In the face of increasing flood risks intensified by climate change, accurate flood inundation mapping is pivotal for effective disaster management. This study introduces a novel explainable deep learning architecture designed to generate precise flood inundation maps from diverse satellite data sources. A comprehensive evaluation of the proposed model is conducted, comparing it with state-of-the-art models across various fusion configurations of Multispectral Optical and Synthetic Aperture Radar (SAR) images. The proposed model consistently outperforms other models across both Sentinel-1 and Sentinel-2 images, achieving an Intersection Over Union (IOU) of 0.5862 and 0.7031, respectively. Furthermore, analysis of the different fusion combinations reveals that the use of Sentinel-1 in combination with RGB, NIR, and SWIR achieves the highest IOU of 0.7053 and that the inclusion of the SWIR band has the greatest positive impact on the results. Gradient-weighted class activation mapping is employed to provide insights into its decision-making processes, enhancing transparency and interpretability. This research contributes significantly to the field of flood inundation mapping, offering an efficient model suitable for diverse applications. This study not only advances flood inundation mapping but also provides a valuable tool for improved understanding of deep learning decision-making in this area, ultimately contributing to improved disaster management strategies.

Explainable Artificial Intelligence (XAI) evaluation has grown significantly due to its extensive adoption, and the catastrophic consequence of misinterpreting sensitive data, especially in the medical field. However, the multidisciplinary nature of XAI research resulted in diverse scholars possessing significant challenges in designing proper evaluation methods. This paper proposes a novel framework of a three-layered top-down approach on how to arrive at an optimal explainer, accenting the persistent need for consensus in XAI evaluation. This paper also investigates a critical comparative evaluation of explanations in both model agnostic and specific explainers including LIME, SHAP, Anchors, and TabNet, aiming to enhance the adaptability of XAI in a tabular domain. The results demonstrate that TabNet achieved the highest classification recall followed by TabPFN, and XGBoost. Additionally, this paper develops an optimal approach by introducing a novel measure of relative performance loss with emphasis on faithfulness and fidelity of global explanations by quantifying the extent to which a model’s capabilities diminish when eliminating topmost features. This addresses a conspicuous gap in the lack of consensus among researchers regarding how global feature importance impacts classification loss, thereby undermining the trust and correctness of such applications. Finally, a practical use case on medical tabular data is provided to concretely illustrate the findings.

The paper proposes and describes the development of conversational artificial intelligence (AI) agent to support hospital healthcare and COVID-19 queries. The conversational AI agent is called “Akira” and it is developed using deep neural network and natural language processing. It is capable of reading the inputs from the user, understanding the input and identifying the intention, and outputting messages towards the user, and these steps are iterated until the user prompts to exit or the programme is terminated. A deep learning model has been trained, and Akira could converse with the user ranging from the conversation over 7 topics related to COVID-19, common cold and flu, mental health, sexual health, abortions, allergens, drugs and medicine. The paper also describes the importance of designing an interactive human-user interface when dealing with conversational agent. In addition. the context of ethical issues and security concerns when designing the agent has been taken into consideration and discussed. The conversational agent is demonstrated to answer queries from a pool of 57 participants.

Cylindrical weir shapes offer a steady-state overflow pattern, where the type of weirs can offer a simple design and provide the ease-to-pass floating debris. This study considers a coefficient of discharge (Cd) prediction for oblique cylindrical weir using three diameters, the first is of D₁ = 0.11 m, the second is of D₂ = 0.09 m, and the third is of D3 = 0.06.5 m, and three inclination angles with respect to channel axis, the first is of θ₁ = 90 ^ͦ, the second is of θ₂ = 45 ^ͦ, and the third is of θ₃ = 30 ^ͦ. The Cd values for total of 56 experiments are estimated by using the radial basis function network (RBFN), in addition of comparing that with the back-propagation neural network (BPNN) and cascade-forward neural network (CFNN). Root mean square error (RMSE), mean square error (MSE), and correlation coefficient (CC) statics are used as metrics measurements. The RBFN attained superior performance comparing to the other neural networks of BPNN and CFNN. It is found that, for the training stage, the RBFN network benchmarked very small RMSE and MSE values of 1.35E-12 and 1.83E-24, respectively and for the testing stage, it also could benchmark very small RMSE and MSE values of 0.0082 and 6.80E-05, respectively.

This paper concentrates on reproducing face images from hand-dorsal images. This idea is adopted to enhance the biometric system outcomes. That is, best identifications can be presented by providing the face images of people as this can lead to directly recognizing the individuals. Non-linear relationships between hand-dorsal images and face images are designed and implemented. The power of Cascade-Forward Neural Network (CFN) and Back Propagation Neural Network (BPN) are employed to reproduce all face details by utilizing a hand-dorsal image. Both networks recorded interesting results in reproducing the details faces. The CFN performance is equal to 2.8571% and the BPN performance is equal to 6.4286%. Furthermore, the Average Correlation (ACORR) for the BPN which achieved 0.9874, this is lower than the ACORR for the CFN obtained to 0.9940. These performances reported that the CFN has significant ability to recognize people according to their face images.

Biometric authentication method based on image processing has obtained considerable attention. Images captured have its unique features especially the variance between objects and background. Hence n this paper, an automatic approach for personal recognition using deep learning algorithm namely the Basic Alexnet model that utilized the SVM algorithm for classification is proposed. The proposed algorithm consists of the following: data acquisition, designing the architecture of the Deep Learning Model (DLM), training the DLM, testing the DLM followed by training and testing the DLM in real time. The proposed biometric authentication method can be used in hospitals and for forensic applications. The total images acquired are 900. Training images are 70% of total images (630 images) and the remainder as testing images for training and testing the basic Alexnet model. Results attained showed that the highest accuracy is at 98%.