Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)最新文献_第8页

PUMA: Deep Metric Imitation Learning for Stable Motion Primitives PUMA：针对稳定运动原型的深度度量模仿学习

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-10-14 DOI: 10.1002/aisy.202400144

Rodrigo Pérez-Dattari, Cosimo Della Santina, Jens Kober

{"title":"PUMA: Deep Metric Imitation Learning for Stable Motion Primitives","authors":"Rodrigo Pérez-Dattari, Cosimo Della Santina, Jens Kober","doi":"10.1002/aisy.202400144","DOIUrl":"https://doi.org/10.1002/aisy.202400144","url":null,"abstract":"Imitation learning (IL) facilitates intuitive robotic programming. However, ensuring the reliability of learned behaviors remains a challenge. In the context of reaching motions, a robot should consistently reach its goal, regardless of its initial conditions. To meet this requirement, IL methods often employ specialized function approximators that guarantee this property by construction. Although effective, these approaches come with some limitations: 1) they are typically restricted in the range of motions they can model, resulting in suboptimal IL capabilities, and 2) they require explicit extensions to account for the geometry of motions that consider orientations. To address these challenges, we introduce a novel stability loss function that does not constrain the function approximator's architecture and enables learning policies that yield accurate results. Furthermore, it is not restricted to a specific state space geometry; therefore, it can easily incorporate the geometry of the robot's state space. Proof of the stability properties induced by this loss is provided and the method is empirically validated in various settings. These settings include Euclidean and non-Euclidean state spaces, as well as first-order and second-order motions, both in simulation and with real robots. More details about the experimental results can be found at https://youtu.be/ZWKLGntCI6w.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 11","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142664707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Versatile Standing Wave Generation Between Arbitrarily Oriented Surfaces Using Acoustic Metasurface Deflectors and Retroreflectors

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-10-13 DOI: 10.1002/aisy.202400474

Chadi Ellouzi, Farhood Aghdasi, Ali Zabihi, Amir K. Miri, Chen Shen

{"title":"Versatile Standing Wave Generation Between Arbitrarily Oriented Surfaces Using Acoustic Metasurface Deflectors and Retroreflectors","authors":"Chadi Ellouzi, Farhood Aghdasi, Ali Zabihi, Amir K. Miri, Chen Shen","doi":"10.1002/aisy.202400474","DOIUrl":"https://doi.org/10.1002/aisy.202400474","url":null,"abstract":"Acoustic wave devices using standing wave configurations have gained interest in various fields like healthcare diagnostics and manufacturing. Their functionalities span from cell sorting to microscale fiber assembly through periodic acoustic pressure fields. Conventional methods usually require parallel acoustic emitters and reflective surfaces, producing constrained standing wave patterns. In this paper, an effective approach for creating versatile acoustic standing wave fields using an acoustic metasurface deflector and retroreflector is introduced. The deflector manipulates the direction of incoming acoustic waves coupled with the retroreflector to reflect these waves back to the source. The proposed design allows the creation of standing waves that are not constrained by the relative angles of the two surfaces involved and allows for customizable wave patterns beyond the standard limits with enhanced adaptability. The system's effectiveness is evaluated through computational simulations using finite element analysis and experimental validation based on a 3D-printed prototype. Results suggest that versatile standing waves between arbitrarily oriented surfaces can be produced through the careful design of the metasurface deflector and retroreflector. This approach can improve the performance of standing wave applications in particle manipulation, thus broadening the range of practical implementations for ultrasound and acoustofluidic technologies.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400474","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D Head Pose Estimation via Normal Maps: A Generalized Solution for Depth Image, Point Cloud, and Mesh 通过法线贴图估计 3D 头部姿势：深度图像、点云和网格的通用解决方案

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-10-13 DOI: 10.1002/aisy.202400159

