检索结果-内蒙古大学图书馆

Single Modality and Joint Fusion for Emotion Recognition on RAVDESS Dataset

SN Computer Science 2024年第6期5卷 669页

作者： Haddad, Syrine Daassi, Olfa Belghith, Safya Laboratory of Robotics Informatics and Complex Systems (RISC Lab-LR16ES07) Tunis Tunisia National Engineering School of Tunis University of Tunis El manar Tunis 1002 Tunisia National Engineering School of Carthage University of Carthage Carthage 2035 Tunisia

Over the last decade, emotion recognition has become a widely researched area worth considering in any project related to affective computing. Due to the limitless applications of this new discipline, the development of emotion recognition systems has emerged as a lucrative opportunity in the corporate sector. Emotion recognition can be detected in many ways, such as face, speech, text, gestures, etc. Hence, this article presents a comprehensive survey of emotion recognition methods, focusing on three key modalities: visual, speech, and audio-visual. Moreover, a novel approach for each modality is proposed, and a comparative analysis is conducted with existing methods to assess their effectiveness. The results of this study revealed that face emotion recognition on the RAVDESS dataset can achieve good results compared to speech emotion recognition, which was the opposite case in previous literature. Combined modalities were found to likely achieve even better results with an accuracy of 89% compared to previous works. Finally, this article concludes by offering new insights and suggestions for future research. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computational models Face emotion recognition Multi-modal emotion recognition RAVDESS dataset Speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A ResNet-based approach for accurate radiographic diagnosis of knee osteoarthritis

引用

CAAI Transactions on Intelligence Technology 2022年第3期7卷 512-521页

作者： Yu Wang Shibo Li Baoliang Zhao Jianwei Zhang Yuanyuan Yang Bing Li School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhenChina Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina TAMS Department of InformaticsUniversity of HamburgHamburgGermany

Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring ***,individual scoring is subjective and error *** study proposes an approach for automated knee osteoarthritis classification based on deep neural *** knee X-ray images are first preprocessed with frequency-domain filtering and histogram normalisation,making the trabecular bone texture more obvious and benefiting the subsequent classification ***,a two-step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet-50 *** addition,a rebalance operation is proposed to deal with the dataset unbalance problem,and a quick search technique is proposed to improve the iterative search efficiency for the joint *** all of these techniques,a classification accuracy of 81.41%is obtained,which is higher compared to the state-of-the-art approaches.

关键词： AMSGrad knee osteoarthritis recognition ResNet VGG

来源：评论

学校读者我要写书评

暂无评论

Dynamic Cloth Manipulation Considering Variable Stiffness and Material Change Using Deep Predictive Model with Parametric Bias

arXiv

引用

arXiv 2024年

作者： Kawaharazuka, Kento Miki, Akihiro Bando, Masahiro Okada, Kei Inaba, Masayuki JSK Robotics Laboratory Department of Mechano-Informatics Graduate School of Information Science and Technology The University of Tokyo Bunkyo-ku Tokyo Japan

Dynamic manipulation of flexible objects such as fabric, which is difficult to modelize, is one of the major challenges in robotics. With the development of deep learning, we are beginning to see results in simulations and in some actual robots, but there are still many problems that have not yet been tackled. Humans can move their arms at high speed using their flexible bodies skillfully, and even when the material to be manipulated changes, they can manipulate the material after moving it several times and understanding its characteristics. Therefore, in this research, we focus on the following two points: (1) body control using a variable stiffness mechanism for more dynamic manipulation, and (2) response to changes in the material of the manipulated object using parametric bias. By incorporating these two approaches into a deep predictive model, we show through simulation and actual robot experiments that Musashi-W, a musculoskeletal humanoid with variable stiffness mechanism, can dynamically manipulate cloth while detecting changes in the physical properties of the manipulated object. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Dance Performance with a Humanoid Robot using a Real-time Gesture Responsive Framework

A Dance Performance with a Humanoid Robot using a Real-time ...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Hui-Ting Hong Chu-Yin Chen Arnaud Tanguy Abderrahmane Kheddar Laboratory of Image Arts and Contemporary Art (AIAC) Digital Images and Virtual Reality (INREV) Team University of Paris Saint-Denis France Montpellier Laboratory of Informatics Robotics and Microelectronics (LIRMM) CNRS–University of Montpellier France CNRS–AIST Joint Robotics Laboratory (JRL) Japan

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

We present a lightweight, real-time gesture responsive framework designed to investigate dynamics of human-robot interaction in live dance performances, merging aspects from choreography and robotics. In particular, it is tailored for artists to integrate human-sized humanoid robots into their dances seamlessly, offering an intuitive solution without the complexities of mastering robot control systems. Unlike existing interaction methods relying on wearable sensors or predetermined music cues, our framework, integrated in a task-space controller, enables the robot to dynamically respond to the dancer’s movements, generating unpredictable yet artistically meaningful gestures without the need for body-mounted sensors. This design choice emphasizes the artistic intention behind the improvisation, illustrating that it is not merely about creating movements spontaneously but rather a way of expression in intuition guided by perception. We assess our framework on the HRP-4 humanoid robot and the result has been successfully demonstrated in a public human-robot dance performance at the Arts Center of Enghien-les-Bains’s 23/24 season launch event, aiming to contribute to the exploration of co-creation between human and human-sized humanoid robot in improvised dance performances.

