Early and precise diagnosis of brain tumors is essential for successful treatment planning and improved patient outcomes. This paper introduces a novel hybrid deep model that incorporates DenseNet121, a convolutional neural network (CNN), and the Swin Transformer, a vision transformer model, by feature-level fusion to classify brain tumors from magnetic resonance imaging (MRI) scans. The suggested method provides a more discriminative and better representation by uniting the global context capability of the Transformer model with the local feature extraction capability of the CNN model. The suggested method was trained and assessed on a publicly available brain MRI dataset of four classes: glioma, meningioma, pituitary tumor, and no tumor. Experimental results indicate that the proposed approach outperforms many baseline models including VGG16, MobileNetV2, and AlexNet with an accuracy of 99.39%, precision of 99.36%, recall of 99.34%, and F1-score of 99.35%. Grad-CAM was utilized to visualize class-discriminative regions in the MRI scans to enhance interpretability, hence validating the model's emphasis on tumor-relevant regions. These outcomes prove the efficacy of coupling Transformer and CNN architectures in obtaining accurate and interpretable brain tumor classification from MRI scans.

 Fuzzy Neural Networks (FNNs) enhance conventional Artificial Neural Networks (ANNs) by incorporating fuzzy membership functions, which enable the handling of uncertainty, ambiguity, and imprecise information. While Fuzzy Backpropagation Neural Networks (FBNNs) improve classification performance across noisy datasets, the effectiveness of fuzzification heavily depends on the proper tuning of membership function parameters—typically optimized manually. This paper presents a novel Artificial Immune System framework for optimizing Fuzzy Backpropagation Neural Networks used in the classification of biological image data. The approach integrates a fuzzy min–max fuzzification layer with a feed-forward backpropagation network and applies an optimization version of an Artificial Immune Network model, derived from opt-aiNet, to tune trapezoidal membership functions. Experimental results confirm that the proposed immune-driven optimization is an effective technique for enhancing FBNN robustness and generalization.

Ischemic brain stroke is the most prevalent type of stroke caused by the occlusion of blood vessels via thrombi or blockages and is the second most common cause of mortality globally, after ischemic heart disease. To improve patient outcomes, ischemic stroke must be diagnosed timely and precise. This paper introduces a novel approach toward ischemic stroke detection from computed tomography (CT) images by integrating deep learning and optimization techniques for feature extraction and selection. The VGG16 model is utilized to extract high-dimensional spatially rich features that efficaciously capture the intricate texture and spatial patterns within the CT scans. To optimize these features, a genetic algorithm (GA) is leveraged to select the most discriminative subset and reduce redundancy. The new method was developed and evaluated on a unique, first-hand dataset gathered from a specialized private hospital in Palestine. The findings show that the suggested combined technique VGG16-GA highly enhances the performance of all classifiers. Notably, the VGG16-GA-XGB model attained superior outcomes, with an accuracy of 98.89%, precision of 98.85%, recall of 98.93%, and an F1-score of 98.92%.

This paper investigates the effects of applying fuzzy techniques to artificial neural networks (ANN) for

the classification of biological data. A fuzzy neural networks (FNNs) model was proposed and evaluated

as a system for image classification. This system involved the process of collecting dataset, image

processing and image classification. Patch-based technique is used to present images to the neural

network. Feed-Forward Backpropagation neural networks are used to build the system. Fuzzy Min-Max

Neural Networks (FMNN) approach was used to synthesize Fuzzification and neural networks to generate

fuzzy neural networks that can handle imprecision and uncertainty. The approach is evaluated using

images from the data portal (Papers with Code) website. Experimental results have shown an improvement

in the performance of fuzzy neural networks compared with neural networks.

Evaluation can be defined as a process of determining the significance of a research output. This is usually done by devising a well-structured study on this output using one or more evaluation measures in which a careful inspection is performed. This paper presents a review of evaluation techniques for Conversational Agents (CAs) and Natural Language Interfaces to Databases (NLIDBs). It then introduces the developed customized evaluation methodology for Conversation-Based Interface to Relational Databases (C-BIRDs). The evaluation methodology created has been divided into two groups of measures. The first is based on quantitative measures, including two measures: task success and dialogue length. The second group is based on a number of qualitative measures, including: prototype ease of use, naturalness of system responses, positive/negative emotion, appearance, text on screen, organization of information, and error message clarity. Then an elaboration is carried out on the devised methodology by adding a discussion and recommendations on the sample size, the experimental setup and the scaling in order to provide a comprehensive evaluation methodology for C-BIRDs. In conclusion the evaluation methodology created is better way for identifying the strengths and weaknesses of C-BIRDs in comparison to the usage of single measure evaluations.

One of the challenges in data mining practices is that the datasets vary in complexity and often have different characteristics such as number of attributes, dependent variables characteristics etc. In terms of regression problems, the features that describe the dataset will vary in their complexity, sparseness verses coverage in relation to the decision space, and the number of outcome classes. Fuzzy Decision trees are well-established classifiers in terms of building robust, representative models of the domain. In order to represent different perspectives of the same domain, fuzzy trees can be used to construct fuzzy decision forests to enhance the predictive ability of singular trees. This paper describes an empirical study which examines the applicability of fuzzy tree regression forests to seven different datasets which have complex properties. The relationship between dataset characteristics and the performance of fuzzy regression tree forests is debated.

Fuzzy decision forests aim to improve the predictive power of single fuzzy decision trees by allowing multiple views of the same domain to be modelled. Such forests have been successfully created for classification problems where the outcome field is discrete; however predicting a continuous output value is more challenging in combining the output from multiple fuzzy decision trees. This paper presents a new approach to creating fuzzy regression tree forests based upon the induction of multiple fuzzy regression decision trees from one training sample, where each tree will represent a different view of the data domain. The singular fuzzy regression trees are induced using a proven algorithm known as Elgasir which fuzzifies crisp CHAID decision trees using trapezoidal membership functions for fuzzification and applies Takagi-Sugeno inference to obtain the final predicted values. A modified version of Artificial Immune System Network model (opt-aiNet) is then used for the simultaneous optimization of the membership functions across all trees within the forest. A strength of the proposed method is that data does not require fuzzification before forest induction this reducing pre-processing time and the need for subjective human experts. Five problem sets from the UCI repository and KEEL repository are used to evaluate the approach. The experimental results have shown that fuzzy regression tree forests reduce the error rate compared with single fuzzy regression trees.