Article
Computer Science, Artificial Intelligence
Mara Graziani, Lidia Dutkiewicz, Davide Calvaresi, Jose Pereira Amorim, Katerina Yordanova, Mor Vered, Rahul Nair, Pedro Henriques Abreu, Tobias Blanke, Valeria Pulignano, John O. Prior, Lode Lauwaert, Wessel Reijers, Adrien Depeursinge, Vincent Andrearczyk, Henning Muller
Summary: Since its emergence in the 1960s, Artificial Intelligence (AI) has been widely applied to various technology products and fields. Machine learning, as a major part of current AI solutions, achieves high performance on various tasks through learning from data and experience. However, the interpretability of AI models, especially deep neural networks, is often challenging. Different domains have different requirements for interpretability and tools for debugging and validating models. In this paper, the authors propose a unified terminology and definition of interpretability in AI systems, aiming to improve clarity and efficiency in the regulation of ethical and reliable AI development, and to facilitate communication across interdisciplinary areas of AI.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Remote Sensing
Shin-nosuke Ishikawa, Masato Todo, Masato Taki, Yasunobu Uchiyama, Kazunari Matsunaga, Peihsuan Lin, Taiki Ogihara, Masao Yasui
Summary: We propose a method called What I Know (WIK) in explainable artificial intelligence (XAI) to provide additional information for verifying the reliability of deep learning models. This method demonstrates an instance in the training dataset that is similar to the input data to be inferred in a remote sensing image classification task. It helps determine whether the training dataset is sufficient for each inference and validates the validity of the model's inferences by checking the selected example data.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Computer Science, Artificial Intelligence
Michal Kolarik, Martin Sarnovsky, Jan Paralic, Frantisek Babic
Summary: Deep learning has shown effectiveness in medical diagnostic tasks compared to traditional machine learning methods, but its black-box nature hinders its real-world applications, especially in healthcare. Explainability of machine learning models is crucial for their adoption in clinical use, and this article reviews the approaches and applications of explainable deep learning in the specific area of medical video processing tasks. The article introduces the field of explainable AI, summarizes the important requirements for explainability in medical applications, provides an overview of existing methods and evaluation metrics, and focuses on those applicable to video data analysis in the medical domain. It also identifies open research issues in this area.
PEERJ COMPUTER SCIENCE
(2023)
Review
Neurosciences
Farzad V. Farahani, Krzysztof Fiok, Behshad Lahijanian, Waldemar Karwowski, Pamela K. Douglas
Summary: Deep neural networks have revolutionized computer vision and medical imaging. However, the lack of transparency in these models hinders their widespread adoption. Explainable artificial intelligence (XAI) techniques offer insights into the decision-making process of neural networks. This article reviews recent applications of post-hoc relevance techniques in neuroimaging and proposes a method for comparing the reliability of XAI methods in deep neural networks.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Biochemical Research Methods
Md Rezaul Karim, Tanhim Islam, Md Shajalal, Oya Beyan, Christoph Lange, Michael Cochez, Dietrich Rebholz-Schuhmann, Stefan Decker
Summary: Artificial intelligence (AI) systems are widely used for solving critical problems in bioinformatics, biomedical informatics, and precision medicine. However, the lack of transparency in complex AI models can be a challenge in understanding their decision-making processes. Explainable AI (XAI) aims to provide transparency and fairness in AI systems, which is particularly important in sensitive areas like healthcare. This paper discusses the importance of explainability in bioinformatics and showcases model-specific and model-agnostic interpretable ML methods that can be customized for bioinformatics research problems. Through case studies, the authors demonstrate how XAI methods can improve transparency and decision fairness in bioinformatics.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Chemistry, Multidisciplinary
Junkang An, Yiwan Zhang, Inwhee Joe
Summary: In this paper, a novel interpretable artificial intelligence (XAI) method called LIME is proposed to interpret deep learning models of tabular data. The specific-input approach using feature importance and partial dependency plots (PDPs) is used. Experimental results show that this approach improves interpretation stability, compensates for the problem of local interpretations, and achieves a balance between global and local interpretations.
APPLIED SCIENCES-BASEL
(2023)
Review
Computer Science, Theory & Methods
Meike Nauta, Jan Trienes, Shreyasi Pathak, Elisa Nguyen, Michelle Peters, Yasmin Schmitt, Joerg Schloetterer, Maurice Van Keulen, Christin Seifert
Summary: The evaluation of explanations for machine learning models is a complex concept that should not be solely based on subjective validation. This study identifies 12 conceptual properties that should be considered for a comprehensive assessment of explanation quality. The evaluation practices of over 300 papers introducing explainable artificial intelligence (XAI) methods in the past 7 years were systematically reviewed, finding that one-third of the papers exclusively relied on anecdotal evidence and one-fifth evaluated with users. The study also provides an extensive overview of quantitative XAI evaluation methods, offering researchers and practitioners concrete tools for validation and benchmarking.
