Search

This comprehensive review of concept-supported interpretation methods in Explainable Artificial Intelligence (XAI) navigates the multifaceted landscape. As machine learning models become more complex, there is a greater need for interpretation methods that deconstruct their decision-making processes. Traditional interpretation techniques frequently emphasise lower-level attributes, resulting in a schism between complex algorithms and human cognition. To bridge this gap, our research focuses on concept-supported XAI, a new line of research in XAI that emphasises higher-level attributes or 'concepts' that are more aligned with end-user understanding and needs. We provide a thorough examination of over twenty-five seminal works, highlighting their respective strengths and weaknesses. A comprehensive list of available concept datasets, as opposed to training datasets, is presented, along with a discussion of sufficiency metrics and the importance of robust evaluation methods. In addition, we identify six key factors that influence the efficacy of concept-supported interpretation: network architecture, network settings, training protocols, concept datasets, the presence of confounding attributes, and standardised evaluation methodology. We also investigate the robustness of these concept-supported methods, emphasising their potential to significantly advance the field by addressing issues like misgeneralization, information overload, trustworthiness, effective human-AI communication, and ethical concerns. The paper concludes with an exploration of open challenges such as the development of automatic concept discovery methods, strategies for expert-AI integration, optimising primary and concept model settings, managing confounding attributes, and designing efficient evaluation processes. [ABSTRACT FROM AUTHOR]

Payment cards offer a simple and convenient method for making purchases. Owing to the increase in the usage of payment cards, especially in online purchases, fraud cases are on the rise. The rise creates financial risk and uncertainty, as in the commercial sector, it incurs billions of losses each year. However, real transaction records that can facilitate the development of effective predictive models for fraud detection are difficult to obtain, mainly because of issues related to confidentially of customer information. In this paper, we apply a total of 13 statistical and machine learning models for payment card fraud detection using both publicly available and real transaction records. The results from both original features and aggregated features are analyzed and compared. A statistical hypothesis test is conducted to evaluate whether the aggregated features identified by a genetic algorithm can offer a better discriminative power, as compared with the original features, in fraud detection. The outcomes positively ascertain the effectiveness of using aggregated features for undertaking real-world payment card fraud detection problems. [ABSTRACT FROM AUTHOR]

In this paper, the research looks at improving clothing parsing using superpixels features extractor network (SP-FEN). Clothing parsing using a fully convolutional network has two parts: an encoder and decoder. The encoder lowers the dimensionality and produces a low-resolution prediction, while the decoder tries to upscale the prediction and returns it to the size of the input image. Typically, fine-grained details get lost in the encoding part of the model is not recovered well in the decoder part. To fix this issue, skip connections are typically used in recovering and adding more fine-grained details to the final prediction. A new method is proposed to introduce superpixels features to the decoder by adding a side network (SP-FEN) that extracts features from superpixels representation of the input image using the SLIC Algorithm. SP-FEN then produces a meaningful superpixels features to be injected into the decoder. The SP-FEN is learning to choose specific features to be fed to the decoder part to boost the outputs overall quality. The proposed method has shown to enhance the MIoU accuracy using the refined Fashionista V1.0 dataset and CFPD dataset. The results showed that the proposed approach achieved superior performance with pixel-wise segmentation and clothing parsing. [ABSTRACT FROM AUTHOR]

The appearance of a human face changes with the change in body weight and age. With varying lifestyle choices, it is hard to imagine the appearance of a given human face in years to come. Future self-perception is highly associated with one's emotional state, as well as health behavior. Negative future self-perception can cause negative lifestyle choice and negative health behavior, leading to depression and eating disorder. In this paper, a new methodology is introduced for future self-face image synthesis using age and weight, resulting in visualization of future face image derived from given weight category and age. A Constrained Local Model is first used for weight progressed future face image synthesized and then age-progressed future face image is generated using Conditional Adversarial Auto Encoder. In the final step, both weight progressed and age-progressed face images fed to face morphing module which synthesized future face image by keeping natural looks. Experimental results show the advantages of proposed method with promising results. [ABSTRACT FROM AUTHOR]

Challenges in time series classification has attracted attention in the past decade. Although large amounts of labeled data are assumed to be available, in reality, labeled data might be scarce to find in many domains. In this paper, we propose an online semi-supervised multi-channel classifier for time series based on growing neural gas (GNG) learning scheme. The method is able to handle multi-channel time series with variation in dimensions and it introduces a label prediction strategy to minimize misclassification. It measures the similarity of input instance and learned templates using weighted multi-channel dynamic time warping technique and learns the topology of input data space specified for each class using the GNG learning algorithm. Comprehensive evaluation is conducted using various datasets, such as gesture recognition, human activity recognition, and human daily-life activity recognition. Experimental results demonstrate good classification results, with indication that the proposed approach requires only a handful of labeled instances to construct an accurate classification model. [ABSTRACT FROM AUTHOR]

Person-independent, emotion specific facial feature tracking have been of interest in the machine vision society for decades. Among various methods, the constrained local model (CLM) has shown significant results in person-independent feature tracking. In 63this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. Considering a 17-point feature model on the frontal face region, the proposed tracking framework incorporates CLM with two incremental clustering algorithms to increase robustness and minimize tracking error during feature tracking. The Patch Clustering algorithm is applied to build an appearance model of face frames by organizing previously encountered similar patches into clusters while the shape Clustering algorithm is applied to build a structure model of face shapes by organizing previously encountered similar shapes into clusters followed by Bayesian adaptive resonance theory (ART). Both models are used to explore the similar features/shapes in the successive images. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed incremental clustering-based facial feature tracking (ICFFT) is evaluated using the FGnet database and the extended Cohn-Kanade (CK+) database. ICFFT demonstrates better results than baseline-method CLM and provides robust tracking as well as improved localization accuracy of emotion specific facial features tracking. [ABSTRACT FROM AUTHOR]