Jiang Wu, Hua Chen

{"title":"3D Head Pose Estimation via Normal Maps: A Generalized Solution for Depth Image, Point Cloud, and Mesh","authors":"Jiang Wu, Hua Chen","doi":"10.1002/aisy.202400159","DOIUrl":"https://doi.org/10.1002/aisy.202400159","url":null,"abstract":"Head pose estimation plays a crucial role in various applications, including human–machine interaction, autonomous driving systems, and 3D reconstruction. Current methods address the problem primarily from a 2D perspective, which limits the efficient utilization of 3D information. Herein, a novel approach, called pose orientation-aware network (POANet), which leverages normal maps for orientation information embedding, providing abundant and robust head pose information, is introduced. POANet incorporates the axial signal perception module and the rotation matrix perception module, these lightweight modules make the approach achieve state-of-the-art (SOTA) performance with few computational costs. This method can directly analyze various topological 3D data without extensive preprocessing. For depth images, POANet outperforms existing methods on the Biwi Kinect head pose dataset, reducing the mean absolute error (MAE) by ≈30% compared to the SOTA methods. POANet is the first method to perform rigid head registration in a landmark-free manner. It also incorporates few-shot learning capabilities and achieves an MAE of about <math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>1</mn>\u0000 <mo>°</mo>\u0000 </mrow>\u0000 <annotation>$1^{circ}$</annotation>\u0000 </semantics></math> on the Headspace dataset. These features make POANet a superior alternative to traditional generalized Procrustes analysis for mesh data processing, offering enhanced convenience for human phenotype studies.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 11","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400159","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142664857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development of a Machine-Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-10-08 DOI: 10.1002/aisy.202400308

Sonia Hermoso-Durán, Nicolas Fraunhoffer, Judith Millastre-Bocos, Oscar Sanchez-Gracia, Pablo F. Garrido, Sonia Vega, Ángel Lanas, Juan Iovanna, Adrián Velázquez-Campoy, Olga Abian

{"title":"Development of a Machine-Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy","authors":"Sonia Hermoso-Durán, Nicolas Fraunhoffer, Judith Millastre-Bocos, Oscar Sanchez-Gracia, Pablo F. Garrido, Sonia Vega, Ángel Lanas, Juan Iovanna, Adrián Velázquez-Campoy, Olga Abian","doi":"10.1002/aisy.202400308","DOIUrl":"https://doi.org/10.1002/aisy.202400308","url":null,"abstract":"Pancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scanning calorimetry (DSC) of blood serum samples, thermal liquid biopsy (TLB), combined with machine-learning (ML) analysis, may offer a more efficient method for diagnosing PDAC. Serum samples from a cohort of 212 PDAC patients and 184 healthy controls are studied. DSC thermograms are analyzed using ML models. The generated models are built applying algorithms based on penalized regression, resampling, categorization, cross validation, and variable selection. The ML-based model demonstrates outstanding ability to discriminate between PDAC patients and control subjects, with a sensitivity of 90% and an area under the ROC receiver operating characteristic curve of 0.83 in the training and test groups. Application of the model to an independent validation cohort of 113 PDAC patients confirms its robustness and utility as a diagnosis tool. The application of ML to serum TLB data emerges as a promising methodology for early diagnosis, representing a significant advance for detecting and managing PDAC, envisaging a minimally invasive and more efficient methodology for identifying biomarkers.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400308","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

H-PME: Development of a Robot Skin Using Halbach Array Permanent Magnet Elastomer

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-10-08 DOI: 10.1002/aisy.202400325

Qichen Wang, Devesh Abhyankar, Yushi Wang, Peizhi Zhang, Tito Pradhono Tomo, Shigeki Sugano, Mitsuhiro Kamezaki

{"title":"H-PME: Development of a Robot Skin Using Halbach Array Permanent Magnet Elastomer","authors":"Qichen Wang, Devesh Abhyankar, Yushi Wang, Peizhi Zhang, Tito Pradhono Tomo, Shigeki Sugano, Mitsuhiro Kamezaki","doi":"10.1002/aisy.202400325","DOIUrl":"https://doi.org/10.1002/aisy.202400325","url":null,"abstract":"This article presents a novel 3-axis Halbach permanent magnet elastomer (H-PME) sensor for the robotic application, which effectively reduces crosstalk along when two sensors are used simultaneously in close proximity, for example, during grasping of thin and delicate objects, needle threading, etc. This sensor integrates a Halbach-array magnetic elastomer, a 3×3 Hall sensor matrix, and a silicone layer. The magnetic elastomer is produced by combining NdFeB powders with a diameter of 5 μm into silicone, following a weight ratio of 50%, and then magnetized using 2D Halbach-array magnets. Simulation results reveal the capability to adjust magnetic field strength and distribution by altering the magnet's orientation. The sensor's efficacy in 3-axis sensing is validated through calibration with a linear model, achieving a good root-mean-square error below 0.7 N in force measurement. The H-PME sensor, with a thickness of merely 4.5 mm, can detect forces up to 50 N. It's simple 3-layer design allows the thickness to be reduced to as low as 2 mm, while also offering ease of replacement. Crucially, crosstalk evaluation experiments show that the proposed H-PME sensor can dramatically mitigate crosstalk interference.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 2","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400325","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DeepSLM: Speckle-Licensed Modulation via Deep Adversarial Learning for Authorized Optical Encryption and Decryption DeepSLM：通过深度对抗学习进行斑点许可调制，实现授权光学加密和解密