关键词： Art Robot control Merging Humanoid robots Human-robot interaction Robot sensing systems Transformers Real-time systems Complexity theory Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Type-2 Fuzzy Controller for Path Tracking of a Mobile Robot

Type-2 Fuzzy Controller for Path Tracking of a Mobile Robot

引用

Telecommunications and Intelligent Systems (ICTIS), International Conference on

作者： Mohammed Taqiyeddine Mahdi Mohamed Nadour Lakhmissi Cherroun Abrar Elaoua Ahmed Hafaifa Vicenc Puig Laboratory of Applied Automatic and Diagnostic Industriel (LAADI) University of Djelfa Algeria Institute of Robotics and Industrial Informatics Polytechnic University of Catalonia Barcelona Spain

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

This study introduces a Type-2 fuzzy logic control (FLC) approach for precise trajectory tracking of mobile robots, emphasizing its superiority in handling complex paths. Using a kinematic model, the proposed Type-2 FLC relies on expert knowledge to reduce tracking errors by adjusting robot movement based on calculated distance and angular discrepancies from the desired trajectory. The enhanced Type-2 fuzzy controller demonstrates significant accuracy and robustness, especially in challenging tracking scenarios, showcasing notable improvements in error reduction and control smoothness. Simulation results confirm that the proposed approach outperforms other methods, highlighting its potential for applications requiring reliable and precise navigation.

关键词： Fuzzy logic Uncertainty Trajectory tracking Simulation Robustness Trajectory Telecommunications Mobile robots Time factors Testing

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Diagnostic Observers for Linear Systems Based on Optimal Control Methods

Synthesis of Diagnostic Observers for Linear Systems Based o...

引用

2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022

作者： Kabanov, Aleksey A. Zuev, Aleksandr V. Zhirabok, Aleksey N. Filaretov, Vladimir F. Department of Informatics and Control in Technical Systems Sevastopol State University Russia Laboratory of Intelligent Information Systems for Marine Robots Institute of Marine Technology Problems FEB RAS Russia Department of Automation and Robotics Far Eastern Federal University Russia Robotics Laboratory Institute of Automation and Control Processes FEB RAS Russia

ISBN: (数字)9781665497947

ISBN: (纸本)9781665497947

The paper considers the problem of fault identification in dynamic systems described by linear differential equations. To solve this problem, diagnostic observers constructed on the basis of optimal control methods are used. The proposed new method for the synthesis of such observers is based on the idea of introducing a new system with some auxiliary control which plays a role of an unknown vector function describing emerging faults. This control is proposed to be formed in such a way that it provides a minimum for the residual functional. Unlike popular approaches to solving the problem of fault identification based on observers operating in a sliding mode, the proposed method allows us to expand the class of systems for which the identification problem can be solved. It is known that the methods of sliding mode observers design impose certain restrictions on the systems under consideration. The suggested theory is illustrated by an example. The simulation results confirmed the operability of the diagnostic observers synthesized using the method proposed in the work. © 2022 IEEE.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

A New Defect Model due to a Dust Particle Affecting the Fingers of FinFET Logic Gates

A New Defect Model due to a Dust Particle Affecting the Fing...

引用

Latin American Test Workshop, LATW

作者： Victor Champac Freddy Forero Michel Renovell Leonardo Miceli Optics and Electronics (INAOE) National Institute for Astrophysics Puebla Mexico Laboratory of Informatics Robotics and Microelectronics of Montpellier (LIRMM) France

The continuous scaling in semiconductor technolo- gies has allowed faster devices with lower power consumption. FinFET technology has become an attractive candidate for high-performance and power-efficient applications. This paper proposes a new defect model that could occur in FinFET technology using Self-Aligned Double Patterning (SADP) and replacement metal gate (RMG) process. This new defect was found by analyzing the impact of a single dust particle in the manufacturing process flux. A single dust particle disconnects two gate transistors from their inputs, and both the two disconnected inputs and the two disconnected gates have a zero-resistance bridge defect. The logic and delay behavior of the defect are analyzed using SPICE electrical simulator. A unique behavior is observed for the defect, whose detection can be missed by existing test generation methodologies. The test pattern conditions to detect the defect using boolean and delay test techniques are determined, showing that the defect requires specific test generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning based control framework for robot gear assembly with demonstration learning and force feedback

