The cardiovascular system is responsible for carrying the blood along with nutrition and oxygen throughout the body. This system consists of heart, blood, and blood vessels. The experts, or doctors called as cardiologists, analyze the sounds of heart’s (lub-dub) beat and flow of blood to diagnose Cardio Vascular Disease (CVD) using a traditional stethoscope and phonological cardiogram technique. Through the stethoscope, the cardiologist will listen to vibration produced by heart beat and heart beat sound and murmur sound are popularly known as phonocardiogram (PCG) signals, which are being recorded for medical diagnosis purposes using a stethoscope. The development of a technique for the automatic recognition of HVD’s assists the experts in recognizing the CVD effectively in the initial stage itself from PCG signals. There are many tools available to help doctors in a clinical setting for the accurate diagnose the CVD in a less time. The main aim of this proposed work is to provide an Artificial Intelligence (AI) based PCG signal analysis for the automatic and early detection of various cardiac conditions using supervised and unsupervised Recurrent Neural Network (RNN) based Bidirectional Long Short-Term Memory (Bi-LSTM) Machine Learning (ML) algorithm. Along with this algorithm, Generative Adversarial Networks (GAN’s) is considered because they can create fresh, high-quality, pseudo-real data that resembles their training set which has been demonstrated by using their two unique networks: Discriminator Network (DN) and the Generator Network (GN). The proposed method is tested using heart sound signals from the well-known, freely accessible PhysioNet and Kaggle datasets. The Experimental results are validated based accuracy, precision, F1-score, sensitivity, and specificity.

The development of the fifth generation (5G) and sixth generation (6G) wireless networks has gained wide spread importance in all aspects of life through the network due to their significantly higher speeds, extraordinarily low latency, and ubiquitous availability. Owing to the importance of their users, components, and services to our everyday lives, the network must secure all of these. With such a wide range of devices and service types being present in the 5G ecosystem, security issues are now much more prevalent. Security solutions, are not implemented, must already be envisioned in order to deal with a range of attacks on numerous services, cutting-edge technology, and more user information available over the network. This research proposes the dual integrated neural network (DINN) for secure data transmission in wireless networks. DINN comprises two neural networks based on sparse and dense dimensions. DINN is designed for any presence of deep learning-based attack in a physical security layer. DINN is evaluated considering the various machine learning attack such as basic_iterative_method attack, momentum_iterative_method attack, post_gradient_descent attack, and C&W attack; comparison is carried out on existing and DINN, considering attack success rate and MSE. Performance analysis suggests that DINN holds a higher level of security against the above attacks.

Cloud computing has become the most challenging research field in the current information technology scenario. In this, a set of user tasks are scheduled and allocated to numerous kinds of heterogeneous virtual machines (VMs) in cloud data centers (CDCs), and these VMs are hosted by diverse types of heterogeneous physical machines (PMs). It extends several features, encompassing elasticity, safety, sustainability, and even adequate maintenance compared to traditional data centers. There are numerous techniques available for VM scheduling and allocation. However, it still requires the existence of new mechanisms that can reduce the execution time (ET) of the tasks, improve the optimization of energy usage and resource utilization (RU), and reduce time consumption. Along with optimization, VM scheduling (VMS) and VM allocation (VMA) are two-level issues that need to be considered with essential policies to govern these mechanisms. Hence, for executing optimal VMS and VMA in the data center, new optimization methodologies, such as enhanced shark smell optimization algorithm (ESSOA) at the first level and Brownian movement-centered gravitation search algorithm (BMGSA) at the second level, are proposed in this work to define the policies. Firstly, the user requests for VMs are reserved on the most appropriate PM by the proposed ESSOA, which has the lowest execution cost within deadline limits, and the proposed BMGSA decides the allocation of the chosen VM on the most appropriate PM within the resource limitations at the second level. To demonstrate the proposed algorithm’s efficiency, the simulations are carried out using the Java language-based CloudSim simulator, and the proposed mechanism outcomes acquired are compared with the existing approaches. The simulation results show that the suggested algorithm is efficient in terms of the execution cost, degree of imbalance (DOI), make span (MS), and resource utilization (RU).

