficiency of lower marker models based on MobileNet architecture in DeepLabCut, which consumes fewer computational resources and is more accurate. © 2024 Institute of Information technology, Warsaw University of Life Sciences - SGGW. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Human Tactile Perception Using Vibration Data 23

Classification of Human Tactile Perception Using Vibration D...

引用

23rd International Conference on Cyberworlds, CW 2024

作者： Lee, Hyung-Tak Bak, Keungyonh Chun, Sungwoo Hwang, Han-Jeong Korea University Dept. Electronics and Information Engineering Sejong Korea Republic of Korea University Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Sejong Korea Republic of

ISBN: (纸本)9798331527174

To enhance the sense of reality in the VR environment, it is essential to incorporate not only visual and hearing but also tactile feedback. Previous studies related to tactile sensation have only focused on object classification to identify the object in contact with the tactile sensor. When people encounter a new object, they can use tactile perception information, such as roughness, to understand the object's attributes and functions. Therefore, for tactile research to be applicable in real-life scenarios, tactile perception classification is essential not only for classifying an object but also for recognizing its attributes and functions. This study aims to investigate the possibility of predicting roughness, one of the important human tactile perceptions, using deep learning models. We created 63 tactile samples, measured the vibration data of each sample using an acceleration sensor, and investigated how humans perceive the roughness of the tactile samples with five different levels. Object classification was performed using five deep learning models, among which the Shallow ConvNet achieved the highest performance, confirming its suitability as the most appropriate model for analyzing vibration data. Using the Shallow ConvNet, we attained a high accuracy of 98.6 ±5.6% for the identification of five levels of roughness, demonstrating that different levels of tactile perception information can be discriminated with high performance. © 2024 IEEE.

关键词： Deep learning Human tactile perception Roughness Vibration data Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Development of EEG-Based Optimal Biomarkers for Decoding Fatigue during Motor Imagery Tasks 13

Development of EEG-Based Optimal Biomarkers for Decoding Fat...

引用

13th International Winter Conference on Brain-Computer Interface, BCI 2025

作者： Lee, Jun-Seok Lee, Seung-Won Kim, Sang-Rok Hwang, Han-Jeong Dept. Electronics and Information Engineering Korea University Sejong30019 Korea Republic of Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong30019 Korea Republic of

ISBN: (纸本)9798331521929

This study aimed to identify electroencephalography (EEG)-based neurophysiological biomarkers for monitoring mental fatigue during motor imagery (MI) tasks. We used EEG data recorded from 29 healthy adults during MI tasks. For the preprocessing of the EEG data, we sequentially performed down-sampling into 200 Hz, independent component analysis (ICA), band-pass filtering between 0.5 and 50 Hz, and common average reference (CAR). The preprocessed EEG data were analyzed using a fast Fourier transform (FFT) to calculate spectral power in the δ (0.5–3 Hz), θ (4–7 Hz), α (8–13 Hz), and β (13–30 Hz) frequency bands. Subsequently, seventeen fatigue-related metrics were calculated using individual spectral powers and their combinations. These fatigue-related metrics were averaged for the frontal lobe (F3 and F4), central lobe (FCC3h and FCC4h), parietal lobe (P3 and P4), and occipital lobe (POO1 and POO2). The statistical significance of the average fatigue metrics was evaluated through Pearson correlation analysis with the sequence of trials. As a result, we observed strong positive correlations (r > 0.9, p © 2025 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Multiplexed Nanoscopy via Buffer Exchange

引用

ACS Nano 2024年第34期18卷 23445-23456页

作者： Chang, Ting-Jui Ben Yang, T. Tony Department of Electrical Engineering National Taiwan University Taipei10617 Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei10617 Taiwan Department of Physics National Taiwan University Taipei10617 Taiwan Nano Science and Technology Program Taiwan International Graduate Program Academia Sinica and National Taiwan University Taipei10617 Taiwan

Understanding cellular functions, particularly in their intricate complexity, can greatly benefit from the spatial mapping of diverse molecules through multitarget single-molecule localization microscopy (SMLM). Existing methodologies, primarily restricting the encoding dimensions to color and lifetime or requiring cyclic staining, often involve broad chromatic detection, specialized optical configurations, or sophisticated labeling techniques. Here, we propose a simple approach called buffer-exchange stochastic optical reconstruction microscopy (beSTORM), which introduces an additional dimension to differentiate between single molecules irrespective of their spectral properties. This method leverages the distinguishable photoblinking responses to distinct buffer conditions, offering a straightforward yet effective means of fluorophore discrimination. Through buffer exchanges, beSTORM achieves multitarget SMLM imaging with minimal crosstalk. Direct integration with expansion microscopy (ExM) demonstrates its capability to resolve up to six proteins at the molecular level within a single emission color without chromatic aberration. Overall, beSTORM presents a highly compatible imaging platform, promising significant advancements in highly multiplexed nanoscopy for exploring multiple targets in biological systems with nanoscale precision. © 2024 The Authors. Published by American Chemical Society.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A methodology for coffee price forecasting based on extreme learning machines