A reinforcement learning based control framework for robot g...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Wenjie Tang Yiming Jiang Chao Zeng Hui Zhang Hang Zhong College of Robotics Hunan University ChangSha China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen China Department of Informatics Universität Hamburg Hamburg Germany

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

Reinforcement learning (RL) has found extensive application in robotic manipulation tasks, particularly in scenarios involving contact-rich activities such as axis-hole assembly and spot welding. However, existing methodologies encounter several key limitations: difficulties in gathering real-world experimental data, slow reward convergence leading to suboptimal strategy performance, and a significant disparity between simulation and reality. This paper introduces a novel framework aimed at over-coming these limitations in the context of robotic gear assembly. Initially, we capture the assembly trajectory executed by a human expert through manual guidance, subsequently incorporating this expert experience into an experience pool. Leveraging the Deep Deterministic Policy Gradient (DDPG) algorithm, along with demonstrations, force feedback, and domain randomization, we train the policy until achieving satisfactory results in simulation. We establish the simulation environment within the MuJoCo simulator and validate the proposed method in real-world gear shaft assembly tasks. Experimental results showcase the robustness and efficacy of our framework in successfully completing assembly tasks.

关键词： Shafts Gears Force feedback Reinforcement learning Spot welding Robustness Trajectory

来源：评论

学校读者我要写书评

暂无评论

Step by Step Building and Evaluation of Low-Cost Capacitive Technology Touch System for Human-Social Robot Interaction

Step by Step Building and Evaluation of Low-Cost Capacitive ...

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Konstantinos Tsirkas Anna-Maria Velentza N. Fachantidis School of Educational & Social Policy University of Macedonia Thessaloniki Greece Laboratory of Informatics and Robotics Applications in Education and Society (LIRES) University of Macedonia Greece

The development of social robots aims to create machines that can interact and collaborate with people in a natural way. To achieve this, social robots must be designed to make people feel physically and psychologically comfortable with them, with haptic communication being a crucial factor. Capacitive touch technology has been implemented in robotics for sensing contact in various areas of a robot's body during human-robot interaction. However, there is a need for low-cost haptic systems that can be easily built and deployed by professionals without engineering backgrounds, such as educators. This study presents a low-cost haptic system built with consumer materials and tested for accuracy and user experience. Results show that the system is more than 80% accurate and persistent and has a high score in user experience across users from different backgrounds. We used Adafruit MPR121, Arduino and 3D printed materials. The system can be easily adapted to different robotic systems and hard materials to enhance human-robot interaction for various social applications. The study highlights the importance of developing low-cost and accessible haptic systems for social robots, which can help increase trust and acceptance of these machines in everyday life.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Droplet 3D cryobioprinting for fabrication of free-standing and volumetric structures

Aggregate

引用

Aggregate 2024年第5期5卷 433-444页

作者： Joshua Weygant Ali Entezari Fritz Koch Ricardo AndréGalaviz Carlos Ezio Garciamendez Pável Hernández Vanessa Ortiz David Sebastián Rendon Ruiz Francisco Aguilar Andrea Andolﬁ Ling Cai Sushila Maharjan Anayancy Osorio Yu Shrike Zhang Division of Engineering in Medicine Department of MedicineBrigham and Women’s HospitalHarvard Medical SchoolCambridgeMassachusettsUSA School of Biomedical Engineering University of Technology SydneyBroadwayNew South WalesAustralia Laboratory for Bioinspired Materials for Biomedical Engineering IMTEK—Department of Microsystems EngineeringUniversity of FreiburgFreiburgGermany Department of Informatics BioengineeringRobotics and Systems Engineering(DIBRIS)University of GenovaGenovaItaly Department of Engineering University of CambridgeCB21PZ CambridgeUK

Droplet-based bioprinting has shown remarkable potential in tissue engineering and regenerative ***,it requires bioinks with low viscosities,which makes it challenging to create complex 3D structures and spatially pattern them with different *** study introduces a novel approach to bioprinting sophisti-cated volumetric objects by merging droplet-based bioprinting and cryobioprinting *** leveraging the beneﬁts of cryopreservation,we fabricated,for theﬁrst time,intricate,self-supporting cell-free or cell-laden structures with single or multiple materials in a simple droplet-based bioprinting process that is facilitated by depositing the droplets onto a cryoplate followed by crosslinking during *** feasibility of this approach is demonstrated by bioprinting several cell types,with cell viability increasing to 80%–90%after up to 2 or 3 weeks of ***,the applicational capabilities of this approach are showcased by bio-printing an endothelialized breast cancer *** results indicate that merging droplet and cryogenic bioprinting complements current droplet-based bioprinting techniques and opens new avenues for the fabrication of volumetric objects with enhanced complexity and functionality,presenting exciting potential for biomedical applications.

关键词： 3D bioprinting biofabrication cryogenic bioprinting droplet printing inkjet tissue engineering

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：