Maintaining good indoor air quality is crucial in buildings dedicated to enhancing the health and well-being of their occupants. This challenge becomes even more complex due to the diverse range of users and spaces within a single institution. Different areas, such as operating rooms and waiting rooms, require specific air quality standards, tailored to the varying health conditions of patients and visitors. Poor air quality can hinder hospital staff in performing their duties effectively and affect patients' comfort during recovery. Hospitals can now achieve indoor air quality standards cost-effectively through Internet of Things (IoT) technology. The IoT enables remote monitoring, offering greater control over indoor conditions like air quality, temperature, humidity, and dust levels. This system monitors air quality, dust concentration, temperature, and humidity within healthcare facilities, sending notifications to staff via an app and push alerts when readings exceed normal levels. It utilizes the MQ135 sensor for air quality, the GP2Y1010AU0F optical dust sensor, and the DHT11 sensor for temperature and humidity, all interfaced with NodeMCU through the Arduino IDE. Data from these sensors is stored on a cloud platform and displayed in a mobile app, with near real-time monitoring from sensors placed throughout the facility. A time-series algorithm, such as Autoregressive Integrated Moving Average (ARIMA), is used to forecast temperature and humidity trends in wards. The system alerts staff when indoor temperature exceeds 27 °C, triggers warnings when air quality surpasses 500 ppm, and issues critical alerts for levels above 650 ppm. Sensor data, sent to the cloud every 120 s, provides staff with insights to better plan actions to improve indoor air quality.

Air pollution has a significant impact on environment resulting in consequences such as global warming and acid rain. Toxic emissions from vehicles are one of the primary sources of pollution. Assessment of air pollution data is critical in order to assist residents in locating the safest areas in the city that are ideal for life. In this work, density‐based spatial clustering of applications with noise (DBSCAN) is used which is among the widely used clustering algorithms in machine learning. It is not only capable of finding clusters of various sizes and shapes but can also detect outliers. DBSCAN takes in two important input parameters—Epsilon (Eps) and Minimum Points (MinPts). Even the slightest of variations in the parameter values fed to DBSCAN makes a big difference in the clustering. There is a need to find Eps value in as minimum time as possible. In this work, the goal is to find the Eps value in less time. For this purpose, a search tree technique is used for finding the Eps input to the DBSCAN algorithm. Predicting air pollution is a complex task due to various challenges associated with the dynamic and multifaceted nature of the atmosphere such as meteorological variability, local emissions and sources, data quality and availability, and emerging pollutants. Extensive experiments prove that the search tree approach to find Eps is quicker and efficient in comparison to the widely used KNN algorithm. The time reduction to find Eps makes a significant impact as the dataset size increases. The input parameters are fed to DBSCAN algorithm to obtain clustering results.

Vision Studio aims to utilize a diverse range of modern deep learning and computer vision principles and techniques to provide a broad array of functionalities in image and video processing. Deep learning is a distinct class of machine learning algorithms that utilize multiple layers to gradually extract more advanced features from raw input. This is beneficial when using a matrix as input for pixels in a photo or frames in a video. Computer vision is a field of artificial intelligence that teaches computers to interpret and comprehend the visual domain. The main functions implemented include deepfake creation, digital ageing (de-ageing), image animation, and deepfake detection. Deepfake creation allows users to utilize deep learning methods, particularly autoencoders, to overlay source images onto a target video. This creates a video of the source person imitating or saying things that the target person does. Digital aging utilizes generative adversarial networks (GANs) to digitally simulate the aging process of an individual. Image animation utilizes first-order motion models to create highly realistic animations from a source image and driving video. Deepfake detection is achieved by using advanced and highly efficient convolutional neural networks (CNNs), primarily employing the EfficientNet family of models.