Development of a new method for measuring multi-parameter of NaCl solution film based on absorption spectroscopy and interpretable convolutional neural network

Objective. P300 can be analyzed in autism spectrum disorder (ASD) to derive biomarkers and can be decoded in brain–computer interfaces to reinforce ASD impaired skills. Convolutional neural networks (CNNs) have been proposed for P300 decoding, outperforming traditional algorithms but they (a) do not investigate optimal designs in different training conditions; (b) lack in interpretability. To overcome these limitations, an interpretable CNN (ICNN), that we recently proposed for motor decoding, has been modified and adopted here, with its optimal design searched via Bayesian optimization. Approach. The ICNN provides a straightforward interpretation of spectral and spatial features learned to decode P300. The Bayesian-optimized (BO) ICNN design was investigated separately for different training strategies (within-subject, within-session, and cross-subject) and BO models were used for the subsequent analyses. Specifically, transfer learning (TL) potentialities were investigated by assessing how pretrained cross-subject BO models performed on a new subject vs. random-initialized models. Furthermore, within-subject BO-derived models were combined with an explanation technique (ICNN + ET) to analyze P300 spectral and spatial features. Main results. The ICNN resulted comparable or even outperformed existing CNNs, at the same time being lighter. BO ICNN designs differed depending on the training strategy, needing more capacity as the training set variability increased. Furthermore, TL provided higher performance than networks trained from scratch. The ICNN + ET analysis suggested the frequency range [2, 5.8] Hz as the most relevant, and spatial features showed a right-hemispheric parietal asymmetry. The ICNN + ET-derived features, but not ERP-derived features, resulted significantly and highly correlated to autism diagnostic observation schedule clinical scores. Significance. This study substantiates the idea that a CNN can be designed both accurate and interpretable for P300 decoding, with an optimized design depending on the training condition. The novel ICNN-based analysis tool was able to better capture ASD neural signatures than traditional event-related potential analysis, possibly paving the way for identifying novel biomarkers.

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs.

Decoding movement kinematics from EEG using an interpretable convolutional neural network

A convolutional neural network (CNN) learning structure is proposed, with added interpretability-oriented layers, in the form of Fuzzy Logic-based rules. This is achieved by creating a classification layer based on a Neural Fuzzy classifier, and integrating it into the overall learning mechanism within the deep learning structure. Using this new structure, one can extract linguistic Fuzzy Logic-based rules from the deep learning structure directly, and link this information to input features, which enhances the interpretability of the overall system. The classification layer is realised via a Radial Basis Function (RBF) Neural-Network, that is a direct equivalent of a class of Fuzzy Logic-based systems. In this work, the development of the RBF neural-fuzzy system and its integration into the deep-learning CNN is presented. The proposed hybrid CNN RBF-NF structure can form a fundamental building block, towards building more complex deep-learning structures with Fuzzy Logic-based interpretability. Using simulation results on benchmark data (MNIST handwriting digits and MNIST Fashion) we show that the proposed learning structure maintains a good level of forecasting/prediction accuracy compared to CNN deep learning structures. Crucially, we also demonstrate in both cases the resulting interpretability, in the form of linguistic rules that link the classification decisions to the input feature space.

The health condition of rolling bearings has a direct impact on the safe operation of rotating machinery. And their working environment is harsh and the working condition is complex, which brings challenges to fault diagnosis. With the development of computer technology, deep learning has been applied in the field of fault diagnosis and has rapidly developed. Among them, convolutional neural network (CNN) has received great attention from researchers due to its powerful data mining ability and feature adaptive learning ability. Based on recent research hotspots, the development history and trend of CNN is summarized and analyzed. Firstly, the basic structure of CNN is introduced and the important progress of classical CNN models for rolling bearing fault diagnosis in recent years is studied. The problems with the classic CNN algorithm have been pointed out. Secondly, to solve the above problems, combined with recent research achievements, various methods and principles for optimizing CNN are introduced and compared from the perspectives of deep feature extraction, hyperparameter optimization, network structure optimization. Although significant progress has been made in the research of fault diagnosis of rolling bearings based on CNN, there is still room for improvement and development in addressing issues such as low accuracy of imbalanced data, weak model generalization, and poor network interpretability. Therefore, the future development trend of CNN networks is discussed finally. And transfer learning models are introduced to improve the generalization ability of CNN and interpretable CNN is used to increase the interpretability of CNN networks.