Emotional factor plays an important role in communication. In the field of psychology, it is known that memory and emotions are closely related to each other. In this paper, we present the significance of emotional factors to associative memory in communication and apply it on human-robot interaction problems. Emotional models for the robot partner are developed, and an interactive robot system with a complex-valued multi-directional associative memory model is proposed. We utilize multi-modal information such as object, gesture, voice, and facial expressions to associate the relationships in associative memory, and generate the emotional information for the robot partner. As a result, the robot partner is able to perform various actions depending on the emotional factors. Results from the interactive experiments indicate possibility of suitable information for communication space being provided from the robot partner. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid online learning model that combines the fuzzy min-max (FMM) neural network and the Classification and Regression Tree (CART) for motor fault detection and diagnosis tasks is described. The hybrid model, known as FMM-CART, incorporates the advantages of both FMM and CART for undertaking data classification (with FMM) and rule extraction (with CART) problems. In particular, the CART model is enhanced with an importance predictor-based feature selection measure. To evaluate the effectiveness of the proposed online FMM-CART model, a series of experiments using publicly available data sets containing motor bearing faults is first conducted. The results (primarily prediction accuracy and model complexity) are analyzed and compared with those reported in the literature. Then, an experimental study on detecting imbalanced voltage supply of an induction motor using a laboratory-scale test rig is performed. In addition to producing accurate results, a set of rules in the form of a decision tree is extracted from FMM-CART to provide explanations for its predictions. The results positively demonstrate the usefulness of FMM-CART with online learning capabilities in tackling real-world motor fault detection and diagnosis tasks. [ABSTRACT FROM AUTHOR]

In this paper, a framework for designing optimum pattern classifiers is proposed. The fuzzy ARTMAP (FAM) is first used as a base classifier. Multiple FAM classifiers form an ensemble to improve classification accuracy. Multi-objective genetic algorithms (GAs) are then used to search for the best combinations of variables, for the FAM classifiers. Based on the population of potential solutions, another GA selects the best combination of FAM classifiers to create an ensemble. Individual decisions are combined using a probabilistic voting scheme. To increase the inter-classifier diversity, a hierarchical parallel GA variant and a negative correlation method is employed during the genetic optimization phase for the ensemble evaluation. The proposed framework is evaluated using benchmark and real-world data sets, and the results compared with literature. Results positively indicate the proposed framework is effective in undertaking data classification tasks. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid model consisting of the fuzzy ARTMAP (FAM) neural network and the classification and regression tree (CART) is formulated. FAM is useful for tackling the stability-plasticity dilemma pertaining to data-based learning systems, while CART is useful for depicting its learned knowledge explicitly in a tree structure. By combining the benefits of both models, FAM-CART is capable of learning data samples stably and, at the same time, explaining its predictions with a set of decision rules. In other words, FAM-CART possesses two important properties of an intelligent system, i.e., learning in a stable manner (by overcoming the stability-plasticity dilemma) and extracting useful explanatory rules (by overcoming the opaqueness issue). To evaluate the usefulness of FAM-CART, six benchmark medical data sets from the UCI repository of machine learning and a real-world medical data classification problem are used for evaluation. For performance comparison, a number of performance metrics which include accuracy, specificity, sensitivity, and the area under the receiver operation characteristic curve are computed. The results are quantified with statistical indicators and compared with those reported in the literature. The outcomes positively indicate that FAM-CART is effective for undertaking data classification tasks. In addition to producing good results, it provides justifications of the predictions in the form of a decision tree so that domain users can easily understand the predictions, therefore making it a useful decision support tool. [ABSTRACT FROM AUTHOR]

In this study, a comprehensive methodology for overcoming the design problem of the Fuzzy ARTMAP neural network is proposed. The issues addressed are the sequence of training data for supervised learning and optimum parameter tuning for parameters such as baseline vigilance. A genetic algorithm search heuristic was chosen to solve this multi-objective optimization problem. To further augment the ARTMAP's pattern classification ability, multiple ARTMAPs were optimized via genetic algorithm and assembled into a classifier ensemble. An optimal ensemble was realized by the inter-classifier diversity of its constituents. This was achieved by mitigating convergence in the genetic algorithms by employing a hierarchical parallel architecture. The best-performing classifiers were then combined in an ensemble, using probabilistic voting for decision combination. This study also integrated the disparate methods to operate within a single framework, which is the proposed novel method for creating an optimum classifier ensemble configuration with minimum user intervention. The methodology was benchmarked using popular data sets from UCI machine learning repository. [ABSTRACT FROM AUTHOR]

Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003-2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented. [ABSTRACT FROM AUTHOR]

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min-Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments. [ABSTRACT FROM AUTHOR]

In this paper, an application of the motor current signature analysis (MCSA) method and the fuzzy min–max (FMM) neural network to detection and classification of induction motor faults is described. The finite element method is employed to generate simulated data pertaining to changes in the stator current signatures under different motor conditions. The MCSA method is then used to process the stator current signatures. Specifically, the power spectral density is employed to extract harmonics features for fault detection and classification with the FMM network. Various types of induction motor faults, which include stator winding faults and eccentricity problems, under different load conditions are experimented. The results are analyzed and compared with those from other methods. The outcomes indicate that the proposed technique is effective for fault detection and diagnosis of induction motors under different conditions. [ABSTRACT FROM AUTHOR]