With an aging population and increased chronic diseases, remote health monitoring has become critical to improving patient care and reducing healthcare costs. The Internet of Things (IoT) has recently drawn much interest as a potential remote health monitoring remedy. IoT-based systems can gather and analyze a wide range of physiological data, including blood oxygen levels, heart rates, body temperatures, and ECG signals, and then provide real-time feedback to medical professionals so they may take appropriate action. This paper proposes an IoT-based system for remote monitoring and early detection of health problems in home clinical settings. The system comprises three sensor types: MAX30100 for measuring blood oxygen level and heart rate; AD8232 ECG sensor module for ECG signal data; and MLX90614 non-contact infrared sensor for body temperature. The collected data is transmitted to a server using the MQTT protocol. A pre-trained deep learning model based on a convolutional neural network with an attention layer is used on the server to classify potential diseases. The system can detect five different categories of heartbeats: Normal Beat, Supraventricular premature beat, Premature ventricular contraction, Fusion of ventricular, and Unclassifiable beat from ECG sensor data and fever or non-fever from body temperature. Furthermore, the system provides a report on the patient’s heart rate and oxygen level, indicating whether they are within normal ranges or not. The system automatically connects the user to the nearest doctor for further diagnosis if any critical abnormalities are detected.

Artificial Intelligence (AI) is a key component in Industry 4.0. Rotating machines are critical components in manufacturing industries. In the vast world of Industry 4.0, where an IoT network acts as a monitoring and decision-making system, predictive maintenance is quickly gaining importance. Predictive maintenance is a method that uses AI to handle potential problems before they cause breakdowns in operations, processes or systems. However, there is a significant issue with the AI models’ (also known as "black boxes") inability to explain their decisions. This interpretability is vital for making maintenance decisions and validating the model’s reliability, leading to improved trust and acceptance of AI-driven predictive maintenance strategies. Explainable AI is the solution because it provides human-understandable insights into how the AI model arrives at its predictions. In this regard, the paper presents Explainable AI-based predictive maintenance of Industrial rotating machines. The proposed approach unfolds in four comprehensive stages: a) Multi-sensor based multi-fault (5 different fault classes) data acquisition, b) Frequency-domain statistical feature extraction, c) Comparison of results for multiple AI algorithms, and d) XAI integration using "Local Interpretable Model Agnostic Explanation (LIME)", "SHapley Additive exPlanation (SHAP)", "Partial Dependence Plot (PDP)" and "Individual Conditional Expectation (ICE)" to interpret the results.

In the rapidly evolving realm of cloud computing security, this paper introduces an innovative solution to address persistent challenges. The proliferation of cloud technology has brought forth heightened concerns regarding data security, necessitating novel approaches to safeguarding sensitive information. The issue centers on the vulnerability of cloud-stored data, often necessitating enhanced encryption and key management strategies. Traditional methods often fall short in mitigating risks associated with compromised encryption keys and centralized key storage. To combat these challenges, our proposed solution encompasses a two-phase approach. In the first phase, dynamic Advanced Encryption Standard (AES) keys are generated, ensuring each file’s encryption with a unique and ever-changing key. This approach significantly enhances file-level security, curtailing an attacker’s ability to decrypt multiple files even if a key is compromised. The second phase introduces blockchain technology, where keys are securely stored with accompanying metadata, bolstering security and data integrity. Elliptic Curve Cryptography (ECC) public key encryption enhances security during transmission and storage, while also facilitating secure file sharing. In conclusion, this comprehensive approach enhances cloud security, providing robust encryption, decentralized key management, and protection against unauthorized access. Its scalability and adaptability make it a valuable asset in contemporary cloud security paradigms, assuring users of data security in the cloud.

Cyber attacks are growing with the rapid development and wide use of internet technology. Botnet attack emerged as one of the most harmful attacks. Botnet identification is becoming challenging due to the numerous attack vectors and the ongoing evolution of viruses. As the Internet of Things (IoT) technology is developing rapidly, many network devices have been subject to botnet attacks leading to substantial losses in different sectors. Botnets pose serious risks to network security and deep learning models have shown potential for efficiently identifying botnet activity from network traffic data. In this research, a botnet identification system is proposed based on the stacking of artificial neural network (ANN), convolutional neural network (CNN), long short-term memory (LSTM), and recurrent neural network (RNN) (ACLR). The experiments are conducted by employing both the individual models, as well as, the proposed ACLR model for performance comparison. The UNSW-NB15 dataset is used for botnet attacks and contains nine different attack types including ’Normal’, ’Generic’, ’Exploits’, ’Fuzzers’, ’DoS’, ’Reconnaissance’, ’Analysis’, ’Backdoor’, ’Shell code’ and ’Worms’. Experimental results indicate the proposed ACLR model gains 0.9698 testing accuracy showing that it is successful in capturing the intricate patterns and characteristics of botnet attacks. The proposed ACLR model’s k values (3, 5, 7, and 10) for a K-fold cross-validation accuracy score is 0.9749 indicating that the model’s robustness and generalizability are demonstrated by k = 5. In addition, the proposed model detects botnets with a high receiver operating characteristic area under the curve (ROC-AUC) of 0.9934 and a precision-recall area under the curve (PR-AUC) of 0.9950. Performance comparison with existing state-of-the-art models further corroborates the superior performance of the proposed approach. The results of this research can be helpful against evolving threats and enhance cyber security procedures.

Thyroid disease has been on the rise during the past few years. Owing to its importance in metabolism, early detection of thyroid disease is a task of critical importance. Despite several existing works on thyroid disease detection, the problem of class imbalance is not investigated very well. In addition, existing studies predominantly focus on the binary-class problem. This study aims to solve these issues by the proposed approach where ten types of thyroid diseases are considered. The proposed approach uses a differential evolution (DE)-based optimization algorithm to fine-tune the parameters of machine learning models. Moreover, conditional generative adversarial networks are used for data augmentation. Several sets of experiments are carried out to analyze the performance of the proposed approach with and without model optimization. Results suggest that a 0.998 accuracy score can be obtained using AdaBoost with DE optimization which is better than existing state-of-the-art models.

Machine learning has significantly improved disease diagnosis, enhancing the efficiency and accuracy of the healthcare system. One critical area where it proves beneficial is diagnosing brain tumors, a life-threatening disease, where early and accurate predictions can save lives. This study focuses on deploying a machine learning-based approach for brain tumor detection, utilizing Magnetic Resonance Imaging (MRI) features. We train the proposed model using 3D-UNet and 2D-UNet segmentation features extracted from MRI, encompassing shape, statistics, gray level size zone matrix, gray level dependence matrix, gray level co-occurrence matrix, and gray level run length matrix values. To improve performance, we propose a hybrid model that combines the strengths of two machine learning models, K-nearest neighbor (KNN) and gradient boosting classifier (GBC), using soft voting criteria. We combine them because, in cases where KNN exhibits poor performance for certain data points, GBC demonstrates significant performance, and vice versa, where GBC shows poor results, KNN performs significantly better. With 2D-UNet segmentation features, the model achieves a 64% accuracy. By training it on 3D-UNet segmentation features, we achieve a significant accuracy of 71% which surpasses existing state-of-the-art models that utilize 3D-UNet segmentation features.