Interpreting convolutional neural network for real-time volatile organic compounds detection and classification using optical emission spectroscopy of plasma

Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One difficulty in the CNN interpretability is that filters and image classes are entangled. In this paper, we introduce a novel pathway to alleviate the entanglement between filters and image classes. The proposed pathway groups the filters in a late conv-layer of CNN into class-specific clusters. Clusters and classes are in a one-to-one relationship. Specifically, we use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. To enable end-to-end optimization, we develop a novel reparameterization trick for handling the non-differentiable Bernoulli sampling. We evaluate the effectiveness of our method on ten widely used network architectures (including nine CNNs and a ViT) and five benchmark datasets. Experimental results have demonstrated that our method PICNN (the combination of standard CNNs with our proposed pathway) exhibits greater interpretability than standard CNNs while achieving higher or comparable discrimination power.

Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks

Interpretable convolutional neural network with multilayer wavelet for Noise-Robust Machinery fault diagnosis

The adoption of convolutional neural network (CNN) models in high-stake domains is hindered by their inability to meet society’s demand for transparency in decision-making. So far, a growing number of methodologies have emerged for developing CNN models that are interpretable by design. However, such models are not capable of providing interpretations in accordance with human perception, while maintaining competent performance. In this paper, we tackle these challenges with a novel, general framework for instantiating inherently interpretable CNN models, named E pluribus unum interpretable CNN (EPU-CNN). An EPU-CNN model consists of CNN sub-networks, each of which receives a different representation of an input image expressing a perceptual feature, such as color or texture. The output of an EPU-CNN model consists of the classification prediction and its interpretation, in terms of relative contributions of perceptual features in different regions of the input image. EPU-CNN models have been extensively evaluated on various publicly available datasets, as well as a contributed benchmark dataset. Medical datasets are used to demonstrate the applicability of EPU-CNN for risk-sensitive decisions in medicine. The experimental results indicate that EPU-CNN models can achieve a comparable or better classification performance than other CNN architectures while providing humanly perceivable interpretations.

Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs make them difficult for human interpretation or understanding in science. In this article, we introduce a greedy structural compression scheme to obtain smaller and more interpretable CNNs, while achieving close to original accuracy. The compression is based on pruning filters with the least contribution to the classification accuracy or the lowest Classification Accuracy Reduction (CAR) importance index. We demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant functionalities such as color filters. These compressed networks are easier to interpret because they retain the filter diversity of uncompressed networks with an order of magnitude fewer filters. Finally, a variant of CAR is introduced to quantify the importance of each image category to each CNN filter. Specifically, the most and the least important class labels are shown to be meaningful interpretations of each filter.

Explainable AI for myocardial infarction using the vectorcardiogram

Lightweight and interpretable convolutional neural network for real-time heart rate monitoring using low-cost video camera under realistic conditions

Recently, many e-commerce websites have encouraged their users to rate shopping items and write review texts. This review information has been very useful for understanding user preferences and item properties, as well as enhancing the capability to make personalized recommendations of these websites. In this paper, we propose to model user preferences and item properties using convolutional neural networks (CNNs) with dual local and global attention, motivated by the superiority of CNNs to extract complex features. By using aggregated review texts from a user and aggregated review text for an item, our model can learn the unique features (embedding) of each user and each item. These features are then used to predict ratings. We train these user and item networks jointly which enable the interaction between users and items in a similar way as matrix factorization. The local attention provides us insight on a user's preferences or an item's properties. The global attention helps CNNs focus on the semantic meaning of the whole review text. Thus, the combined local and global attentions enable an interpretable and better-learned representation of users and items. We validate the proposed models by testing on popular review datasets in Yelp and Amazon and compare the results with matrix factorization (MF), the hidden factor and topical (HFT) model, and the recently proposed convolutional matrix factorization (ConvMF+). Our proposed CNNs with dual attention model outperforms HFT and ConvMF+ in terms of mean square errors (MSE). In addition, we compare the user/item embeddings learned from these models for classification and recommendation. These results also confirm the superior quality of user/item embeddings learned from our model.

Convolutional neural networks (CNNs) are essential tools for identifying the wear state of a milling cutter. However, the decision mechanism and classification basis of CNNs is unclear, which reduces the credibility of the recognition results and limits their application in industrial recognition. Tackling the challenge of poor interpretability in traditional CNNs, this paper introduces an interpretable convolutional neural network (STA-CNN) designed specifically for identifying the wear state of milling cutters. Firstly, an attention layer is embedded in the CNN to prioritize important milling cutter wear information. Secondly, the Stockwell transform (S-Transform) is embedded into the spatial attention convolution layer to form an interpretable Stockwell attention convolution layer. Finally, a physically meaningful loss function is designed for the tool wear state to guide the STA-CNN model in learning and updating the parameters. The STA-CNN model achieves 98% accuracy in recognizing tool wear states and demonstrates good interpretability.