Diagnosing health in composite battery electrodes with explainable deep learning and partial charging data

Lithium-ion batteries with composite anodes of graphite and silicon are increasingly being used. However, their degradation pathways are complicated due to the blended nature of the electrodes, with graphite and silicon degrading at different rates. Here, we develop a deep learning health diagnostic framework to rapidly quantify and separate the different degradation rates of graphite and silicon in composite anodes using partial charging data. The convolutional neural network (CNN), trained with synthetic data, uses experimental partial charging data to diagnose electrode-level health of tested batteries, with errors of less than 3.1% (corresponding to the loss of active material reaching ∼75%). Sensitivity analysis of the capacity-voltage curve under different degradation modes is performed to provide a physically informed voltage window for diagnostics with partial charging data. By using the gradient-weighted class activation mapping approach, we provide explainable insights into how these CNNs work;highlighting regions of the voltage-curve to which they are most sensitive. Robustness is validated by introducing noise to the data, with no significant negative impact on the diagnostic accuracy for noise levels below 10 mV, thus highlighting the potential for deep learning approaches in the diagnostics of lithium-ion battery performance under real-world conditions. The framework presented here can be generalised to other cell formats and chemistries, providing robust and explainable battery diagnostics for both conventional single material electrodes, but also the more challenging composite electrodes.

Atherosclerotic plaque classification in carotid ultrasound images using machine learning and explainable deep learning

Objective The incidence of cardiovascular diseases(CVD)is rising rapidly worldwide.Some forms of CVD,such as stroke and heart attack,are more common among patients with certain conditions.Atherosclerosis development is a major factor underlying cardiovascular events,such as heart attack and stroke,and its early detection may prevent such events.Ultrasound imaging of carotid arteries is a useful method for diagnosis of atherosclerotic plaques;however,an automated method to classify atherosclerotic plaques for evaluation of early-stage CVD is needed.Here,we propose an automated method for classification of high-risk atherosclerotic plaque ultrasound images.Methods Five deep learning(DL)models(VGG16,ResNet-50,GoogLeNet,XceptionNet,and SqueezeNet)were used for automated classification and the results compared with those of a machine learning(ML)-based technique,involving extraction of 23 texture features from ultrasound images and classification using a Support Vector Machine classifier.To enhance model interpretability,output gradient-weighted convolutional activation maps(GradCAMs)were generated and overlayed on original images.Results A series of indices,including accuracy,sensitivity,specificity,F1-score,Cohen-kappa index,and area under the curve values,were calculated to evaluate model performance.GradCAM output images allowed visualization of the most significant ultrasound image regions.The GoogLeNet model yielded the highest accuracy(98.20%).Conclusion ML models may be also suitable for applications requiring low computational resource.Further,DL models could be more completely automated than ML models.

Development and testing of an image transformer for explainable autonomous driving systems

Purpose–Perception has been identified as the main cause underlying most autonomous vehicle related accidents.As the key technology in perception,deep learning(DL)based computer vision models are generally considered to be black boxes due to poor interpretability.These have exacerbated user distrust and further forestalled their widespread deployment in practical usage.This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations.The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.Design/methodology/approach–This paper proposes an explainable end-to-end autonomous driving system based on“Transformer,”a state-ofthe-art self-attention(SA)based model.The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations,and aims to achieve soft attention over the image’s global features.Findings–The results demonstrate the efficacy of the proposed model as it exhibits superior performance(in terms of correct prediction of actions and explanations)compared to the benchmark model by a significant margin with much lower computational cost on a public data set(BDD-OIA).From the ablation studies,the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.Originality/value–In the contexts of situational awareness and driver assistance,the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions.In addition,the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships.This provision is critical in the development of autonomous systems.