A new computing paradigm that has been growing in computing systems is fog computing. In the healthcare industry, Internet of Things (IoT) driven fog computing is being developed to speed up the services for the general public and save billions of lives. This new computing platform, based on the fog computing paradigm, may reduce latency when transmitting and communicating signals with faraway servers, allowing medical services to be delivered more quickly in both spatial and temporal dimensions. One of the necessary qualities of computing systems that can enable the completion of healthcare operations is latency reduction. Fog computing can provide reduced latency when compared to cloud computing due to the use of only low-end computers, mobile phones, and personal devices in fog computing. In this paper, a new framework for healthcare monitoring for managing real-time notification based on fog computing has been proposed. The proposed system monitors the patient’s body temperature, heart rate, and blood pressure values obtained from the sensors that are embedded into a wearable device and notifies the doctors or caregivers in real time if there occur any contradictions in the normal threshold value using the machine learning algorithms. The notification can also be set for the patients to alert them about the periodical medications or diet to be maintained by the patients. The cloud layer stores the big data into the cloud for future references for the hospitals and the researchers.

Patients are required to be observed and treated continually in some emergency situations. However, due to time constraints, visiting the hospital to execute such tasks is challenging. This can be achieved using a remote healthcare monitoring system. The proposed system introduces an effective data science technique for IoT supported healthcare monitoring system with the rapid adoption of cloud computing that enhances the efficiency of data processing and the accessibility of data in the cloud. Many IoT sensors are employed, which collect real healthcare data. These data are retained in the cloud for the processing of data science. In the Healthcare Monitoring-Data Science Technique (HM-DST), initially, an altered data science technique is introduced. This algorithm is known as the Improved Pigeon Optimization (IPO) algorithm, which is employed for grouping the stored data in the cloud, which helps in improving the prediction rate. Next, the optimum feature selection technique for extraction and selection of features is illustrated. A Backtracking Search-Based Deep Neural Network (BS-DNN) is utilized for classifying human healthcare. The proposed system’s performance is finally examined with various healthcare datasets of real time and the variations are observed with the available smart healthcare systems for monitoring.

Cardiac arrhythmia is an illness in which a heartbeat is erratic, either too slow or too rapid. It happens as a result of faulty electrical impulses that coordinate the heartbeats. Sudden cardiac death can occur as a result of certain serious arrhythmia disorders. As a result, the primary goal of electrocardiogram (ECG) investigation is to reliably perceive arrhythmias as life‐threatening to provide a suitable therapy and save lives. ECG signals are waveforms that denote the electrical movement of the human heart (P, QRS, and T). The duration, structure, and distances between various peaks of each waveform are utilized to identify heart problems. The signals’ autoregressive (AR) analysis is then used to obtain a specific selection of signal features, the parameters of the AR signal model. Groups of retrieved AR characteristics for three various ECG kinds are cleanly separated in the training dataset, providing high connection classification and heart problem diagnosis to each ECG signal within the training dataset. A new technique based on two‐event‐related moving averages (TERMAs) and fractional Fourier transform (FFT) algorithms is suggested to better evaluate ECG signals. This study could help researchers examine the current state‐of‐the‐art approaches employed in the detection of arrhythmia situations. The characteristic of our suggested machine learning approach is cross‐database training and testing with improved characteristics.

Since the Pre-Roman era, olive trees have a significant economic and cultural value. In 2019, the Al-Jouf region, in the north of the Kingdom of Saudi Arabia, gained a global presence by entering the Guinness World Records, with the largest number of olive trees in the world. Olive tree detecting and counting from a given satellite image are a significant and difficult computer vision problem. Because olive farms are spread out over a large area, manually counting the trees is impossible. Moreover, accurate automatic detection and counting of olive trees in satellite images have many challenges such as scale variations, weather changes, perspective distortions, and orientation changes. Another problem is the lack of a standard database of olive trees available for deep learning applications. To address these problems, we first build a large-scale olive dataset dedicated to deep learning research and applications. The dataset consists of 230 RGB images collected over the territory of Al-Jouf, KSA. We then propose an efficient deep learning model (SwinTUnet) for detecting and counting olive trees from satellite imagery. The proposed SwinTUnet is a Unet-like network which consists of an encoder, a decoder, and skip connections. Swin Transformer block is the fundamental unit of SwinTUnet to learn local and global semantic information. The results of an experimental study on the proposed dataset show that the SwinTUnet model outperforms the related studies in terms of overall detection with a 0.94% estimation error.

Indoor localization methods can help many sectors, such as healthcare centers, smart homes, museums, warehouses, and retail malls, improve their service areas. As a result, it is crucial to look for low-cost methods that can provide exact localization in indoor locations. In this context, image-based localization methods can play an important role in estimating both the position and the orientation of cameras regarding an object. Image-based localization faces many issues, such as image scale and rotation variance. Also, image-based localization’s accuracy and speed (latency) are two critical factors. This paper proposes an efficient 6-DoF deep-learning model for image-based localization. This model incorporates the channel attention module and the Scale Pyramid Module (SPM). It not only enhances accuracy but also ensures the model’s real-time performance. In complex scenes, a channel attention module is employed to distinguish between the textures of the foregrounds and backgrounds. Our model adapted an SPM, a feature pyramid module for dealing with image scale and rotation variance issues. Furthermore, the proposed model employs two regressions (two fully connected layers), one for position and the other for orientation, which increases outcome accuracy. Experiments on standard indoor and outdoor datasets show that the proposed model has a significantly lower Mean Squared Error (MSE) for both position and orientation. On the indoor 7-Scenes dataset, the MSE for the position is reduced to 0.19 m and 6.25° for the orientation. Furthermore, on the outdoor Cambridge landmarks dataset, the MSE for the position is reduced to 0.63 m and 2.03° for the orientation. According to the findings, the proposed approach is superior and more successful than the baseline methods.