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-09-30 DOI: 10.1002/aisy.202400150

Haofan Huang, Qi Zhao, Huanhao Li, Yuandong Zheng, Zhipeng Yu, Tianting Zhong, Shengfu Cheng, Chi Man Woo, Yi Gao, Honglin Liu, Yuanjin Zheng, Jie Tian, Puxiang Lai

{"title":"DeepSLM: Speckle-Licensed Modulation via Deep Adversarial Learning for Authorized Optical Encryption and Decryption","authors":"Haofan Huang, Qi Zhao, Huanhao Li, Yuandong Zheng, Zhipeng Yu, Tianting Zhong, Shengfu Cheng, Chi Man Woo, Yi Gao, Honglin Liu, Yuanjin Zheng, Jie Tian, Puxiang Lai","doi":"10.1002/aisy.202400150","DOIUrl":"https://doi.org/10.1002/aisy.202400150","url":null,"abstract":"Optical encryption is pivotal in information security, offering parallel processing, speed, and robust security. The simplicity and compatibility of speckle-based cryptosystems have garnered considerable attention. Yet, the predictable statistical distribution of speckle optical fields’ characteristics can invite statistical attacks, undermining these encryption methods. The proposed solution, a deep adversarial learning-based speckle modulation network (DeepSLM), disrupts the strong intercorrelation of speckle grains. Utilizing the unique encoding properties of speckle patterns, DeepSLM facilitates license editing within the modulation phase, pioneering a layered authentication encryption system. Our empirical studies confirm DeepSLM's superior performance on key metrics. Notably, the testing dataset reveals an average Pearson correlation coefficient above 0.97 between decrypted images and their original counterparts for intricate subjects like human faces, attesting to the method's high fidelity. This innovation marries adjustable modification, optical encryption, and deep learning to enforce tiered data access control, charting new paths for creating user-specific access protocols.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 11","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400150","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142665164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A High-Precision Dynamic Movement Recognition Algorithm Using Multimodal Biological Signals for Human–Machine Interaction

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-09-30 DOI: 10.1002/aisy.202400483

Chenhao Cao, Gang Ma, Zelin Chen, Yiming Ouyang, Hu Jin, Shiwu Zhang

{"title":"A High-Precision Dynamic Movement Recognition Algorithm Using Multimodal Biological Signals for Human–Machine Interaction","authors":"Chenhao Cao, Gang Ma, Zelin Chen, Yiming Ouyang, Hu Jin, Shiwu Zhang","doi":"10.1002/aisy.202400483","DOIUrl":"https://doi.org/10.1002/aisy.202400483","url":null,"abstract":"Accurate recognition of human dynamic movement is essential for seamless human–machine interaction (HMI) across various domains. However, most of the existing methods are single-modal movement recognition, which has inherent limitations, such as limited feature representation and instability to noise, which will affect its practical performance. To address these limitations, this article proposes a novel fusion approach that can integrate two biological signals, including electromyography (EMG) and bioelectrical impedance (BI). The fusion method combines EMG for capturing dynamic movement features and BI for discerning key postures representing discrete points within dynamic movements. In this method, the identification of key postures and their temporal sequences provide a guiding framework for the selection and weighted correction of probability prediction matrices in EMG-based dynamic recognition. To verify the effectiveness of the method, six dynamic upper limb movements and nine key postures are defined, and a Universal Robot that can follow movements is employed for experimental validation. Experimental results demonstrate that the recognition accuracy of the dynamic movement reaches 96.2%, representing an improvement of nearly 10% compared with single-modal signal. This study illustrates the potential of multimodal fusion of EMG and BI in movement recognition, with broad prospects for application in HMI fields.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400483","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analog Sequential Hippocampal Memory Model for Trajectory Learning and Recalling: A Robustness Analysis Overview

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-09-30 DOI: 10.1002/aisy.202400282

Daniel Casanueva-Morato, Alvaro Ayuso-Martinez, Giacomo Indiveri, Juan P. Dominguez-Morales, Gabriel Jimenez-Moreno

