Brain tumor classification is essential for clinical diagnosis and treatment planning. Deep learning models have shown great promise in this task, but they are often challenged by the complex and diverse nature of brain tumors. To address this challenge, we propose a novel deep residual and region-based convolutional neural network (CNN) architecture, called Res-BRNet, for brain tumor classification using magnetic resonance imaging (MRI) scans. Res-BRNet employs a systematic combination of regional and boundary-based operations within modified spatial and residual blocks. The spatial blocks extract homogeneity, heterogeneity, and boundary-related features of brain tumors, while the residual blocks significantly capture local and global texture variations. We evaluated the performance of Res-BRNet on a challenging dataset collected from Kaggle repositories, Br35H, and figshare, containing various tumor categories, including meningioma, glioma, pituitary, and healthy images. Res-BRNet outperformed standard CNN models, achieving excellent accuracy (98.22%), sensitivity (0.9811), F1-score (0.9841), and precision (0.9822). Our results suggest that Res-BRNet is a promising tool for brain tumor classification, with the potential to improve the accuracy and efficiency of clinical diagnosis and treatment planning.

In recent years, rapid advancements in deepfakes (incorporating Artificial Intelligence (AI), machine, and deep learning) have updated tools and techniques for manipulating multimedia. Though technology has primarily been utilized for beneficial purposes, such as education and entertainment, it is also used for malicious or unethical tasks to spread disinformation or ruin someone’s dignity, even if it encompasses harassing and blackmailing victims. Deepfakes refer to high-quality and realistic multimedia-manipulated content that has been digitally modified or synthetically generated. We conducted a systematic literature review of deepfake detection to offer an updated overview of existing research work that initially describes the widely accessible deepfake generation tools, classifications, and detection process. We highlighted recent techniques in visual deepfake detection based on the feature representations, grouped into four domains: spatial, temporal, frequency, and spatio-temporal, including their key features and limitations by providing details of existing datasets, together with the potentials of deepfake and its future directions. This study tried to add an updated repository of technological change in deepfake, which could help researchers to develop robust deepfake models.

Detecting website phishing is crucial for protecting sensitive information, including personal data and financial details. It helps maintain trust and reputation for both businesses and users while preventing malware infections and cyber-attacks. This research addresses the need for advanced detection mechanisms for the identification of phishing websites. For this purpose, we explore state-of-the-art machine learning, ensemble learning, and deep learning algorithms. To evaluate the efficacy of the proposed method, the top features are ranked using information gain, gain ratio, and Principal Component Analysis (PCA) which help to classify a website as phishing or non-phishing. The statistical exploratory data analysis using data visualization techniques helps to provide deep insights into the dataset. The proposed system is trained using a dataset that covers 11,055 websites. The ensemble learning model applied achieved an impressive accuracy of as high as 99% in predicting phishing websites, surpassing previous models, and setting a new benchmark in the field. The findings highlight the effectiveness of the proposed model, and such advanced approaches may help to maintain the stability and security of online platforms.

Road traffic accidents have increased globally, which has led to significant challenges to urban safety and public health. This concerning trend is also evident in California, where major cities have seen a rise in accidents. This research conducts a spatio-temporal analysis of traffic accidents across the four major Californian cities—Los Angeles, Sacramento, San Diego, and San Jose—over five years. It achieves this through an integration of Geographic Information System (GIS) functionalities (space–time cube analysis) with non-parametric statistical and spatial techniques (DBSCAN, KDE, and the Getis-Ord Gi* method). Our findings from the temporal analysis showed that the most accidents occurred in Los Angeles over five years, while San Diego and San Jose had the least occurrences. The severity maps showed that the majority of accidents in all cities were level 2. Moreover, spatio-temporal dynamics, captured via the space–time cube analysis, visualized significant accident hotspot locations. The clustering of accidents using DBSCAN verified the temporal and hotspot analysis results by showing areas with high accident rates and different clustering patterns. Additionally, integrating KDE with the population density and the Getis-Ord Gi* method explained the relationship between high-density regions and accident occurrences. The utilization of GIS-based analytical techniques in this study shows the complex interplay between accident occurrences, severity, and demographic factors. The insight gained from this study can be further used to implement effective data-driven road safety strategies.

Malaria is a potentially fatal plasmodium parasite injected by female anopheles mosquitoes that infect red blood cells and cause millions of lifelong disability worldwide yearly. However, specialists’ manual screening in clinical practice is laborious and prone to error. Therefore, a novel Deep Boosted and Ensemble Learning (DBEL) framework, comprising the stacking of new Boosted-BR-STM convolutional neural networks (CNN) and the ensemble ML classifiers, is developed to screen malaria parasite images. The proposed Boosted-BR-STM is based on a new dilated-convolutional block-based Split Transform Merge (STM) and feature-map Squeezing–Boosting (SB) ideas. Moreover, the new STM block uses regional and boundary operations to learn the malaria parasite’s homogeneity, heterogeneity, and boundary with patterns. Furthermore, the diverse boosted channels are attained by employing Transfer Learning-based new feature-map SB in STM blocks at the abstract, medium, and conclusion levels to learn minute intensity and texture variation of the parasitic pattern. Additionally, to enhance the learning capacity of Boosted-BR-STM and foster a more diverse representation of features, boosting at the final stage is achieved through TL by utilizing multipath residual learning. The proposed DBEL framework implicates the stacking of prominent and diverse boosted channels and provides the generated discriminative features of the developed Boosted-BR-STM to the ensemble of ML classifiers. The proposed framework improves the discrimination ability and generalization of ensemble learning. Moreover, the deep feature spaces of the developed Boosted-BR-STM and customized CNNs are fed into ML classifiers for comparative analysis. The proposed DBEL framework outperforms the existing techniques on the NIH malaria dataset that are enhanced using discrete wavelet transform to enrich feature space. The proposed DBEL framework achieved Accuracy (98.50%), Sensitivity (0.9920), F-score (0.9850), and AUC (0.9960), which suggests it to be utilized for malaria parasite screening.