Vehicular networks improve quality of life, security, and safety, making them crucial to smart city development. With the rapid advancement of intelligent vehicles, the confidentiality and security concerns surrounding vehicular ad hoc networks (VANETs) have garnered considerable attention. VANETs are intrinsically more vulnerable to attacks than wired networks due to high mobility, common network medium, and lack of centrally managed security services. Intrusion detection (ID) servers are the first protection layer against cyberattacks in this digital age. The most frequently used mechanism in a VANET is intrusion detection systems (IDSs), which rely on vehicle collaboration to identify attackers. Regrettably, existing cooperative IDSs get corrupted and cause the IDSs to operate abnormally. This article presents an approach to intrusion detection based on the distributed federated learning (FL) of heterogeneous neural networks for smart cities. It saves time and resources by using the most efficient intruder detection approach. First, vehicles use a federated learning technique to develop local, deep learning-based IDS classifiers for VANET data streams. They then share their locally learned classifiers upon request, significantly reducing communication overhead with neighboring vehicles. Then, an ensemble of federated heterogeneous neural networks is constructed for each vehicle, including locally and remotely trained classifiers. Finally, the global ensemble model is again shared with local devices for their updating. The effectiveness of the suggested method for intrusion detection in VANETs is evaluated using performance indicators such as attack detection rates, classification accuracy, precision, recall, and F1 scores over a ToN-IoT data stream. The ID model shows 0.994 training and 0.981 testing accuracy.

The state-of-the-art Credit Card Fraud Detection (CCFD) systems utilize supervised rule-based schemes to identify fraudulent behaviors in static data. Designing an efficient framework for CCFD is particularly challenging due to the imbalanced distribution of positive and negative classes in data. Conventional works overlook hidden transaction patterns and the performance evaluation methods of algorithm or system. The early models have also been criticized for over-fitting, i.e. models having less prediction accuracy than training or classification accuracy. However, the categorical accuracy is more important than overall accuracy for extremely imbalanced data; most of the previous works do not evaluate their model on the basis of categorical accuracy. In this work, we propose a predictive framework (DEAL) based on novel Deep Ensemble Learning for detecting fraudulent transaction in real-time data stream. The proposed framework is adaptive against data imbalance and robust against latent transaction patterns such as spending behavior. To build the model and predict the fraud, the transactions from real data from a major bank are passed as tensors to ensemble of Deep Learning Network. The adaptive optimization is suggested to minimize the objective function and improve fraud prediction. All Experiments are conducted in Python using scikit-learn, Google TensorFlow, and Keras Deep Learning libraries. The results demonstrate its superiority over state-of-the-art methods in catching frauds.

Diabetes has been recognized as a global medical problem for more than half a century. Patients with diabetes can benefit from the Internet of Things (IoT) devices such as continuous glucose monitoring (CGM), intelligent pens, and similar devices. Smart devices generate continuous data streams that must be processed in real-time to benefit the users. The amount of medical data collected is vast and heterogeneous since it is gathered from various sources. An accurate diagnosis can be achieved through a variety of scientific and medical techniques. It is necessary to process this streaming data faster to obtain relevant and significant knowledge. Recently, the research has concentrated on improving the prediction model's performance by using ensemble-based and Deep Learning (DL) approaches. However, the performance of the DL model can degrade due to overfitting. This paper proposes the Extra-Tree Ensemble feature selection technique to reduce the input feature space with DL (ETEODL), a predictive framework to predict the likelihood of diabetes. In the proposed work, dropout layers follow the hidden layers of the DL model to prevent overfitting. This research utilized a dataset from the UCI Machine learning (ML) repository for an Early-stage prediction of diabetes. The proposed scheme results have been compared with state-of-the-art ML algorithms, and the comparison validates the effectiveness of the predictive framework. This proposed work, which outperforms the other selected classifiers, achieves a 97.38 per cent accuracy rate. F1-Score, precision, and recall percent are 96, 97.7, and 97.7, respectively. The comparison unveils the superiority of the suggested approach. Thus, the proposed method effectively improves the performance against the earlier ML techniques and recent DL approaches and avoids overfitting.

Malignant melanoma is a type of benign skin cancer that is the most lethal due to its rapid development and affects a large number of people worldwide. Also, it is one of the deadliest diseases in the world. Moreover, existing research has stated that risk factors may be significantly decreased by making it nearly curable if diagnosed early on. This prompt identification and categorization necessitate using an automated system, even though the existing method is rather difficult. Hence our research employs the YOLO v3 - DCNN architecture to discover and categorize the deadliest kinds of skin cancer. Initially, YOLO v3 generates the feature map; simultaneously, colour features are extracted using colour moments with QuadHistogram, whereas Grey Level Co-occurrence Matrix (GLCM) with Redundant Contourlet Transform(RCT) generated texture features, and both (colour and texture) features get fused. Then, fused features are fed into the Deep Convolutional Neural Network (DCNN), which classifies the different types of skin cancer. Finally, our proposed approach is compared with the current works. Consequently, our proposed YOLO-v3 –DCNN has greater accuracy when contrasted with the baseline techniques.

In issues pertaining to higher education, deep learning (DL), and its connection to educational data, it is crucial to forecast students’ success. The ability to predict a student’s success aids in choosing courses and developing future study schedules. Apart from forecasting children’s performance, it also assists educators and administrators in keeping an eye on pupils, offering them support, and incorporating training initiatives to maximize outcomes. Student prediction has the advantage of lowering official warning flags and removing ineffective pupils from the classroom. By helping students select courses and study schedules that are suited for their skill levels, prediction supports the students directly. In the proposed approach, a methodology based on the integration of convolutional neural network (CNN) and long short-term memory (LSTM) is proposed to optimize students’ performance prediction systems. This study utilized a student performance dataset from the UCI ML Repository. It includes information on student achievements in secondary education from two Portuguese schools. The suggested method overcomes the following three problems in model development: an imbalanced dataset, a lack of feedback mechanism to enhance the quality of learning, and an inadequate mechanism to extract the learning patterns/relevant features to predict student performance. The suggested system’s effectiveness has been demonstrated by the accuracy (98.45) and loss (0.1989) obtained to achieve the best prediction.