Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.

Brain tumors are a leading cause of death globally, with numerous types varying in malignancy, and only 12% of adults diagnosed with brain cancer survive beyond five years. This research introduces a hyperparametric convolutional neural network (CNN) model to identify brain tumors, with significant practical implications. By fine-tuning the hyperparameters of the CNN model, we optimize feature extraction and systematically reduce model complexity, thereby enhancing the accuracy of brain tumor diagnosis. The critical hyperparameters include batch size, layer counts, learning rate, activation functions, pooling strategies, padding, and filter size. The hyperparameter-tuned CNN model was trained on three different brain MRI datasets available at Kaggle, producing outstanding performance scores, with an average value of 97% for accuracy, precision, recall, and F1-score. Our optimized model is effective, as demonstrated by our methodical comparisons with state-of-the-art approaches. Our hyperparameter modifications enhanced the model performance and strengthened its capacity for generalization, giving medical practitioners a more accurate and effective tool for making crucial judgments regarding brain tumor diagnosis. Our model is a significant step in the right direction toward trustworthy and accurate medical diagnosis, with practical implications for improving patient outcomes.

The ubiquitous and ever-evolving nature of cyber threats demands innovative approaches that can adapt to the dynamic relationships and structures within network data. Traditional models struggle to adapt to the continuously changing nature of network traffic, where both structural dependencies and temporal evolution must be accurately captured to detect anomalies and predict future threats. To address the challenges, this research introduces V-GCN (Variational Graph Convolutional Network), a new model that integrates the probabilistic latent space modelling of Variational Autoencoders (VAEs) with the structural learning capabilities of Graph Convolutional Networks (GCNs). The proposed model is designed to capture both temporal dependencies and uncertainties inherent in dynamic networks, and as such, it is highly suitable for tasks such as link prediction and node classification. The proposed hybrid model encodes node features into a probabilistic latent space using a VAE encoder and refine the representations using GCN layers, that aggregates structural information from neighbouring nodes. The integration of variational inference with graph convolution enables V-GCN to adapt to the dynamic evolution of network traffic and measure the uncertainties in node and edge relationships. The DynKDD dataset, a dynamic adaptation of the NSL-KDD dataset, is developed in this research to evaluate the model performance. The dataset introduces temporal dynamics into the conventional NSL-KDD dataset, enabling the application of advanced graph-based learning models such as V-GCN. Experimental evaluation indicates that V-GCN significantly outperforms baseline models such as GCNs, Graph Sample and Aggregation (GraphSAGE), and Graph Attention Networks (GATs). In node classification, V-GCN achieved a 10% higher F1-score (0.845), with precision reaching 83.7%, and a balanced accuracy of 84.2%, underscoring its ability to handle uncertainty and adapt to changing network structures in dynamic environments. V-GCN achieved a 15% improvement in AUC-ROC (0.98), a 12% increase in average precision (0.9357), and a 14% higher F1-score (0.8196) in link prediction tasks compared to baseline models. The V-GCN’s integration of probabilistic modelling and graph convolution sets a new benchmark for dynamic network traffic analysis, providing a superior solution to real-world challenges in cybersecurity, social network analysis and beyond.

In the consumer space, deep fakes refer to highly realistic, AI-generated images, audio, or videos that mimic real people generated by cutting-edge technologies such as Generative Adversarial Networks (GANs). In the digital age, recognizing and detecting deepfakes is a critical problem. The most common solutions for deepfake creation are those based on GANs, which can efficiently manipulate multimedia data or create from scratch. GANs comprise two neural networks, a Generator (G) and a Discriminator (D), that concurrently work during competition. The generator generates artificial data, whereas the discriminator calculates the authenticity of generated and real data. This adversarial procedure causes the generator to generate more realistic content. Identifying deep fakes produced by GANs using deep learning (DL) includes leveraging complex neural networks to detect subtle anomalies and artefacts that GANs accidentally introduce. Convolutional Neural Network (CNN) are very effective for these tasks, as they learn to discern inconsistencies and complex features in image textures, lighting, and facial features frequently missed by human eyes. This CNN model is trained on a massive database of fake and authentic images, allowing them to detect minor defects. This study presents a Deep Feature Fusion-based Fake Face Detection Generated by Generative Adversarial Networks (DF4D-GGAN) technique for Consumer Space Environment. The goal of the DF4D-GGAN technique is to detect the presence of real or deepfake images generated by DL. In the DF4D-GGAN technique, the Gaussian filtering (GF) approach is used for preprocessing the input images. Besides, the feature fusion process uses EfficientNet-b4 and ShuffleNet. Moreover, the hyperparameter selection of the DL models is performed by an improved slime mould algorithm (ISMA). Finally, an extreme learning machine (ELM) classifier has been employed to proficiently recognize real and fake images. To validate the results of the DF4D-GGAN technique, a series of simulations were made on benchmark datasets. The results stated that the DF4D-GGAN technique gains improved results over other models.