引用

Information Processing in Agriculture 2022年第4期9卷 556-565页

作者： Carolina Deina Matheus Henrique do Amaral Prates Carlos Henrique Rodrigues Alves Marcella Scoczynski Ribeiro Martins Flavio Trojan Sergio Luiz Stevan Jr Hugo Valadares Siqueira Department of Production Engineering Federal University of Rio Grande do Sul90.035-190Brazil Department of Electronics Federal University of TechnologyParana 84017-220Brazil Graduate Program in Production Engineering Federal University of TechnologyParana 84017-220Brazil

This work introduces a methodology to estimate coffee prices based on the use of Extreme Learning *** process is initiated by identifying the presence of nonstationary components,like seasonality and *** components are withdrawn if they are ***,the temporal lags are selected based on the response of the Partial Autocorre-lation Function *** predictors,we address the following models:Exponential Smooth-ing(ES),Autoregressive(AR)and Autoregressive Integrated and Moving Average(ARIMA)models,Multilayer Perceptron(MLP)and Extreme Learning Machines(ELMs)neural *** computational results based on three error metrics and two coffee types(Ara-bica and Robusta)showed that the neural networks,especially the ELM,can reach higher performance levels than the other *** methodology,which presents preprocess-ing stages,lag selection,and use of ELM,is a novelty that contributes to the coffee prices forecasting field.

关键词： Coffee price forecasting Linear models Artificial neural networks Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Energy Material for Extreme Environment: Unveiling Novel Self-Resilience of Hf1-xZrxO2 for Electrostatic Energy Storage (EES) and Pyroelectric Energy Harvesting (PEH)

Energy Material for Extreme Environment: Unveiling Novel Sel...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Liu, C.-H. Hsiang, K.-Y. Chang, F.-S. Chang, Y.-T. Liu, C.W. Lee, M.H. Program for Semiconductor Devices Materials and Hetero-integration Graduate School of Advanced Technology National Taiwan University Taipei Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan

ISBN: (纸本)9798350365429

The antiferroelectric (AFE) HfO2-based capacitor has been proposed as dual-functional for electrostatic energy storage and pyroelectric energy harvesting (PEH) for the first time. The partial-AFE (P-AFE) has a superior power and energy density capability of 1.46x1010 W/kg and 0.96 Wh/kg, respectively, as compared with state-of-the-art capacitors and cell batteries. Furthermore, the harvestable energy density (HED) of P-AFE was experimentally measured at an outstanding 10.37 J/cm3 within ΔT=223K (RT to 77K). The HfO2-based energy material is examined in low-temperature and X-ray irradiation and validates the degradation dominated by E-field cycling. The AFE capacitors inherently reflect the self-resilience effect and the physical mechanism of the fatigue and recovery are unveiled by VOs redistribution. There is great potential for utilizing benefits in energy storage and harvesting through the novel recovery strategy toward an unlimited lifetime of energy devices for extreme environments. © 2024 IEEE.

关键词： Capacitor storage

来源：评论

学校读者我要写书评

暂无评论

2D Polynomial Regression Modeling for Predictive Analysis of Glucose Concentration in NP-Model Fractal Microwave Sensor Using Frequency and Transmission Coefficient Disparities 13

2D Polynomial Regression Modeling for Predictive Analysis of...

引用

13th International Electrical Engineering Congress, iEECON 2025

作者： Nantapanich, Nutyada Mahatthanajatuphat, Pisit Wongsin, Norakamon Lee, Wilaiporn Rajamangala University of Technology Thanyaburi Faculty of Engineering Department of Electronics and Telecommunication Engineering Pathum Thani Thailand Yothinburana School Regular Program in Mathematics-Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331543952

The article introduces a two-dimensional polynomial regression model for the predictive analysis of glucose concentration in a fractal microwave sensor NP model, utilizing frequency and transmission coefficient differences to examine their correlation with glucose concentration levels. The sensor employed in this investigation is fabricated on an economical FR-4 substrate to minimize costs. The sensor structure is developed with the fractal structure reduction method established by the NP model to operate at a frequency of roughly 2.97 GHz. The CST Studio software is utilized to analyze the findings from the simulation of the suggested sensor structure. Furthermore, the proposed sensor is integrated into a test apparatus comprising a sensor platform and a liquid tube constructed from PPA material. The liquid under examination is a glucose and water mixture at varying concentrations. It was analyzed using a VNA instrument to evaluate its frequency response and the magnitude of the alteration in the transmission coefficient. The values are utilized to create a two-dimensional polynomial regression model. The experiments demonstrated that the proposed sensor model possesses an Adjusted R² value of 0.99499 and an average error of approximately 3.57% for glucose concentration analysis throughout the range of 5% to 30%, with sensitivities of 0.00879 dB/% for insertion loss and 0.092 MHz/% for frequency variation, facilitating accurate glucose concentration prediction analysis. © 2025 IEEE.

