The abnormal growth of malignant or nonmalignant tissues in the brain causes long-term damage to the brain. Magnetic resonance imaging (MRI) is one of the most common methods of detecting brain tumors. To determine whether a patient has a brain tumor, MRI filters are physically examined by experts after they are received. It is possible for MRI images examined by different specialists to produce inconsistent results since professionals formulate evaluations differently. Furthermore, merely identifying a tumor is not enough. To begin treatment as soon as possible, it is equally important to determine the type of tumor the patient has. In this paper, we consider the multiclass classification of brain tumors since significant work has been done on binary classification. In order to detect tumors faster, more unbiased, and reliably, we investigated the performance of several deep learning (DL) architectures including Visual Geometry Group 16 (VGG16), InceptionV3, VGG19, ResNet50, InceptionResNetV2, and Xception. Following this, we propose a transfer learning(TL) based multiclass classification model called IVX16 based on the three best-performing TL models. We use a dataset consisting of a total of 3264 images. Through extensive experiments, we achieve peak accuracy of $95.11\%$ , $93.88\%$ , $94.19\%$ , $93.88\%$ , $93.58\%$ , $94.5\%$ , and $96.94\%$ for VGG16, InceptionV3, VGG19, ResNet50, InceptionResNetV2, Xception, and IVX16, respectively. Furthermore, we use Explainable AI to evaluate the performance and validity of each DL model and implement recently introduced Vison Transformer (ViT) models and compare their obtained output with the TL and ensemble model.

Farmers usually plan the cultivation process based on their previous experiences. Due to the lack of precise knowledge about cultivation, they end up cultivating undesirable crops. To help the farmers take decisions that can make their farming more efficient and profitable, the research tries to establish an intelligent information prediction analysis on farming in Bangladesh. However, this way of farming here is still at the initial stage. The research suggests area based beneficial crop rank before the cultivation process. It indicates the crops that are cost effective for cultivation for a particular area of land. To achieve these results, we are considering six major crops which are Aus rice, Aman rice, Boro rice, Potato, Jute and Wheat. The prediction is based on analyzing a static set of data using Supervised Machine Learning techniques. This static dataset contains previous years' data taken from the Yearbook of Agricultural Statistics and Bangladesh Agricultural Research Council of those crops according to the area. The research has an intent to use Decision Tree Learning-ID3 (Iterative Dichotomiser 3) and K-Nearest Neighbors Regression algorithms.

Agriculture is the essential ingredients to mankind which is a major source of livelihood. Agriculture work in Bangladesh is mostly done in old ways which directly affects our economy. In addition, institutions of agriculture are working with manual data which cannot provide a proper solution for crop selection and yield prediction. This paper shows the best way of crop selection and yield prediction in minimum cost and effort. Artificial Neural Network is considered robust tools for modeling and prediction. This algorithm aims to get better output and prediction, as well as, support vector machine, Logistic Regression, and random forest algorithm is also considered in this study for comparing the accuracy and error rate. Moreover, all of these algorithms used here are just to see how well they performed for a dataset which is over 0.3 million. We have collected 46 parameters such as - maximum and minimum temperature, average rainfall, humidity, climate, weather, and types of land, types of chemical fertilizer, types of soil, soil structure, soil composition, soil moisture, soil consistency, soil reaction and soil texture for applying into this prediction process. In this paper, we have suggested using the deep neural network for agricultural crop selection and yield prediction.