ACM COMPUTING SURVEYS
(2023)
Article
Biochemical Research Methods
An-Phi Nguyen, Stefania Vasilaki, Maria Rodriguez Martinez
Summary: Interpretability is crucial for machine learning models in critical scenarios. We propose FLAN, a structurally constrained deep neural network that processes each input feature separately, allowing users to estimate the effect of each feature independently.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Chemistry, Multidisciplinary
Jan Paralic, Michal Kolarik, Zuzana Paralicova, Oliver Lohaj, Adam Jozefik
Summary: Deep neural network models have achieved significant results in various challenging tasks, including medical diagnostics. To establish the credibility of these black-box models in the medical field, it is important to focus on their explainability. While there have been studies combining deep learning methods with explainability methods for analyzing medical image data, the explainability of stream data, such as electrocardiograms (ECGs), has been largely unexplored. This article addresses the explainability of black-box models for stream data from 12-lead ECGs and proposes a perturbation explainability method that is validated through a user study with medical students. The results highlight the effectiveness of the proposed method and the importance of integrating multiple data sources in the diagnostic process.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Ali Raza, Kim Phuc Tran, Ludovic Koehl, Shujun Li
Summary: In this study, a novel end-to-end framework is proposed for ECG-based healthcare using explainable artificial intelligence and deep convolutional neural networks in a federated setting. The framework addresses challenges such as data availability and privacy concerns, and provides interpretability of the classification results, aiding clinical practitioners in decision-making.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Nakyeong Yang, Jeongje Jo, Myeongjun Jeon, Wooju Kim, Juyoung Kang
Summary: The launch of academic search engines has allowed researchers to access scholarly materials for free, leading to a rapid increase in academic literature. However, information overload makes it challenging for researchers to find relevant studies or researchers with similar interests.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Environmental Sciences
Abhirup Dikshit, Biswajeet Pradhan
Summary: Accurately predicting natural hazards, especially drought, is challenging. Including climatic variables in data-driven prediction models improves accuracy. Using explainable artificial intelligence models can help understand local interactions during different drought conditions and periods.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Review
Chemistry, Analytical
Ahmad Chaddad, Jihao Peng, Jian Xu, Ahmed Bouridane
Summary: Artificial intelligence with deep learning is widely used in medical imaging and healthcare tasks. To be a viable tool, AI needs to mimic human judgment and interpretation skills. Explainable AI aims to explain the information behind the black-box model of deep learning that reveals how decisions are made.
Article
Genetics & Heredity
Jan Henric Klau, Carlo Maj, Hannah Klinkhammer, Peter M. Krawitz, Andreas Mayr, Axel M. Hillmer, Johannes Schumacher, Dominik Heider
Summary: Polygenic risk scores (PRS) calculate disease risk based on weighted sum of associated alleles from genetic loci estimated by regression models. Recent advances enable creation of polygenic predictors for complex traits and diseases, influenced by multiple genetic variants, each with negligible effect on overall risk. Study finds that adding additional PRS from other diseases and using machine learning models, like deep learning, improves overall predictive performance significantly.
FRONTIERS IN GENETICS
(2023)
Article
Computer Science, Artificial Intelligence
Xiao-Hui Li, Caleb Chen Cao, Yuhan Shi, Wei Bai, Han Gao, Luyu Qiu, Cong Wang, Yuanyuan Gao, Shenjia Zhang, Xun Xue, Lei Chen
Summary: The rapid development of Artificial Intelligence presents challenges in explaining AI models. A best explaining practice should leverage causal information and hidden scenarios in the data itself. However, there is currently a lack of clear taxonomy and systematic review in this area.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Automation & Control Systems
Zhao-Xu Yang, Hai-Jun Rong, Pak Kin Wong, Plamen Angelov, Zhi-Xin Yang, Hang Wang
Summary: The SEDCPID controller is constructed using fuzzy rules and data clouds, and has the advantage of evolving structure and simultaneously adapting parameters in an online manner.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Computer Science, Artificial Intelligence
Eduardo Soares, Plamen P. Angelov, Bruno Costa, Marcos P. Gerardo Castro, Subramanya Nageshrao, Dimitar Filev
Summary: This article introduces a novel approach to developing explainable machine learning models by approximating a deep reinforcement learning model with IF-THEN rules and enhancing interpretability through visualizing rules. Experimental results demonstrate the effective interpretability of specific DRL agents and the potential extension to a broader set of deep neural network models.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Plamen Angelov, Eduardo Soares
Summary: The paper introduces a new classification method and algorithm that can autonomously detect and learn new classes, with training guided by a minimal amount of labeled data samples. The algorithm automatically selects input features based on data density, generating an interpretable model based on data distribution prototypes.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Chemistry, Analytical
Ritesh Vyas, Bryan M. Williams, Hossein Rahmani, Ricki Boswell-Challand, Zheheng Jiang, Plamen Angelov, Sue Black
Summary: The knuckle creases on the dorsal side of the hand can be used to identify offenders of serious crime when other recognizable biometric traits are not available. This paper proposes an ensemble approach using multiple object detector frameworks to accurately localize the knuckle regions. The effectiveness of the approach is tested on large-scale hand databases and its superiority over individual detectors is shown.
