Recently, there has been considerable growth in the internet of things (IoT)-based healthcare applications; however, they suffer from a lack of intrusion detection systems (IDS). Leveraging recent technologies, such as machine learning (ML), edge computing, and blockchain, can provide suitable and strong security solutions for preserving the privacy of medical data. In this paper, FIDChain IDS is proposed using lightweight artificial neural networks (ANN) in a federated learning (FL) way to ensure healthcare data privacy preservation with the advances of blockchain technology that provides a distributed ledger for aggregating the local weights and then broadcasting the updated global weights after averaging, which prevents poisoning attacks and provides full transparency and immutability over the distributed system with negligible overhead. Applying the detection model at the edge protects the cloud if an attack happens, as it blocks the data from its gateway with smaller detection time and lesser computing and processing capacity as FL deals with smaller sets of data. The ANN and eXtreme Gradient Boosting (XGBoost) models were evaluated using the BoT-IoT dataset. The results show that ANN models have higher accuracy and better performance with the heterogeneity of data in IoT devices, such as intensive care unit (ICU) in healthcare systems. Testing the FIDChain with different datasets (CSE-CIC-IDS2018, Bot Net IoT, and KDD Cup 99) reveals that the BoT-IoT dataset has the most stable and accurate results for testing IoT applications, such as those used in healthcare systems.

As the economy has grown rapidly in recent years, more and more people have begun putting their money into the stock market. Thus, predicting trends in the stock market is regarded as a crucial endeavor, and one that has proven to be more fruitful than others. Profitable investments will result in rising stock prices. Investors face significant difficulties making stock market-related predictions due to the lack of movement and noise in the data. In this paper, a new system for predicting stock market prices is introduced, namely stock market prediction based on deep leaning (SMP-DL). SMP-DL splits into two stages, which are (i) data preprocessing (DP) and (ii) stock price’s prediction (SP²). In the first stage, data are preprocessed to obtain cleaned ones through several stages which are detect and reject missing value, feature selection, and data normalization. Then, in the second stage (e.g., SP²), the cleaned data will pass through the used predicted model. In SP², long short-term memory (LSTM) combined with bidirectional gated recurrent unit (BiGRU) to predict the closing price of stock market. The obtained results showed that the proposed system perform well when compared to other existing methods. As RMSE, MSE, MAE, andR²values are 0.2883, 0.0831, 0.2099, and 0.9948. Moreover, the proposed method was applied using different datasets and it performs well.

One of the most prevalent forms of cancer among women worldwide is breast cancer, the leading cause of mortality. The vital procedure of early breast cancer detection can help with the right medical care, prevent the spread of cancer cells, as well as lower the risk of death and disability. The two most prevalent techniques for correctly detecting and classifying breast cancer through the use of Computer-Aided Diagnosis (CAD) technology are artificial intelligence (AI) and machine learning (ML). This work intends to highlight the significance of applying AI for breast cancer early detection to reduce its risks. The various techniques for recognizing breast cancer are also addressed. Also, the design process of the CAD system, including pre-processing stage, segmentation, extraction of features, and feature selection, is explained. The classification methodologies for detecting breast cancer will then be evaluated.

The Smart Meter Neighborhood Area Network (SM-NAN), commonly referred to as the last mile network, is a crucial component in enabling communication within the smart grid. This network facilitates the connection between Smart Meters (SMs) and Data Aggregation Points (DAPs), responsible for gathering energy consumption and invoicing data from SMs. The placement of DAPs significantly impacts the distance and transmission lines connecting them to SMs. Our research focuses on optimizing DAP deployment to minimize mean and maximum distances between DAPs and SMs. The paper introduces a system that introduces the concept of network division and develops two techniques to address the DAP placement problem. Through extensive simulations based on actual suburban community topologies, our findings demonstrate the effectiveness of these approaches in reducing the communication gap between DAPs and connected SMs. This research presents promising ideas to enhance the efficiency and performance of the last mile network in the Smart Grid (SG). The performance of two algorithms, DPCA _avg and DPCA_ws, is compared and simulated with varying numbers of DAPs (K = 1, 2, 3, 4, 5, and 6) in the subnetwork, considering maximum and mean distance minimization, as well as the maximum number of hops per path. Results indicate that both DPCA _avg and DPCA_ws effectively reduce mean and maximum distances between DAPs and SMs, respectively. DPCA _avg achieves a maximum distance of 797.3 m, with a mean distance of 345.31 m. In contrast, DPCA_ws focuses on minimizing the maximum distance, resulting in a maximum distance of 750.3 m and a mean distance of 423.1 m when the number of DAPs is one (k = 1). DPCA_ws demonstrates an awareness of maximum distance and minimizes it, while DPCA _avg prioritizes mean distance reduction. Additionally, DPCA_ws reduces the maximum number of hops per path, further optimizing the last mile network.