Tomato leaf diseases can incur significant financial damage by having adverse impacts on crops and, consequently, they are a major concern for tomato growers all over the world. The diseases may come in a variety of forms, caused by environmental stress and various pathogens. An automated approach to detect leaf disease from images would assist farmers to take effective control measures quickly and affordably. Therefore, the proposed study aims to analyze the effects of transformer-based approaches that aggregate different scales of attention on variants of features for the classification of tomato leaf diseases from image data. Four state-of-the-art transformer-based models, namely, External Attention Transformer (EANet), Multi-Axis Vision Transformer (MaxViT), Compact Convolutional Transformers (CCT), and Pyramid Vision Transformer (PVT), are trained and tested on a multiclass tomato disease dataset. The result analysis showcases that MaxViT comfortably outperforms the other three transformer models with $97\%$ overall accuracy, as opposed to the $89\%$ accuracy achieved by EANet, $91\%$ by CCT, and $93\%$ by PVT. MaxViT also achieves a smoother learning curve compared to the other transformers. Afterwards, we further verified the legitimacy of the results on another relatively smaller dataset. Overall, the exhaustive empirical analysis presented in the paper proves that the MaxViT architecture is the most effective transformer model to classify tomato leaf disease, providing the availability of powerful hardware to incorporate the model.

The field of medical image analysis is in a constant state of evolution, particularly in the challenging tasks of segmenting organs, diseases, and abnormalities. Therefore, in the realm of dental disease diagnosis, image segmentation plays a crucial role in addressing the difficulties faced by dentists worldwide when diagnosing dental diseases with the naked eye. One prominent deep neural network architecture, known as U-Net, originally designed for biomedical image segmentation, has seen multiple variations and advancements aimed at improving its performance. However, the lack of comparative studies has made it challenging to assess the effectiveness of these U-Net variants in segmenting dental X-ray images. The primary objective of this research is to conduct a comprehensive performance comparison among various U-Net architectures for dental image segmentation. Specifically, we examine six U-Net architecture variants: Vanilla U-Net, Dense U-Net, Attention U-Net, SE U-Net, Residual U-Net, and R2 U-Net. These variants employ configurations with two and three convolutional layers in both the encoder and decoder blocks. Our evaluation metrics include Accuracy, Dice coefficient, F1 score, and IoU (Intersection over Union). Among these U-Net variants, Vanilla U-Net, with two convolutional layers, demonstrated the highest level of performance, achieving an Accuracy of 95.56% and an IoU score of 88% on the validation set. Notably, this model also exhibited a shorter processing time compared to the other architectures. Conversely, when employing three convolutional layers, the Dense U-Net variant emerged as the top performer, achieving an Accuracy of 95.94% and an IoU score of 89.07% on the validation set. Furthermore, the segmentation process successfully isolates the teeth from the surrounding structures, which holds promise for improving disease detection through the development of automated disease diagnosis models.

The emergence of medical sensors in Smart Healthcare Systems (SHS) has enabled the development of sophisticated Internet of Medical Things (IoMT) networks which is crucial for tracking vital physiological parameters in consumer electronics. These networks are progressively incorporated into consumer devices allowing users to monitor their health parameters effortlessly. Nonetheless, they encounter considerable security and privacy issues stemming from weaknesses in data transfer. Despite the potential of Intrusion Detection Systems (IDS), there is a critical need for a real-time, highly precise attack detection system optimized for the edge-centric Internet of Medical Things (IoMT) environment in consumer sensor devices. Therefore, we introduce the federated kolmogorov-arnold network (FedIoMT), an advanced federated learning framework that utilizes meta-learning along with an advanced clustering method to achieve robust model aggregation. Our FedIoMT acts as both an adaptive personalized updating mechanism and a shared global classifier. In addition, we propose a novel intrusion detection model that uses the kolmogorov-arnold convolutional network (KANConvNet) as its local classifier, which improves scalability and interpretability in the FL framework updates. Our FedIoMT model demonstrates superior performance compared to other existing FL-based methods, achieving validation accuracies of 99.38%, 99.23%, 99.26%, and 99.2% across four benchmark IoMT datasets under the IID setting. FedIoMT utilizes significantly more floating point operations per second (FLOP) counts up to 2.8 times more than other models and also excels in memory efficiency, consuming up to 93% less peak memory across devices compared to the alternatives. We thoroughly evaluated FedIoMT on embedded consumer devices, demonstrating its resource-efficient characteristics.