Article
Computer Science, Artificial Intelligence
Zhao-Xu Yang, Hai-Jun Rong, Pak Kin Wong, Plamen Angelov, Chi Man Vong, Chi Wai Chiu, Zhi-Xin Yang
Summary: This paper proposes an intelligent engine knock detection system based on engine vibration signals, utilizing VMD for signal filtering and IMF selection, GA for parameter optimization, and a multiple feature learning approach for feature extraction from denoised signals. The features are trained by SBELM to achieve a classification accuracy of 98.27%.
COGNITIVE COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Xiaowei Gu, Ce Zhang, Qiang Shen, Jungong Han, Plamen P. Angelov, Peter M. Atkinson
Summary: A novel semi-supervised ensemble framework was proposed for remote sensing scene classification, utilizing a self-training hierarchical prototype-based classifier to address the challenges of labelled data scarcity and scene complexity. Experimental results demonstrated significant improvements in classification accuracy on popular benchmark datasets with limited labelled images available.
INFORMATION FUSION
(2022)
Editorial Material
Computer Science, Information Systems
Mahardhika Pratama, Edwin Lughofer, Plamen P. Angelov
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Zhao-Xu Yang, Hai-Jun Rong, Plamen Angelov, Zhi-Xin Yang
Summary: This article proposes a novel incremental statistical evolving fuzzy inference system (SEFIS) that can update system parameters and evolve structure components in the presence of non-Gaussian noises. The system generates new rules based on statistical model sufficiency and deletes inactive rules to improve performance and accuracy. Additionally, an adaptive maximum correntropy extend Kalman filter is introduced to update parameters and enhance robustness. Simulation studies demonstrate that the proposed SEFIS has faster learning speed and higher accuracy compared to existing evolving fuzzy systems (EFSs) in both noise-free and noisy conditions.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xiaowei Gu, Plamen P. Angelov
Summary: This article introduces a novel multiclass fuzzily weighted AdaBoost-based ensemble system using a self-organizing fuzzy inference system as the ensemble component. By utilizing confidence scores from the SOFIS for sample weight updating and ensemble output generation, the proposed FWAdaBoost system achieves more accurate classification boundaries and greater prediction precision, demonstrating effectiveness in various benchmark classification problems.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Mona Alghamdi, Plamen Angelov, Lopez Pellicer Alvaro
Summary: This paper presents an approach for person identification based on knuckle creases and fingernails. It introduces a framework that includes localization, recognition, segmentation, and similarity matching of hand components. The results show that knuckle patterns and fingernails play a significant role in person identification.
Proceedings Paper
Computer Science, Artificial Intelligence
Nathanael L. Baisa, Bryan Williams, Hossein Rahmani, Plamen Angelov, Sue Black
Summary: In cases of serious crime, especially sexual abuse, hand images are often the only available information for identification. However, analyzing these images is challenging due to their capture in uncontrolled situations. To address this issue, researchers propose a method that learns global and local feature representations for hand-based person identification. By creating global and local branches on the conv-layer, the method can learn robust discriminative features at both global and part-levels. Evaluations on large datasets demonstrate the significant superiority of the proposed method compared to other approaches.
2022 ELEVENTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zheheng Jiang, Hossein Rahmani, Plamen Angelov, Sue Black, Bryan M. Williams
Summary: This study proposes a new method for matching images of different sizes, addressing the challenge through integer linear programming problems and graph-context attention networks. Experimental results demonstrate the superior performance of this method in keypoint matching and graph-level matching.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Xiaowei Gu, Plamen P. Angelov, Ce Zhang, Peter M. Atkinson
Summary: Large-scale satellite sensor images are valuable but challenging data sources for Earth observation. This research proposes a semi-supervised deep rule-based approach (SeRBIA) for autonomous analysis and classification of these images into detailed land-use categories. SeRBIA achieves high accuracy and interpretability by continuously learning from both labelled and unlabelled images using an ensemble feature descriptor.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Mona Alghamdi, Plamen Angelov, Bryan Williams
Summary: The study introduces a person identification method that utilizes knuckle creases and fingernail information from hand images. Results indicate that knuckle patterns and fingernails play a significant role in person identification, with fingernails showing slightly higher identification results compared to other hand components.
2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Alejandro Moran, Vincent Canals, Plamen P. Angelov, Christian F. Frasser, Erik S. Skibinsky-Gitlin, Joan Font, Eugeni Isern, Miquel Roca, Josep L. Rossello
Summary: This paper proposes a hardware acceleration technique using stochastic computing for the evolving ADP algorithm, showing potential benefits in reducing power consumption in embedded systems. Simulations of the proposed design on different datasets reveal some impact on clustering metrics compared to floating-point designs, with the potential for outperforming in certain cases while maintaining similar results to the original floating-point calculations.
2021 XXXVI CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS21)
(2021)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.