No abstract

Cancer research has seen explosive development exploring deep learning (DL) techniques for analysing magnetic resonance imaging (MRI) images for predicting brain tumours. We have observed a substantial gap in explanation, interpretability, and high accuracy for DL models. Consequently, we propose an explanation-driven DL model by utilising a convolutional neural network (CNN), local interpretable model-agnostic explanation (LIME), and Shapley additive explanation (SHAP) for the prediction of discrete subtypes of brain tumours (meningioma, glioma, and pituitary) using an MRI image dataset. Unlike previous models, our model used a dual-input CNN approach to prevail over the classification challenge with images of inferior quality in terms of noise and metal artifacts by adding Gaussian noise. Our CNN training results reveal 94.64% accuracy as compared to other state-of-the-art methods. We used SHAP to ensure consistency and local accuracy for interpretation as Shapley values examine all future predictions applying all possible combinations of inputs. In contrast, LIME constructs sparse linear models around each prediction to illustrate how the model operates in the immediate area. Our emphasis for this study is interpretability and high accuracy, which is critical for realising disparities in predictive performance, helpful in developing trust, and essential in integration into clinical practice. The proposed method has a vast clinical application that could potentially be used for mass screening in resource-constraint countries.

Directing research on Alzheimer’s towards only early prediction and accuracy cannot be considered a feasible approach towards tackling a ubiquitous degenerative disease today. Applying deep learning (DL), Explainable artificial intelligence(XAI) and advancing towards the human-computer interface(HCI) model can be a leap forward in medical research. This research aims to propose a robust explainable HCI model using shapley additive explanation (SHAP), local interpretable model-agnostic explanations (LIME) and DL algorithms. The use of DL algorithms: logistic regression(80.87%), support vector machine (85.8%), k-nearest neighbour(87.24%), multilayer perceptron(91.94%), decision tree(100%) and explainability can help exploring untapped avenues for research in medical sciences that can mould the future of HCI models. The outcomes of the proposed model depict higher prediction accuracy bringing efficient computer interface in decision making, and suggests a high level of relevance in the field of medical and clinical research.

The most significant and rapidly expanding fintech services in Nepal are provided by several fintech firms. Customer satisfaction must be compared side by side even if every organization has made an effort to expand the usage of services. Many studies have concentrated on evaluating the impact of various factors on customer satisfaction, but significantly fewer studies have been conducted to explore the factors and focus of machine learning. Based on the planned behavioural theory (TPB), the study is concentrated on exploring and evaluating customer satisfaction on a different stimulus offered by F1 Soft (a fintech firm in nepal), customers’ loyalty and the compatibility they gain through the company’s services. By exploring various factors affecting customer satisfaction by using principal component analysis (PCA) and explainable AI (XAI), the study explored the eight factors (customer service, compatibility, ease of use, assurance, loyalty intention, technology perception, speed and firm’s innovativeness) which affect customer satisfaction individually. Furthermore, by using support vector machine (SVM) and logistic regression (LR), the major contributing factors are explained with local interpretable model-agnostic explanation (LIME) and Shapley additive explanations (SHAP). SVM holds the training accuracy of 89.13% whereas LR achieves 87.88%, and both algorithms show that compatibilty issues consider the major contributing factor for customer satisfaction. Contributing toward different dimensions, determinants, and the results of customer satisfaction in fintech, the study suggests how fintech companies must integrate factors affecting customer satisfaction in their system for further process development.

Deepfake technology uses auto-encoders and generative adversarial networks to replace or artificially construct fine-tuned faces, emotions, and sounds. Although there have been significant advancements in the identification of particular fake images, a reliable counterfeit face detector is still lacking, making it difficult to identify fake photos in situations with further compression, blurring, scaling, etc. Deep learning models resolve the research gap to correctly recognize phony images, whose objectionable content might encourage fraudulent activity and cause major problems. To reduce the gap and enlarge the fields of view of the network, we propose a dual input convolutional neural network (DICNN) model with ten-fold cross validation with an average training accuracy of 99.36 ±0.62, a test accuracy of 99.08 ± 0.64, and a validation accuracy of 99.30 ± 0.94. Additionally, we used ’SHapley Additive exPlanations (SHAP) ’ as explainable AI (XAI) Shapely values to explain the results and interoperability visually by imposing the model into SHAP. The proposed model holds significant importance for being accepted by forensics and security experts because of its distinctive features and considerably higher accuracy than state-of-the-art methods.