{"title":"Analog Sequential Hippocampal Memory Model for Trajectory Learning and Recalling: A Robustness Analysis Overview","authors":"Daniel Casanueva-Morato, Alvaro Ayuso-Martinez, Giacomo Indiveri, Juan P. Dominguez-Morales, Gabriel Jimenez-Moreno","doi":"10.1002/aisy.202400282","DOIUrl":"https://doi.org/10.1002/aisy.202400282","url":null,"abstract":"The rapid expansion of information systems in all areas of society demands more powerful, efficient, and low-energy consumption computing systems. Neuromorphic engineering has emerged as a solution that attempts to mimic the brain to incorporate its capabilities to solve complex problems in a computationally and energy-efficient way in real time. Within neuromorphic computing, building systems to efficiently store the information is still a challenge. Among all the brain regions, the hippocampus stands out as a short-term memory capable of learning and recalling large amounts of information quickly and efficiently. Herein, a spike-based bio-inspired hippocampus sequential memory model is proposed that makes use of the benefits of analog computing and spiking neural networks (SNNs): noise robustness, improved real-time operation, and energy efficiency. This model is applied to robotic navigation to learn and recall trajectories that lead to a goal position within a known grid environment. The model is implemented on the special-purpose SNNs mixed-signal DYNAP-SE hardware platform. Through extensive experimentation together with an extensive analysis of the model's behavior in the presence of external noise sources, its correct functioning is demonstrated, proving the robustness and consistency of the proposed neuromorphic sequential memory system.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143121312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Review on Recent Trends of Bioinspired Soft Robotics: Actuators, Control Methods, Materials Selection, Sensors, Challenges, and Future Prospects

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-09-30 DOI: 10.1002/aisy.202400414

Abhirup Sarker, Tamzid Ul Islam, Md. Robiul Islam

{"title":"A Review on Recent Trends of Bioinspired Soft Robotics: Actuators, Control Methods, Materials Selection, Sensors, Challenges, and Future Prospects","authors":"Abhirup Sarker, Tamzid Ul Islam, Md. Robiul Islam","doi":"10.1002/aisy.202400414","DOIUrl":"https://doi.org/10.1002/aisy.202400414","url":null,"abstract":"Bioinspired soft robotics is an emerging field that aims to develop flexible and adaptive robots inspired by the movement and capabilities of biological organisms. This review article examines recent advances in materials, actuation mechanisms, sensors, and control strategies and discusses the challenges and future prospects of bioinspired soft robotics. Key innovations highlighted include pneumatic, elastomer actuators, variable-length shape memory alloy tendons, closed-loop control with soft sensors, and the incorporation of soft materials including shape memory polymers and conductive composites. Challenges in soft robotics such as achieving complex motion control, incorporating feedback systems, modeling soft material dynamics, and replicating biological muscle efficiency with artificial muscles are also discussed. Promising future directions are explored including the integration of biodegradable materials, machine learning-based control algorithms, and leveraging data-driven techniques for modeling and control. Building on progress in multi-functional materials, manufacturing techniques, and bioinspired design principles, soft robots hold considerable promise for expanding robot capabilities, enhancing versatility and adaptability, enabling applications from wearable assistive devices to search and rescue operations. This review provides a holistic perspective encompassing key drivers propelling innovations in the vibrant field of bioinspired soft robotics.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400414","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143633130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN

IF 6.8

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2024-09-30 DOI: 10.1002/aisy.202400359

Changqi Sun, Hao Xu, Yuntian Chen, Dongxiao Zhang

{"title":"AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN","authors":"Changqi Sun, Hao Xu, Yuntian Chen, Dongxiao Zhang","doi":"10.1002/aisy.202400359","DOIUrl":"https://doi.org/10.1002/aisy.202400359","url":null,"abstract":"Explainable artificial intelligence (XAI) aims to develop transparent explanatory approaches for “black-box” deep learning models. However, it remains difficult for existing methods to achieve the trade-off of the three key criteria in interpretability, namely, reliability, understandability, and usability, which hinder their practical applications. In this article, we propose a self-supervised automatic semantic interpretable explainable artificial intelligence (AS-XAI) framework, which utilizes transparent orthogonal embedding semantic extraction spaces and row-centered principal component analysis (PCA) for global semantic interpretation of model decisions in the absence of human interference, without additional computational costs. In addition, the invariance of filter feature high-rank decomposition is used to evaluate model sensitivity to different semantic concepts. Extensive experiments demonstrate that robust and orthogonal semantic spaces can be automatically extracted by AS-XAI, providing more effective global interpretability for convolutional neural networks (CNNs) and generating human-comprehensible explanations. The proposed approach offers broad fine-grained extensible practical applications, including shared semantic interpretation under out-of-distribution (OOD) categories, auxiliary explanations for species that are challenging to distinguish, and classification explanations from various perspectives. In a systematic evaluation by users with varying levels of AI knowledge, AS-XAI demonstrated superior “glass box” characteristics.","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"6 12","pages":""},"PeriodicalIF":6.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400359","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143253796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0