关键词： Polynomial regression

来源：评论

学校读者我要写书评

暂无评论

Minimal Yet Big Impact: How AI Agent Back-channeling Enhances Conversational Engagement through Conversation Persistence and Context Richness

Minimal Yet Big Impact: How AI Agent Back-channeling Enhance...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Jang, Jin Yea Shin, Saim Gweon, Gahgene Department of Intelligence and Information Seoul National University Korea Republic of Artificial Intelligence Research Center Korea Electronics Technology Institute Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

The increasing use of AI agents in conversational services, such as counseling, highlights the importance of back-channeling (BC) as an active listening strategy to enhance conversational engagement. BC improves conversational engagement by providing timely acknowledgments and encouraging the speaker to continue talking. This study investigates the effect of BC provided by an AI agent on conversational engagement, offering insights for the future design of AI conversational services. We conducted an experiment with 55 participants, divided into Todak_BC and Todak_NoBC groups based on the presence or absence of the BC feature in Todak, a conversational agent. Each participant engaged in nine sessions with predetermined subjects and questions. We collected and analyzed approximately 6 hours and 30 minutes of conversation logs to evaluate conversational engagement using both quantitative (conversation persistence, including conversation duration and number of utterances) and qualitative metrics (context richness, including self-disclosure and topic diversity). The findings reveal significantly higher conversational engagement in the Todak_BC group compared to the Todak_NoBC group across all metrics (p © 2024 Association for Computational Linguistics.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Characteristics of a High-impedance Folded Dipole Antenna in the Millimeter Wave Band

Characteristics of a High-impedance Folded Dipole Antenna in...

引用

2022 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2022

作者： Yamashiro, Koki Takashima, Yoshiki Noguchi, Keisuke Kanazawa Institute of Technology Graduate Program in Electrical Engineering and Electronics Ishikawa Nonoichi Japan Toko Electrical Constriction Chiyoda Tokyo Japan Kanazawa Institute of Technology Electrical and Electronics Engineering Ishikawa Nonoichi Japan

ISBN: (数字)9781665432382

ISBN: (纸本)9781665432382

Rectenna with high rectification efficiency is demanded for wireless power transfer systems. In order to improve rectification efficiency at mm-wave band, we study on high impedance antennas. This paper reports the characteristics of a folded dipole antenna consisting of open-Terminated two strips on an Alumina substrate. We designed the antenna with over 1000Ω at 28 GHz using EM simulator. As results, we obtained input resistance of 1463.7Ω with radiation efficiency of 86.7%. © 2022 IEEE.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

The design and evaluation of an AR-based serious game to teach programming

引用

Computers and Graphics (Pergamon) 2022年 103卷 1-18页

作者： Sharma, Vandit Bhagat, Kaushal Kumar Huang, Huai-Hsuan Chen, Nian-Shing Department of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur Kharagpur721302 India Advanced Technology Development Centre Indian Institute of Technology Kharagpur Kharagpur721302 India Institute for Research Excellence in Learning Sciences Program of Learning Sciences National Taiwan Normal University Taiwan

The ubiquity of smartphone and tablet devices, combined with the increasing availability of serious games, has enabled students to learn various abstract concepts in an appealing and convenient manner. While several researchers have explored the use of Augmented Reality (AR) in serious games, many of these games have not been critically explained or evaluated. To that end, we employed game-based learning methodologies and Game Learning Analytics (GLA) to systematize the design and evaluation of an AR-based serious game to teach programming. We evaluated our game for usability and effectiveness by conducting a user study on twenty-seven undergraduate students. The evaluation primarily consisted of a learning test conducted twice – before and after playing the game – along with a usability questionnaire that players completed after playing the game. Our results showed that players made significant progress after playing the game. The game helped players improve their basic programming skills, especially for the group having lower prior programming skills. The results highlighted various ways in which GLA can be used to benefit different stakeholders in the game. Based on players’ qualitative responses, we also identified several areas of improvement, most prominently the trade-off between ease of use and game complexity. We provide suggestions and discuss implications for future work. © 2022 Elsevier Ltd

关键词： Serious games

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：